thibaud frere commited on
Commit
d15ea6f
·
1 Parent(s): 36d62ce

update template

Browse files
Files changed (42) hide show
  1. app/.astro/astro/content.d.ts +204 -0
  2. app/astro.config.mjs +12 -132
  3. app/package-lock.json +0 -0
  4. app/package.json +0 -0
  5. app/plugins/rehype/code-copy-and-label.mjs +129 -0
  6. app/plugins/rehype/post-citation.mjs +441 -0
  7. app/plugins/rehype/restore-at-in-code.mjs +22 -0
  8. app/plugins/rehype/wrap-tables.mjs +43 -0
  9. app/plugins/remark/ignore-citations-in-code.mjs +21 -0
  10. app/postcss.config.mjs +14 -0
  11. app/src/components/Accordion.astro +27 -8
  12. app/src/components/Footer.astro +164 -16
  13. app/src/components/Hero.astro +174 -41
  14. app/src/components/HtmlEmbed.astro +44 -10
  15. app/src/components/Note.astro +33 -14
  16. app/src/components/ResponsiveImage.astro +213 -0
  17. app/src/components/Sidenote.astro +28 -3
  18. app/src/components/TableOfContents.astro +396 -0
  19. app/src/components/ThemeToggle.astro +7 -0
  20. app/src/content/article.mdx +20 -8
  21. app/src/content/assets/data/against_baselines.csv +3 -961
  22. app/src/content/assets/data/all_ratings_luis.csv +3 -1201
  23. app/src/content/assets/data/formatting_filters.csv +3 -1201
  24. app/src/content/assets/data/internal_deduplication.csv +3 -729
  25. app/src/content/assets/data/relevance_filters.csv +3 -1201
  26. app/src/content/assets/data/remove_ch.csv +3 -455
  27. app/src/content/assets/data/s25_ratings.csv +3 -1189
  28. app/src/content/assets/data/ss_vs_s1.csv +3 -481
  29. app/src/env.d.ts +13 -1
  30. app/src/pages/index.astro +91 -316
  31. app/src/styles/_base.css +11 -219
  32. app/src/styles/_layout.css +91 -75
  33. app/src/styles/_print.css +68 -0
  34. app/src/styles/_reset.css +13 -0
  35. app/src/styles/_variables.css +64 -23
  36. app/src/styles/components/_button.css +58 -0
  37. app/src/styles/components/_code.css +111 -49
  38. app/src/styles/components/_footer.css +0 -56
  39. app/src/styles/components/_poltly.css +0 -44
  40. app/src/styles/components/_table.css +95 -0
  41. app/src/styles/components/_tag.css +14 -0
  42. app/src/styles/global.css +20 -49
app/.astro/astro/content.d.ts CHANGED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ declare module 'astro:content' {
2
+ interface Render {
3
+ '.mdx': Promise<{
4
+ Content: import('astro').MarkdownInstance<{}>['Content'];
5
+ headings: import('astro').MarkdownHeading[];
6
+ remarkPluginFrontmatter: Record<string, any>;
7
+ components: import('astro').MDXInstance<{}>['components'];
8
+ }>;
9
+ }
10
+ }
11
+
12
+ declare module 'astro:content' {
13
+ interface RenderResult {
14
+ Content: import('astro/runtime/server/index.js').AstroComponentFactory;
15
+ headings: import('astro').MarkdownHeading[];
16
+ remarkPluginFrontmatter: Record<string, any>;
17
+ }
18
+ interface Render {
19
+ '.md': Promise<RenderResult>;
20
+ }
21
+
22
+ export interface RenderedContent {
23
+ html: string;
24
+ metadata?: {
25
+ imagePaths: Array<string>;
26
+ [key: string]: unknown;
27
+ };
28
+ }
29
+ }
30
+
31
+ declare module 'astro:content' {
32
+ type Flatten<T> = T extends { [K: string]: infer U } ? U : never;
33
+
34
+ export type CollectionKey = keyof AnyEntryMap;
35
+ export type CollectionEntry<C extends CollectionKey> = Flatten<AnyEntryMap[C]>;
36
+
37
+ export type ContentCollectionKey = keyof ContentEntryMap;
38
+ export type DataCollectionKey = keyof DataEntryMap;
39
+
40
+ type AllValuesOf<T> = T extends any ? T[keyof T] : never;
41
+ type ValidContentEntrySlug<C extends keyof ContentEntryMap> = AllValuesOf<
42
+ ContentEntryMap[C]
43
+ >['slug'];
44
+
45
+ /** @deprecated Use `getEntry` instead. */
46
+ export function getEntryBySlug<
47
+ C extends keyof ContentEntryMap,
48
+ E extends ValidContentEntrySlug<C> | (string & {}),
49
+ >(
50
+ collection: C,
51
+ // Note that this has to accept a regular string too, for SSR
52
+ entrySlug: E,
53
+ ): E extends ValidContentEntrySlug<C>
54
+ ? Promise<CollectionEntry<C>>
55
+ : Promise<CollectionEntry<C> | undefined>;
56
+
57
+ /** @deprecated Use `getEntry` instead. */
58
+ export function getDataEntryById<C extends keyof DataEntryMap, E extends keyof DataEntryMap[C]>(
59
+ collection: C,
60
+ entryId: E,
61
+ ): Promise<CollectionEntry<C>>;
62
+
63
+ export function getCollection<C extends keyof AnyEntryMap, E extends CollectionEntry<C>>(
64
+ collection: C,
65
+ filter?: (entry: CollectionEntry<C>) => entry is E,
66
+ ): Promise<E[]>;
67
+ export function getCollection<C extends keyof AnyEntryMap>(
68
+ collection: C,
69
+ filter?: (entry: CollectionEntry<C>) => unknown,
70
+ ): Promise<CollectionEntry<C>[]>;
71
+
72
+ export function getEntry<
73
+ C extends keyof ContentEntryMap,
74
+ E extends ValidContentEntrySlug<C> | (string & {}),
75
+ >(entry: {
76
+ collection: C;
77
+ slug: E;
78
+ }): E extends ValidContentEntrySlug<C>
79
+ ? Promise<CollectionEntry<C>>
80
+ : Promise<CollectionEntry<C> | undefined>;
81
+ export function getEntry<
82
+ C extends keyof DataEntryMap,
83
+ E extends keyof DataEntryMap[C] | (string & {}),
84
+ >(entry: {
85
+ collection: C;
86
+ id: E;
87
+ }): E extends keyof DataEntryMap[C]
88
+ ? Promise<DataEntryMap[C][E]>
89
+ : Promise<CollectionEntry<C> | undefined>;
90
+ export function getEntry<
91
+ C extends keyof ContentEntryMap,
92
+ E extends ValidContentEntrySlug<C> | (string & {}),
93
+ >(
94
+ collection: C,
95
+ slug: E,
96
+ ): E extends ValidContentEntrySlug<C>
97
+ ? Promise<CollectionEntry<C>>
98
+ : Promise<CollectionEntry<C> | undefined>;
99
+ export function getEntry<
100
+ C extends keyof DataEntryMap,
101
+ E extends keyof DataEntryMap[C] | (string & {}),
102
+ >(
103
+ collection: C,
104
+ id: E,
105
+ ): E extends keyof DataEntryMap[C]
106
+ ? Promise<DataEntryMap[C][E]>
107
+ : Promise<CollectionEntry<C> | undefined>;
108
+
109
+ /** Resolve an array of entry references from the same collection */
110
+ export function getEntries<C extends keyof ContentEntryMap>(
111
+ entries: {
112
+ collection: C;
113
+ slug: ValidContentEntrySlug<C>;
114
+ }[],
115
+ ): Promise<CollectionEntry<C>[]>;
116
+ export function getEntries<C extends keyof DataEntryMap>(
117
+ entries: {
118
+ collection: C;
119
+ id: keyof DataEntryMap[C];
120
+ }[],
121
+ ): Promise<CollectionEntry<C>[]>;
122
+
123
+ export function render<C extends keyof AnyEntryMap>(
124
+ entry: AnyEntryMap[C][string],
125
+ ): Promise<RenderResult>;
126
+
127
+ export function reference<C extends keyof AnyEntryMap>(
128
+ collection: C,
129
+ ): import('astro/zod').ZodEffects<
130
+ import('astro/zod').ZodString,
131
+ C extends keyof ContentEntryMap
132
+ ? {
133
+ collection: C;
134
+ slug: ValidContentEntrySlug<C>;
135
+ }
136
+ : {
137
+ collection: C;
138
+ id: keyof DataEntryMap[C];
139
+ }
140
+ >;
141
+ // Allow generic `string` to avoid excessive type errors in the config
142
+ // if `dev` is not running to update as you edit.
143
+ // Invalid collection names will be caught at build time.
144
+ export function reference<C extends string>(
145
+ collection: C,
146
+ ): import('astro/zod').ZodEffects<import('astro/zod').ZodString, never>;
147
+
148
+ type ReturnTypeOrOriginal<T> = T extends (...args: any[]) => infer R ? R : T;
149
+ type InferEntrySchema<C extends keyof AnyEntryMap> = import('astro/zod').infer<
150
+ ReturnTypeOrOriginal<Required<ContentConfig['collections'][C]>['schema']>
151
+ >;
152
+
153
+ type ContentEntryMap = {
154
+ "chapters": {
155
+ "available-blocks.mdx": {
156
+ id: "available-blocks.mdx";
157
+ slug: "available-blocks";
158
+ body: string;
159
+ collection: "chapters";
160
+ data: any
161
+ } & { render(): Render[".mdx"] };
162
+ "best-pratices.mdx": {
163
+ id: "best-pratices.mdx";
164
+ slug: "best-pratices";
165
+ body: string;
166
+ collection: "chapters";
167
+ data: any
168
+ } & { render(): Render[".mdx"] };
169
+ "getting-started.mdx": {
170
+ id: "getting-started.mdx";
171
+ slug: "getting-started";
172
+ body: string;
173
+ collection: "chapters";
174
+ data: any
175
+ } & { render(): Render[".mdx"] };
176
+ "writing-your-content.mdx": {
177
+ id: "writing-your-content.mdx";
178
+ slug: "writing-your-content";
179
+ body: string;
180
+ collection: "chapters";
181
+ data: any
182
+ } & { render(): Render[".mdx"] };
183
+ };
184
+
185
+ };
186
+
187
+ type DataEntryMap = {
188
+ "assets": Record<string, {
189
+ id: string;
190
+ collection: "assets";
191
+ data: any;
192
+ }>;
193
+ "embeds": Record<string, {
194
+ id: string;
195
+ collection: "embeds";
196
+ data: any;
197
+ }>;
198
+
199
+ };
200
+
201
+ type AnyEntryMap = ContentEntryMap & DataEntryMap;
202
+
203
+ export type ContentConfig = never;
204
+ }
app/astro.config.mjs CHANGED
@@ -8,137 +8,14 @@ import remarkFootnotes from 'remark-footnotes';
8
  import rehypeSlug from 'rehype-slug';
9
  import rehypeAutolinkHeadings from 'rehype-autolink-headings';
10
  import rehypeCitation from 'rehype-citation';
 
 
 
 
 
11
  // Built-in Shiki (dual themes) — no rehype-pretty-code
12
 
13
- // Minimal rehype plugin to wrap code blocks with a copy button and a language label
14
- function rehypeCodeCopyAndLabel() {
15
- return (tree) => {
16
- // Walk the tree; lightweight visitor to find <pre><code>
17
- const visit = (node, parent) => {
18
- if (!node || typeof node !== 'object') return;
19
- const children = Array.isArray(node.children) ? node.children : [];
20
- if (node.tagName === 'pre' && children.some(c => c.tagName === 'code')) {
21
- // Find code child and guess language
22
- const code = children.find(c => c.tagName === 'code');
23
- const collectClasses = (val) => Array.isArray(val) ? val.map(String) : (typeof val === 'string' ? String(val).split(/\s+/) : []);
24
- const fromClass = (names) => {
25
- const hit = names.find((n) => /^language-/.test(String(n)));
26
- return hit ? String(hit).replace(/^language-/, '') : '';
27
- };
28
- const codeClasses = collectClasses(code?.properties?.className);
29
- const preClasses = collectClasses(node?.properties?.className);
30
- const candidates = [
31
- code?.properties?.['data-language'],
32
- fromClass(codeClasses),
33
- node?.properties?.['data-language'],
34
- fromClass(preClasses),
35
- ];
36
- let lang = candidates.find(Boolean) || '';
37
- const lower = String(lang).toLowerCase();
38
- const toExt = (s) => {
39
- switch (String(s).toLowerCase()) {
40
- case 'typescript': case 'ts': return 'ts';
41
- case 'tsx': return 'tsx';
42
- case 'javascript': case 'js': case 'node': return 'js';
43
- case 'jsx': return 'jsx';
44
- case 'python': case 'py': return 'py';
45
- case 'bash': case 'shell': case 'sh': return 'sh';
46
- case 'markdown': case 'md': return 'md';
47
- case 'yaml': case 'yml': return 'yml';
48
- case 'html': return 'html';
49
- case 'css': return 'css';
50
- case 'json': return 'json';
51
- default: return lower || '';
52
- }
53
- };
54
- const ext = toExt(lower);
55
- const displayLang = ext ? String(ext).toUpperCase() : '';
56
- // Determine if single-line block: prefer Shiki lines, then text content
57
- const countLinesFromShiki = () => {
58
- const isLineEl = (el) => el && el.type === 'element' && el.tagName === 'span' && Array.isArray(el.properties?.className) && el.properties.className.includes('line');
59
- const hasNonWhitespaceText = (node) => {
60
- if (!node) return false;
61
- if (node.type === 'text') return /\S/.test(String(node.value || ''));
62
- const kids = Array.isArray(node.children) ? node.children : [];
63
- return kids.some(hasNonWhitespaceText);
64
- };
65
- const collectLines = (node, acc) => {
66
- if (!node || typeof node !== 'object') return;
67
- if (isLineEl(node)) acc.push(node);
68
- const kids = Array.isArray(node.children) ? node.children : [];
69
- kids.forEach((k) => collectLines(k, acc));
70
- };
71
- const lines = [];
72
- collectLines(code, lines);
73
- const nonEmpty = lines.filter((ln) => hasNonWhitespaceText(ln)).length;
74
- return nonEmpty || 0;
75
- };
76
- const countLinesFromText = () => {
77
- // Parse raw text content of the <code> node including nested spans
78
- const extractText = (node) => {
79
- if (!node) return '';
80
- if (node.type === 'text') return String(node.value || '');
81
- const kids = Array.isArray(node.children) ? node.children : [];
82
- return kids.map(extractText).join('');
83
- };
84
- const raw = extractText(code);
85
- if (!raw || !/\S/.test(raw)) return 0;
86
- return raw.split('\n').filter(line => /\S/.test(line)).length;
87
- };
88
- const lines = countLinesFromShiki() || countLinesFromText();
89
- const isSingleLine = lines <= 1;
90
- // Also treat code blocks shorter than a threshold as single-line (defensive)
91
- if (!isSingleLine) {
92
- const approxChars = (() => {
93
- const extract = (n) => Array.isArray(n?.children) ? n.children.map(extract).join('') : (n?.type === 'text' ? String(n.value||'') : '');
94
- return extract(code).length;
95
- })();
96
- if (approxChars < 6) {
97
- // e.g., "npm i" alone
98
- // downgrade to single-line behavior
99
- node.__forceSingle = true;
100
- }
101
- }
102
- // Ensure CSS-only label works: set data-language on <code> and <pre>, and wrapper
103
- code.properties = code.properties || {};
104
- if (ext) code.properties['data-language'] = ext;
105
- node.properties = node.properties || {};
106
- if (ext) node.properties['data-language'] = ext;
107
- // Replace <pre> with wrapper div.code-card containing button + pre
108
- const wrapper = {
109
- type: 'element',
110
- tagName: 'div',
111
- properties: { className: ['code-card'].concat((isSingleLine || node.__forceSingle) ? ['no-copy'] : []), 'data-language': ext },
112
- children: (isSingleLine || node.__forceSingle) ? [ node ] : [
113
- {
114
- type: 'element',
115
- tagName: 'button',
116
- properties: { className: ['code-copy', 'button--ghost'], type: 'button', 'aria-label': 'Copy code' },
117
- children: [
118
- {
119
- type: 'element',
120
- tagName: 'svg',
121
- properties: { viewBox: '0 0 24 24', 'aria-hidden': 'true', focusable: 'false' },
122
- children: [
123
- { type: 'element', tagName: 'path', properties: { d: 'M16 1H4c-1.1 0-2 .9-2 2v12h2V3h12V1zm3 4H8c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h11c1.1 0 2-.9 2-2V7c0-1.1-.9-2-2-2zm0 16H8V7h11v14z' }, children: [] }
124
- ]
125
- }
126
- ]
127
- },
128
- node
129
- ]
130
- };
131
- if (parent && Array.isArray(parent.children)) {
132
- const idx = parent.children.indexOf(node);
133
- if (idx !== -1) parent.children[idx] = wrapper;
134
- }
135
- return; // don't visit nested
136
- }
137
- children.forEach((c) => visit(c, node));
138
- };
139
- visit(tree, null);
140
- };
141
- }
142
 
143
  export default defineConfig({
144
  output: 'static',
@@ -165,6 +42,7 @@ export default defineConfig({
165
  }
166
  },
167
  remarkPlugins: [
 
168
  remarkMath,
169
  [remarkFootnotes, { inlineNotes: true }]
170
  ],
@@ -174,10 +52,12 @@ export default defineConfig({
174
  rehypeKatex,
175
  [rehypeCitation, {
176
  bibliography: 'src/content/bibliography.bib',
177
- linkCitations: true,
178
- csl: 'vancouver'
179
  }],
180
- rehypeCodeCopyAndLabel
 
 
 
181
  ]
182
  }
183
  });
 
8
  import rehypeSlug from 'rehype-slug';
9
  import rehypeAutolinkHeadings from 'rehype-autolink-headings';
10
  import rehypeCitation from 'rehype-citation';
11
+ import rehypeCodeCopyAndLabel from './plugins/rehype/code-copy-and-label.mjs';
12
+ import rehypeReferencesAndFootnotes from './plugins/rehype/post-citation.mjs';
13
+ import remarkIgnoreCitationsInCode from './plugins/remark/ignore-citations-in-code.mjs';
14
+ import rehypeRestoreAtInCode from './plugins/rehype/restore-at-in-code.mjs';
15
+ import rehypeWrapTables from './plugins/rehype/wrap-tables.mjs';
16
  // Built-in Shiki (dual themes) — no rehype-pretty-code
17
 
18
+ // Plugins moved to app/plugins/*
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
 
20
  export default defineConfig({
21
  output: 'static',
 
42
  }
43
  },
44
  remarkPlugins: [
45
+ remarkIgnoreCitationsInCode,
46
  remarkMath,
47
  [remarkFootnotes, { inlineNotes: true }]
48
  ],
 
52
  rehypeKatex,
53
  [rehypeCitation, {
54
  bibliography: 'src/content/bibliography.bib',
55
+ linkCitations: true
 
56
  }],
57
+ rehypeReferencesAndFootnotes,
58
+ rehypeRestoreAtInCode,
59
+ rehypeCodeCopyAndLabel,
60
+ rehypeWrapTables
61
  ]
62
  }
63
  });
app/package-lock.json CHANGED
Binary files a/app/package-lock.json and b/app/package-lock.json differ
 
app/package.json CHANGED
Binary files a/app/package.json and b/app/package.json differ
 
app/plugins/rehype/code-copy-and-label.mjs ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // Minimal rehype plugin to wrap code blocks with a copy button and a language label
2
+ // Exported as a standalone module to keep astro.config.mjs lean
3
+ export default function rehypeCodeCopyAndLabel() {
4
+ return (tree) => {
5
+ // Walk the tree; lightweight visitor to find <pre><code>
6
+ const visit = (node, parent) => {
7
+ if (!node || typeof node !== 'object') return;
8
+ const children = Array.isArray(node.children) ? node.children : [];
9
+ if (node.tagName === 'pre' && children.some(c => c.tagName === 'code')) {
10
+ // Find code child and guess language
11
+ const code = children.find(c => c.tagName === 'code');
12
+ const collectClasses = (val) => Array.isArray(val) ? val.map(String) : (typeof val === 'string' ? String(val).split(/\s+/) : []);
13
+ const fromClass = (names) => {
14
+ const hit = names.find((n) => /^language-/.test(String(n)));
15
+ return hit ? String(hit).replace(/^language-/, '') : '';
16
+ };
17
+ const codeClasses = collectClasses(code?.properties?.className);
18
+ const preClasses = collectClasses(node?.properties?.className);
19
+ const candidates = [
20
+ code?.properties?.['data-language'],
21
+ fromClass(codeClasses),
22
+ node?.properties?.['data-language'],
23
+ fromClass(preClasses),
24
+ ];
25
+ let lang = candidates.find(Boolean) || '';
26
+ const lower = String(lang).toLowerCase();
27
+ const toExt = (s) => {
28
+ switch (String(s).toLowerCase()) {
29
+ case 'typescript': case 'ts': return 'ts';
30
+ case 'tsx': return 'tsx';
31
+ case 'javascript': case 'js': case 'node': return 'js';
32
+ case 'jsx': return 'jsx';
33
+ case 'python': case 'py': return 'py';
34
+ case 'bash': case 'shell': case 'sh': return 'sh';
35
+ case 'markdown': case 'md': return 'md';
36
+ case 'yaml': case 'yml': return 'yml';
37
+ case 'html': return 'html';
38
+ case 'css': return 'css';
39
+ case 'json': return 'json';
40
+ default: return lower || '';
41
+ }
42
+ };
43
+ const ext = toExt(lower);
44
+ // Determine if single-line block: prefer Shiki lines, then text content
45
+ const countLinesFromShiki = () => {
46
+ const isLineEl = (el) => el && el.type === 'element' && el.tagName === 'span' && Array.isArray(el.properties?.className) && el.properties.className.includes('line');
47
+ const hasNonWhitespaceText = (node) => {
48
+ if (!node) return false;
49
+ if (node.type === 'text') return /\S/.test(String(node.value || ''));
50
+ const kids = Array.isArray(node.children) ? node.children : [];
51
+ return kids.some(hasNonWhitespaceText);
52
+ };
53
+ const collectLines = (node, acc) => {
54
+ if (!node || typeof node !== 'object') return;
55
+ if (isLineEl(node)) acc.push(node);
56
+ const kids = Array.isArray(node.children) ? node.children : [];
57
+ kids.forEach((k) => collectLines(k, acc));
58
+ };
59
+ const lines = [];
60
+ collectLines(code, lines);
61
+ const nonEmpty = lines.filter((ln) => hasNonWhitespaceText(ln)).length;
62
+ return nonEmpty || 0;
63
+ };
64
+ const countLinesFromText = () => {
65
+ // Parse raw text content of the <code> node including nested spans
66
+ const extractText = (node) => {
67
+ if (!node) return '';
68
+ if (node.type === 'text') return String(node.value || '');
69
+ const kids = Array.isArray(node.children) ? node.children : [];
70
+ return kids.map(extractText).join('');
71
+ };
72
+ const raw = extractText(code);
73
+ if (!raw || !/\S/.test(raw)) return 0;
74
+ return raw.split('\n').filter(line => /\S/.test(line)).length;
75
+ };
76
+ const lines = countLinesFromShiki() || countLinesFromText();
77
+ const isSingleLine = lines <= 1;
78
+ // Also treat code blocks shorter than a threshold as single-line (defensive)
79
+ if (!isSingleLine) {
80
+ const approxChars = (() => {
81
+ const extract = (n) => Array.isArray(n?.children) ? n.children.map(extract).join('') : (n?.type === 'text' ? String(n.value||'') : '');
82
+ return extract(code).length;
83
+ })();
84
+ if (approxChars < 6) {
85
+ node.__forceSingle = true;
86
+ }
87
+ }
88
+ // Ensure CSS-only label works: set data-language on <code> and <pre>, and wrapper
89
+ code.properties = code.properties || {};
90
+ if (ext) code.properties['data-language'] = ext;
91
+ node.properties = node.properties || {};
92
+ if (ext) node.properties['data-language'] = ext;
93
+ // Replace <pre> with wrapper div.code-card containing button + pre
94
+ const wrapper = {
95
+ type: 'element',
96
+ tagName: 'div',
97
+ properties: { className: ['code-card'].concat((isSingleLine || node.__forceSingle) ? ['no-copy'] : []), 'data-language': ext },
98
+ children: (isSingleLine || node.__forceSingle) ? [ node ] : [
99
+ {
100
+ type: 'element',
101
+ tagName: 'button',
102
+ properties: { className: ['code-copy', 'button--ghost'], type: 'button', 'aria-label': 'Copy code' },
103
+ children: [
104
+ {
105
+ type: 'element',
106
+ tagName: 'svg',
107
+ properties: { viewBox: '0 0 24 24', 'aria-hidden': 'true', focusable: 'false' },
108
+ children: [
109
+ { type: 'element', tagName: 'path', properties: { d: 'M16 1H4c-1.1 0-2 .9-2 2v12h2V3h12V1zm3 4H8c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h11c1.1 0 2-.9 2-2V7c0-1.1-.9-2-2-2zm0 16H8V7h11v14z' }, children: [] }
110
+ ]
111
+ }
112
+ ]
113
+ },
114
+ node
115
+ ]
116
+ };
117
+ if (parent && Array.isArray(parent.children)) {
118
+ const idx = parent.children.indexOf(node);
119
+ if (idx !== -1) parent.children[idx] = wrapper;
120
+ }
121
+ return; // don't visit nested
122
+ }
123
+ children.forEach((c) => visit(c, node));
124
+ };
125
+ visit(tree, null);
126
+ };
127
+ }
128
+
129
+
app/plugins/rehype/post-citation.mjs ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // rehype plugin to post-process citations and footnotes at build-time
2
+ // - Normalizes the bibliography into <ol class="references"> with <li id="...">
3
+ // - Linkifies DOI/URL occurrences inside references
4
+ // - Appends back-reference links (↩ back: 1, 2, ...) from each reference to in-text citation anchors
5
+ // - Cleans up footnotes block (.footnotes)
6
+
7
+ export default function rehypeReferencesAndFootnotes() {
8
+ return (tree) => {
9
+ const isElement = (n) => n && typeof n === 'object' && n.type === 'element';
10
+ const getChildren = (n) => (Array.isArray(n?.children) ? n.children : []);
11
+
12
+ const walk = (node, parent, fn) => {
13
+ if (!node || typeof node !== 'object') return;
14
+ fn && fn(node, parent);
15
+ const kids = getChildren(node);
16
+ for (const child of kids) walk(child, node, fn);
17
+ };
18
+
19
+ const ensureArray = (v) => (Array.isArray(v) ? v : v != null ? [v] : []);
20
+
21
+ const hasClass = (el, name) => {
22
+ const cn = ensureArray(el?.properties?.className).map(String);
23
+ return cn.includes(name);
24
+ };
25
+
26
+ const setAttr = (el, key, val) => {
27
+ el.properties = el.properties || {};
28
+ if (val == null) delete el.properties[key];
29
+ else el.properties[key] = val;
30
+ };
31
+
32
+ const getAttr = (el, key) => (el?.properties ? el.properties[key] : undefined);
33
+
34
+ // Shared helpers for backlinks + backrefs block
35
+ const collectBacklinksForIdSet = (idSet, anchorPrefix) => {
36
+ const idToBacklinks = new Map();
37
+ const idToAnchorNodes = new Map();
38
+ if (!idSet || idSet.size === 0) return { idToBacklinks, idToAnchorNodes };
39
+ walk(tree, null, (node) => {
40
+ if (!isElement(node) || node.tagName !== 'a') return;
41
+ const href = String(getAttr(node, 'href') || '');
42
+ if (!href.startsWith('#')) return;
43
+ const id = href.slice(1);
44
+ if (!idSet.has(id)) return;
45
+ // Ensure a stable id
46
+ let anchorId = String(getAttr(node, 'id') || '');
47
+ if (!anchorId) {
48
+ const list = idToBacklinks.get(id) || [];
49
+ anchorId = `${anchorPrefix}-${id}-${list.length + 1}`;
50
+ setAttr(node, 'id', anchorId);
51
+ }
52
+ const list = idToBacklinks.get(id) || [];
53
+ list.push(anchorId);
54
+ idToBacklinks.set(id, list);
55
+ const nodes = idToAnchorNodes.get(id) || [];
56
+ nodes.push(node);
57
+ idToAnchorNodes.set(id, nodes);
58
+ });
59
+ return { idToBacklinks, idToAnchorNodes };
60
+ };
61
+
62
+ const createBackIcon = () => ({
63
+ type: 'element',
64
+ tagName: 'svg',
65
+ properties: {
66
+ className: ['back-icon'],
67
+ width: 12,
68
+ height: 12,
69
+ viewBox: '0 0 24 24',
70
+ fill: 'none',
71
+ stroke: 'currentColor',
72
+ 'stroke-width': 2,
73
+ 'stroke-linecap': 'round',
74
+ 'stroke-linejoin': 'round',
75
+ 'aria-hidden': 'true',
76
+ focusable: 'false'
77
+ },
78
+ children: [
79
+ { type: 'element', tagName: 'line', properties: { x1: 12, y1: 19, x2: 12, y2: 5 }, children: [] },
80
+ { type: 'element', tagName: 'polyline', properties: { points: '5 12 12 5 19 12' }, children: [] }
81
+ ]
82
+ });
83
+
84
+ const appendBackrefsBlock = (listElement, idToBacklinks, ariaLabel) => {
85
+ if (!listElement || !idToBacklinks || idToBacklinks.size === 0) return;
86
+ for (const li of getChildren(listElement)) {
87
+ if (!isElement(li) || li.tagName !== 'li') continue;
88
+ const id = String(getAttr(li, 'id') || '');
89
+ if (!id) continue;
90
+ const keys = idToBacklinks.get(id);
91
+ if (!keys || !keys.length) continue;
92
+ // Remove pre-existing .backrefs in this li to avoid duplicates
93
+ li.children = getChildren(li).filter((n) => !(isElement(n) && n.tagName === 'small' && hasClass(n, 'backrefs')));
94
+ const small = {
95
+ type: 'element',
96
+ tagName: 'small',
97
+ properties: { className: ['backrefs'] },
98
+ children: []
99
+ };
100
+ if (keys.length === 1) {
101
+ // Single backlink: just the icon wrapped in the anchor
102
+ const a = {
103
+ type: 'element',
104
+ tagName: 'a',
105
+ properties: { href: `#${keys[0]}`, 'aria-label': ariaLabel },
106
+ children: [ createBackIcon() ]
107
+ };
108
+ small.children.push(a);
109
+ } else {
110
+ // Multiple backlinks: icon + label + numbered links
111
+ small.children.push(createBackIcon());
112
+ small.children.push({ type: 'text', value: ' back: ' });
113
+ keys.forEach((backId, idx) => {
114
+ small.children.push({
115
+ type: 'element',
116
+ tagName: 'a',
117
+ properties: { href: `#${backId}`, 'aria-label': ariaLabel },
118
+ children: [ { type: 'text', value: String(idx + 1) } ]
119
+ });
120
+ if (idx < keys.length - 1) small.children.push({ type: 'text', value: ', ' });
121
+ });
122
+ }
123
+ li.children.push(small);
124
+ }
125
+ };
126
+ // Remove default back-reference anchors generated by remark-footnotes inside a footnote item
127
+ const getTextContent = (el) => {
128
+ if (!el) return '';
129
+ const stack = [el];
130
+ let out = '';
131
+ while (stack.length) {
132
+ const cur = stack.pop();
133
+ if (!cur) continue;
134
+ if (cur.type === 'text') out += String(cur.value || '');
135
+ const kids = getChildren(cur);
136
+ for (let i = kids.length - 1; i >= 0; i--) stack.push(kids[i]);
137
+ }
138
+ return out;
139
+ };
140
+
141
+ const removeFootnoteBackrefAnchors = (el) => {
142
+ if (!isElement(el)) return;
143
+ const kids = getChildren(el);
144
+ for (let i = kids.length - 1; i >= 0; i--) {
145
+ const child = kids[i];
146
+ if (isElement(child)) {
147
+ if (
148
+ child.tagName === 'a' && (
149
+ getAttr(child, 'data-footnote-backref') != null ||
150
+ hasClass(child, 'footnote-backref') ||
151
+ String(getAttr(child, 'role') || '').toLowerCase() === 'doc-backlink' ||
152
+ String(getAttr(child, 'aria-label') || '').toLowerCase().includes('back to content') ||
153
+ String(getAttr(child, 'href') || '').startsWith('#fnref') ||
154
+ // Fallback: text-based detection like "↩" or "↩2"
155
+ /^\s*↩\s*\d*\s*$/u.test(getTextContent(child))
156
+ )
157
+ ) {
158
+ // Remove the anchor
159
+ el.children.splice(i, 1);
160
+ continue;
161
+ }
162
+ // Recurse into element
163
+ removeFootnoteBackrefAnchors(child);
164
+ // If a wrapper like <sup> or <span> became empty, remove it
165
+ const becameKids = getChildren(child);
166
+ if ((child.tagName === 'sup' || child.tagName === 'span') && (!becameKids || becameKids.length === 0)) {
167
+ el.children.splice(i, 1);
168
+ }
169
+ }
170
+ }
171
+ };
172
+
173
+
174
+ const normDoiHref = (href) => {
175
+ if (!href) return href;
176
+ const DUP = /https?:\/\/(?:dx\.)?doi\.org\/(?:https?:\/\/(?:dx\.)?doi\.org\/)+/gi;
177
+ const ONE = /https?:\/\/(?:dx\.)?doi\.org\/(10\.[^\s<>"']+)/i;
178
+ href = String(href).replace(DUP, 'https://doi.org/');
179
+ const m = href.match(ONE);
180
+ return m ? `https://doi.org/${m[1]}` : href;
181
+ };
182
+
183
+ const DOI_BARE = /\b10\.[0-9]{4,9}\/[\-._;()\/:A-Z0-9]+\b/gi;
184
+ const URL_GEN = /\bhttps?:\/\/[^\s<>()"']+/gi;
185
+
186
+ const linkifyTextNode = (textNode) => {
187
+ const text = String(textNode.value || '');
188
+ let last = 0;
189
+ const parts = [];
190
+ const pushText = (s) => { if (s) parts.push({ type: 'text', value: s }); };
191
+
192
+ const matches = [];
193
+ // Collect URL matches
194
+ let m;
195
+ URL_GEN.lastIndex = 0;
196
+ while ((m = URL_GEN.exec(text)) !== null) {
197
+ matches.push({ type: 'url', start: m.index, end: URL_GEN.lastIndex, raw: m[0] });
198
+ }
199
+ // Collect DOI matches
200
+ DOI_BARE.lastIndex = 0;
201
+ while ((m = DOI_BARE.exec(text)) !== null) {
202
+ matches.push({ type: 'doi', start: m.index, end: DOI_BARE.lastIndex, raw: m[0] });
203
+ }
204
+ matches.sort((a, b) => a.start - b.start);
205
+
206
+ for (const match of matches) {
207
+ if (match.start < last) continue; // overlapping
208
+ pushText(text.slice(last, match.start));
209
+ if (match.type === 'url') {
210
+ const href = normDoiHref(match.raw);
211
+ const doiOne = href.match(/https?:\/\/(?:dx\.)?doi\.org\/(10\.[^\s<>"']+)/i);
212
+ const a = {
213
+ type: 'element',
214
+ tagName: 'a',
215
+ properties: { href, target: '_blank', rel: 'noopener noreferrer' },
216
+ children: [{ type: 'text', value: doiOne ? doiOne[1] : href }]
217
+ };
218
+ parts.push(a);
219
+ } else {
220
+ const href = `https://doi.org/${match.raw}`;
221
+ const a = {
222
+ type: 'element',
223
+ tagName: 'a',
224
+ properties: { href, target: '_blank', rel: 'noopener noreferrer' },
225
+ children: [{ type: 'text', value: match.raw }]
226
+ };
227
+ parts.push(a);
228
+ }
229
+ last = match.end;
230
+ }
231
+
232
+ pushText(text.slice(last));
233
+ return parts;
234
+ };
235
+
236
+ const linkifyInElement = (el) => {
237
+ const kids = getChildren(el);
238
+ for (let i = 0; i < kids.length; i++) {
239
+ const child = kids[i];
240
+ if (!child) continue;
241
+ if (child.type === 'text') {
242
+ const replacement = linkifyTextNode(child);
243
+ if (replacement.length === 1 && replacement[0].type === 'text') continue;
244
+ // Replace the single text node with multiple nodes
245
+ el.children.splice(i, 1, ...replacement);
246
+ i += replacement.length - 1;
247
+ } else if (isElement(child)) {
248
+ if (child.tagName === 'a') {
249
+ const href = normDoiHref(getAttr(child, 'href'));
250
+ setAttr(child, 'href', href);
251
+ const m = String(href || '').match(/https?:\/\/(?:dx\.)?doi\.org\/(10\.[^\s<>"']+)/i);
252
+ if (m && (!child.children || child.children.length === 0)) {
253
+ child.children = [{ type: 'text', value: m[1] }];
254
+ }
255
+ continue;
256
+ }
257
+ linkifyInElement(child);
258
+ }
259
+ }
260
+ // Deduplicate adjacent identical anchors
261
+ for (let i = 1; i < el.children.length; i++) {
262
+ const prev = el.children[i - 1];
263
+ const curr = el.children[i];
264
+ if (isElement(prev) && isElement(curr) && prev.tagName === 'a' && curr.tagName === 'a') {
265
+ const key = `${getAttr(prev, 'href') || ''}|${(prev.children?.[0]?.value) || ''}`;
266
+ const key2 = `${getAttr(curr, 'href') || ''}|${(curr.children?.[0]?.value) || ''}`;
267
+ if (key === key2) {
268
+ el.children.splice(i, 1);
269
+ i--;
270
+ }
271
+ }
272
+ }
273
+ };
274
+
275
+ // Find references container and normalize its list
276
+ const findReferencesRoot = () => {
277
+ let found = null;
278
+ walk(tree, null, (node) => {
279
+ if (found) return;
280
+ if (!isElement(node)) return;
281
+ const id = getAttr(node, 'id');
282
+ if (id === 'references' || hasClass(node, 'references') || hasClass(node, 'bibliography')) {
283
+ found = node;
284
+ }
285
+ });
286
+ return found;
287
+ };
288
+
289
+ const toOrderedList = (container) => {
290
+ // If there is already an <ol>, use it; otherwise convert common structures
291
+ let ol = getChildren(container).find((c) => isElement(c) && c.tagName === 'ol');
292
+ if (!ol) {
293
+ ol = { type: 'element', tagName: 'ol', properties: { className: ['references'] }, children: [] };
294
+ const candidates = getChildren(container).filter((n) => isElement(n));
295
+ if (candidates.length) {
296
+ for (const node of candidates) {
297
+ if (hasClass(node, 'csl-entry') || node.tagName === 'li' || node.tagName === 'p' || node.tagName === 'div') {
298
+ const li = { type: 'element', tagName: 'li', properties: {}, children: getChildren(node) };
299
+ if (getAttr(node, 'id')) setAttr(li, 'id', getAttr(node, 'id'));
300
+ ol.children.push(li);
301
+ }
302
+ }
303
+ }
304
+ // Replace container children by the new ol
305
+ container.children = [ol];
306
+ }
307
+ if (!hasClass(ol, 'references')) {
308
+ const cls = ensureArray(ol.properties?.className).map(String);
309
+ if (!cls.includes('references')) cls.push('references');
310
+ ol.properties = ol.properties || {};
311
+ ol.properties.className = cls;
312
+ }
313
+ return ol;
314
+ };
315
+
316
+ const refsRoot = findReferencesRoot();
317
+ let refsOl = null;
318
+ const refIdSet = new Set();
319
+ const refIdToExternalHref = new Map();
320
+
321
+ if (refsRoot) {
322
+ refsOl = toOrderedList(refsRoot);
323
+ // Collect item ids and linkify their content
324
+ for (const li of getChildren(refsOl)) {
325
+ if (!isElement(li) || li.tagName !== 'li') continue;
326
+ if (!getAttr(li, 'id')) {
327
+ // Try to find a nested element with id to promote
328
+ const nestedWithId = getChildren(li).find((n) => isElement(n) && getAttr(n, 'id'));
329
+ if (nestedWithId) setAttr(li, 'id', getAttr(nestedWithId, 'id'));
330
+ }
331
+ const id = getAttr(li, 'id');
332
+ if (id) refIdSet.add(String(id));
333
+ linkifyInElement(li);
334
+ // Record first external link href (e.g., DOI/URL) if present
335
+ if (id) {
336
+ let externalHref = null;
337
+ const stack = [li];
338
+ while (stack.length) {
339
+ const cur = stack.pop();
340
+ const kids = getChildren(cur);
341
+ for (const k of kids) {
342
+ if (isElement(k) && k.tagName === 'a') {
343
+ const href = String(getAttr(k, 'href') || '');
344
+ if (/^https?:\/\//i.test(href)) {
345
+ externalHref = href;
346
+ break;
347
+ }
348
+ }
349
+ if (isElement(k)) stack.push(k);
350
+ }
351
+ if (externalHref) break;
352
+ }
353
+ if (externalHref) refIdToExternalHref.set(String(id), externalHref);
354
+ }
355
+ }
356
+ setAttr(refsRoot, 'data-built-refs', '1');
357
+ }
358
+
359
+ // Collect in-text anchors that point to references ids
360
+ const { idToBacklinks: refIdToBacklinks, idToAnchorNodes: refIdToCitationAnchors } = collectBacklinksForIdSet(refIdSet, 'refctx');
361
+
362
+ // Append backlinks into references list items
363
+ appendBackrefsBlock(refsOl, refIdToBacklinks, 'Back to citation');
364
+
365
+ // Rewrite in-text citation anchors to external link when available
366
+ if (refIdToCitationAnchors.size > 0) {
367
+ for (const [id, anchors] of refIdToCitationAnchors.entries()) {
368
+ const ext = refIdToExternalHref.get(id);
369
+ if (!ext) continue;
370
+ for (const a of anchors) {
371
+ setAttr(a, 'data-ref-id', id);
372
+ setAttr(a, 'href', ext);
373
+ const existingTarget = getAttr(a, 'target');
374
+ if (!existingTarget) setAttr(a, 'target', '_blank');
375
+ const rel = String(getAttr(a, 'rel') || '');
376
+ const relSet = new Set(rel ? rel.split(/\s+/) : []);
377
+ relSet.add('noopener');
378
+ relSet.add('noreferrer');
379
+ setAttr(a, 'rel', Array.from(relSet).join(' '));
380
+ }
381
+ }
382
+ }
383
+
384
+ // Footnotes cleanup + backrefs harmonized with references
385
+ const cleanupFootnotes = () => {
386
+ let root = null;
387
+ walk(tree, null, (node) => {
388
+ if (!isElement(node)) return;
389
+ if (hasClass(node, 'footnotes')) root = node;
390
+ });
391
+ if (!root) return { root: null, ol: null, idSet: new Set() };
392
+ // Remove <hr> direct children
393
+ root.children = getChildren(root).filter((n) => !(isElement(n) && n.tagName === 'hr'));
394
+ // Ensure an <ol>
395
+ let ol = getChildren(root).find((c) => isElement(c) && c.tagName === 'ol');
396
+ if (!ol) {
397
+ ol = { type: 'element', tagName: 'ol', properties: {}, children: [] };
398
+ const items = getChildren(root).filter((n) => isElement(n) && (n.tagName === 'li' || hasClass(n, 'footnote') || n.tagName === 'p' || n.tagName === 'div'));
399
+ if (items.length) {
400
+ for (const it of items) {
401
+ const li = { type: 'element', tagName: 'li', properties: {}, children: getChildren(it) };
402
+ // Promote nested id if present (e.g., <p id="fn-1">)
403
+ const nestedWithId = getChildren(it).find((n) => isElement(n) && getAttr(n, 'id'));
404
+ if (nestedWithId) setAttr(li, 'id', getAttr(nestedWithId, 'id'));
405
+ ol.children.push(li);
406
+ }
407
+ }
408
+ root.children = [ol];
409
+ }
410
+ // For existing structures, try to promote ids from children when missing
411
+ for (const li of getChildren(ol)) {
412
+ if (!isElement(li) || li.tagName !== 'li') continue;
413
+ if (!getAttr(li, 'id')) {
414
+ const nestedWithId = getChildren(li).find((n) => isElement(n) && getAttr(n, 'id'));
415
+ if (nestedWithId) setAttr(li, 'id', getAttr(nestedWithId, 'id'));
416
+ }
417
+ // Remove default footnote backrefs anywhere inside (to avoid duplication)
418
+ removeFootnoteBackrefAnchors(li);
419
+ }
420
+ setAttr(root, 'data-built-footnotes', '1');
421
+ // Collect id set
422
+ const idSet = new Set();
423
+ for (const li of getChildren(ol)) {
424
+ if (!isElement(li) || li.tagName !== 'li') continue;
425
+ const id = getAttr(li, 'id');
426
+ if (id) idSet.add(String(id));
427
+ }
428
+ return { root, ol, idSet };
429
+ };
430
+
431
+ const { root: footRoot, ol: footOl, idSet: footIdSet } = cleanupFootnotes();
432
+
433
+ // Collect in-text anchors pointing to footnotes
434
+ const { idToBacklinks: footIdToBacklinks } = collectBacklinksForIdSet(footIdSet, 'footctx');
435
+
436
+ // Append backlinks into footnote list items (identical pattern to references)
437
+ appendBackrefsBlock(footOl, footIdToBacklinks, 'Back to footnote call');
438
+ };
439
+ }
440
+
441
+
app/plugins/rehype/restore-at-in-code.mjs ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // Rehype plugin to restore '@' inside code nodes after rehype-citation ran
2
+ export default function rehypeRestoreAtInCode() {
3
+ return (tree) => {
4
+ const restoreInNode = (node) => {
5
+ if (!node || typeof node !== 'object') return;
6
+ const isText = node.type === 'text';
7
+ if (isText && typeof node.value === 'string' && node.value.includes('__AT_SENTINEL__')) {
8
+ node.value = node.value.replace(/__AT_SENTINEL__/g, '@');
9
+ }
10
+ const isCodeEl = node.type === 'element' && node.tagName === 'code';
11
+ const children = Array.isArray(node.children) ? node.children : [];
12
+ if (isCodeEl && children.length) {
13
+ children.forEach(restoreInNode);
14
+ return;
15
+ }
16
+ children.forEach(restoreInNode);
17
+ };
18
+ restoreInNode(tree);
19
+ };
20
+ }
21
+
22
+
app/plugins/rehype/wrap-tables.mjs ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // rehype plugin: wrap bare <table> elements in a <div class="table-scroll"> container
2
+ // so that tables stay width:100% while enabling horizontal scroll when content overflows
3
+
4
+ export default function rehypeWrapTables() {
5
+ return (tree) => {
6
+ const isElement = (n) => n && typeof n === 'object' && n.type === 'element';
7
+ const getChildren = (n) => (Array.isArray(n?.children) ? n.children : []);
8
+
9
+ const walk = (node, parent, fn) => {
10
+ if (!node || typeof node !== 'object') return;
11
+ fn && fn(node, parent);
12
+ const kids = getChildren(node);
13
+ for (const child of kids) walk(child, node, fn);
14
+ };
15
+
16
+ const ensureArray = (v) => (Array.isArray(v) ? v : v != null ? [v] : []);
17
+ const hasClass = (el, name) => ensureArray(el?.properties?.className).map(String).includes(name);
18
+
19
+ const wrapTable = (tableNode, parent) => {
20
+ if (!parent || !Array.isArray(parent.children)) return;
21
+ // Don't double-wrap if already inside .table-scroll
22
+ if (parent.tagName === 'div' && hasClass(parent, 'table-scroll')) return;
23
+
24
+ const wrapper = {
25
+ type: 'element',
26
+ tagName: 'div',
27
+ properties: { className: ['table-scroll'] },
28
+ children: [tableNode]
29
+ };
30
+
31
+ const idx = parent.children.indexOf(tableNode);
32
+ if (idx >= 0) parent.children.splice(idx, 1, wrapper);
33
+ };
34
+
35
+ walk(tree, null, (node, parent) => {
36
+ if (!isElement(node)) return;
37
+ if (node.tagName !== 'table') return;
38
+ wrapTable(node, parent);
39
+ });
40
+ };
41
+ }
42
+
43
+
app/plugins/remark/ignore-citations-in-code.mjs ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // Remark plugin to ignore citations inside code (block and inline)
2
+ export default function remarkIgnoreCitationsInCode() {
3
+ return (tree) => {
4
+ const visit = (node) => {
5
+ if (!node || typeof node !== 'object') return;
6
+ const type = node.type;
7
+ if (type === 'code' || type === 'inlineCode') {
8
+ if (typeof node.value === 'string' && node.value.includes('@')) {
9
+ // Use a sentinel to avoid rehype-citation, will be restored later in rehype
10
+ node.value = node.value.replace(/@/g, '__AT_SENTINEL__');
11
+ }
12
+ return; // do not traverse into code
13
+ }
14
+ const children = Array.isArray(node.children) ? node.children : [];
15
+ children.forEach(visit);
16
+ };
17
+ visit(tree);
18
+ };
19
+ }
20
+
21
+
app/postcss.config.mjs ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // PostCSS config enabling Custom Media Queries
2
+ // Allows usage of: @media (--bp-content-collapse) { ... }
3
+
4
+ import postcssCustomMedia from 'postcss-custom-media';
5
+ import postcssPresetEnv from 'postcss-preset-env';
6
+
7
+ export default {
8
+ plugins: [
9
+ postcssCustomMedia(),
10
+ postcssPresetEnv({
11
+ stage: 0
12
+ })
13
+ ]
14
+ };
app/src/components/Accordion.astro CHANGED
@@ -76,6 +76,8 @@ const wrapperClass = ["accordion", className].filter(Boolean).join(" ");
76
 
77
  <style>
78
  .accordion {
 
 
79
  border: 1px solid var(--border-color);
80
  border-radius: 10px;
81
  background: var(--surface-bg);
@@ -87,16 +89,16 @@ const wrapperClass = ["accordion", className].filter(Boolean).join(" ");
87
  }
88
 
89
  .accordion__summary {
 
90
  list-style: none;
91
  display: flex;
92
  align-items: center;
93
- justify-content: center;
94
  gap: 4px;
95
- padding: 4px;
96
  cursor: pointer;
97
  color: var(--text-color);
98
  user-select: none;
99
- position: relative;
100
  }
101
 
102
  /* Remove conditional padding to avoid jump on close */
@@ -114,8 +116,7 @@ const wrapperClass = ["accordion", className].filter(Boolean).join(" ");
114
  }
115
 
116
  .accordion__chevron {
117
- position: absolute;
118
- right: 8px;
119
  transition: transform 220ms ease;
120
  opacity: .85;
121
  }
@@ -133,7 +134,8 @@ const wrapperClass = ["accordion", className].filter(Boolean).join(" ");
133
  }
134
 
135
  .accordion__content {
136
- padding: 12px 4px 4px;
 
137
  }
138
 
139
  /* Ensure the very last slotted element has no bottom spacing */
@@ -142,15 +144,30 @@ const wrapperClass = ["accordion", className].filter(Boolean).join(" ");
142
  margin-bottom: 0 !important;
143
  }
144
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
145
  /* Separator between header and content when open (edge-to-edge) */
146
  .accordion[open] .accordion__content-wrapper::before {
147
  content: "";
148
  position: absolute;
149
  left: 0;
150
  right: 0;
151
- top: 6px; /* space below header */
152
  height: 1px;
153
- background: var(--neutral-300);
154
  pointer-events: none;
155
  }
156
 
@@ -160,6 +177,8 @@ const wrapperClass = ["accordion", className].filter(Boolean).join(" ");
160
  outline-offset: 3px;
161
  border-radius: 8px;
162
  }
 
 
163
  </style>
164
 
165
 
 
76
 
77
  <style>
78
  .accordion {
79
+ margin: 0 0 var(--spacing-4);
80
+ padding: 0;
81
  border: 1px solid var(--border-color);
82
  border-radius: 10px;
83
  background: var(--surface-bg);
 
89
  }
90
 
91
  .accordion__summary {
92
+ margin: 0;
93
  list-style: none;
94
  display: flex;
95
  align-items: center;
96
+ justify-content: space-between;
97
  gap: 4px;
98
+ padding: 10px 8px;
99
  cursor: pointer;
100
  color: var(--text-color);
101
  user-select: none;
 
102
  }
103
 
104
  /* Remove conditional padding to avoid jump on close */
 
116
  }
117
 
118
  .accordion__chevron {
119
+ flex: 0 0 auto;
 
120
  transition: transform 220ms ease;
121
  opacity: .85;
122
  }
 
134
  }
135
 
136
  .accordion__content {
137
+ margin: 0;
138
+ padding: 0;
139
  }
140
 
141
  /* Ensure the very last slotted element has no bottom spacing */
 
144
  margin-bottom: 0 !important;
145
  }
146
 
147
+ /* Ensure the very first slotted element has no top spacing */
148
+ .accordion .accordion__content > :global(*:first-child) {
149
+ margin-top: 0 !important;
150
+ }
151
+
152
+ /* Content padding: default for direct children, opt-out for code/tables */
153
+ .accordion .accordion__content > :global(*) {
154
+ padding: 8px;
155
+ }
156
+ .accordion .accordion__content > :global(.table-scroll),
157
+ .accordion .accordion__content > :global(pre),
158
+ .accordion .accordion__content > :global(.code-card) {
159
+ padding: 0;
160
+ }
161
+
162
  /* Separator between header and content when open (edge-to-edge) */
163
  .accordion[open] .accordion__content-wrapper::before {
164
  content: "";
165
  position: absolute;
166
  left: 0;
167
  right: 0;
168
+ top: 0px; /* space below header */
169
  height: 1px;
170
+ background: var(--border-color);
171
  pointer-events: none;
172
  }
173
 
 
177
  outline-offset: 3px;
178
  border-radius: 8px;
179
  }
180
+
181
+
182
  </style>
183
 
184
 
app/src/components/Footer.astro CHANGED
@@ -2,10 +2,12 @@
2
  interface Props {
3
  citationText: string;
4
  bibtex: string;
 
 
5
  }
6
- const { citationText, bibtex } = Astro.props as Props;
7
  ---
8
- <footer class="distill-footer">
9
  <div class="footer-inner">
10
  <section class="citation-block">
11
  <h3>Citation</h3>
@@ -15,6 +17,18 @@ const { citationText, bibtex } = Astro.props as Props;
15
  <p>BibTeX citation</p>
16
  <pre class="citation long">{bibtex}</pre>
17
  </section>
 
 
 
 
 
 
 
 
 
 
 
 
18
  <section class="references-block">
19
  <slot />
20
  </section>
@@ -24,7 +38,7 @@ const { citationText, bibtex } = Astro.props as Props;
24
 
25
  <script is:inline>
26
  (() => {
27
- const getFooter = () => document.currentScript?.closest('footer') || document.querySelector('footer.distill-footer');
28
  const footer = getFooter();
29
  if (!footer) return;
30
  const target = footer.querySelector('.references-block');
@@ -32,14 +46,6 @@ const { citationText, bibtex } = Astro.props as Props;
32
 
33
  const contentRoot = document.querySelector('section.content-grid main') || document.querySelector('main') || document.body;
34
 
35
- const findFirstOutsideFooter = (selectors) => {
36
- for (const sel of selectors) {
37
- const el = contentRoot.querySelector(sel);
38
- if (el && !footer.contains(el)) return el;
39
- }
40
- return null;
41
- };
42
-
43
  const ensureHeading = (text) => {
44
  const exists = Array.from(target.children).some((c) => c.tagName === 'H3' && c.textContent.trim().toLowerCase() === text.toLowerCase());
45
  if (!exists) {
@@ -51,10 +57,6 @@ const { citationText, bibtex } = Astro.props as Props;
51
 
52
  const moveIntoFooter = (element, headingText) => {
53
  if (!element) return false;
54
- if (element.classList.contains('footnotes')) {
55
- const hr = element.querySelector('hr');
56
- if (hr) hr.remove();
57
- }
58
  // Remove an eventual heading already included inside the block (avoid duplicates)
59
  const firstHeading = element.querySelector(':scope > h1, :scope > h2, :scope > h3');
60
  if (firstHeading) {
@@ -68,10 +70,18 @@ const { citationText, bibtex } = Astro.props as Props;
68
  target.appendChild(element);
69
  return true;
70
  };
71
-
72
  const run = () => {
 
 
 
 
 
 
 
 
73
  const referencesEl = findFirstOutsideFooter(['#references', '.references', '.bibliography']);
74
  const footnotesEl = findFirstOutsideFooter(['.footnotes']);
 
75
  const movedRefs = moveIntoFooter(referencesEl, 'References');
76
  const movedNotes = moveIntoFooter(footnotesEl, 'Footnotes');
77
  return movedRefs || movedNotes;
@@ -94,3 +104,141 @@ const { citationText, bibtex } = Astro.props as Props;
94
  </script>
95
 
96
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  interface Props {
3
  citationText: string;
4
  bibtex: string;
5
+ licence?: string;
6
+ doi?: string;
7
  }
8
+ const { citationText, bibtex, licence, doi } = Astro.props as Props;
9
  ---
10
+ <footer class="footer">
11
  <div class="footer-inner">
12
  <section class="citation-block">
13
  <h3>Citation</h3>
 
17
  <p>BibTeX citation</p>
18
  <pre class="citation long">{bibtex}</pre>
19
  </section>
20
+ {doi && (
21
+ <section class="doi-block">
22
+ <h3>DOI</h3>
23
+ <p><a href={`https://doi.org/${doi}`} target="_blank" rel="noopener noreferrer">{doi}</a></p>
24
+ </section>
25
+ )}
26
+ {licence && (
27
+ <section class="reuse-block">
28
+ <h3>Reuse</h3>
29
+ <p set:html={licence}></p>
30
+ </section>
31
+ )}
32
  <section class="references-block">
33
  <slot />
34
  </section>
 
38
 
39
  <script is:inline>
40
  (() => {
41
+ const getFooter = () => document.currentScript?.closest('footer') || document.querySelector('footer.footer');
42
  const footer = getFooter();
43
  if (!footer) return;
44
  const target = footer.querySelector('.references-block');
 
46
 
47
  const contentRoot = document.querySelector('section.content-grid main') || document.querySelector('main') || document.body;
48
 
 
 
 
 
 
 
 
 
49
  const ensureHeading = (text) => {
50
  const exists = Array.from(target.children).some((c) => c.tagName === 'H3' && c.textContent.trim().toLowerCase() === text.toLowerCase());
51
  if (!exists) {
 
57
 
58
  const moveIntoFooter = (element, headingText) => {
59
  if (!element) return false;
 
 
 
 
60
  // Remove an eventual heading already included inside the block (avoid duplicates)
61
  const firstHeading = element.querySelector(':scope > h1, :scope > h2, :scope > h3');
62
  if (firstHeading) {
 
70
  target.appendChild(element);
71
  return true;
72
  };
 
73
  const run = () => {
74
+ const findFirstOutsideFooter = (selectors) => {
75
+ for (const sel of selectors) {
76
+ const el = contentRoot.querySelector(sel);
77
+ if (el && !footer.contains(el)) return el;
78
+ }
79
+ return null;
80
+ };
81
+
82
  const referencesEl = findFirstOutsideFooter(['#references', '.references', '.bibliography']);
83
  const footnotesEl = findFirstOutsideFooter(['.footnotes']);
84
+
85
  const movedRefs = moveIntoFooter(referencesEl, 'References');
86
  const movedNotes = moveIntoFooter(footnotesEl, 'Footnotes');
87
  return movedRefs || movedNotes;
 
104
  </script>
105
 
106
 
107
+ <style is:global>
108
+ .footer {
109
+ contain: layout style;
110
+ font-size: 0.8em;
111
+ line-height: 1.7em;
112
+ margin-top: 60px;
113
+ margin-bottom: 0;
114
+ border-top: 1px solid rgba(0, 0, 0, 0.1);
115
+ color: rgba(0, 0, 0, 0.5);
116
+ }
117
+
118
+ .footer-inner {
119
+ max-width: 1280px;
120
+ margin: 0 auto;
121
+ padding: 60px 16px 48px;
122
+ display: grid;
123
+ grid-template-columns: 220px minmax(0, 680px) 260px;
124
+ gap: 32px;
125
+ align-items: start;
126
+ }
127
+
128
+ /* Use the parent grid (3 columns like .content-grid) */
129
+ .citation-block,
130
+ .references-block,
131
+ .reuse-block,
132
+ .doi-block {
133
+ display: contents;
134
+ }
135
+
136
+ .citation-block > h3,
137
+ .references-block > h3,
138
+ .reuse-block > h3,
139
+ .doi-block > h3 {
140
+ grid-column: 1;
141
+ font-size: 15px;
142
+ margin: 0;
143
+ text-align: right;
144
+ padding-right: 30px;
145
+ }
146
+
147
+ .citation-block > :not(h3),
148
+ .references-block > :not(h3),
149
+ .reuse-block > :not(h3),
150
+ .doi-block > :not(h3) {
151
+ grid-column: 2;
152
+ }
153
+
154
+
155
+ .citation-block h3 {
156
+ margin: 0 0 8px;
157
+ }
158
+
159
+ .citation-block h4 {
160
+ margin: 16px 0 8px;
161
+ font-size: 14px;
162
+ text-transform: uppercase;
163
+ color: var(--muted-color);
164
+ }
165
+
166
+ .citation-block p,
167
+ .reuse-block p,
168
+ .doi-block p,
169
+ .footnotes ol,
170
+ .footnotes ol p,
171
+ .references {
172
+ margin-top: 0;
173
+ }
174
+
175
+ /* Distill-like appendix citation styling */
176
+ .citation {
177
+ font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
178
+ font-size: 11px;
179
+ line-height: 15px;
180
+ border-left: 1px solid rgba(0, 0, 0, 0.1);
181
+ padding-left: 18px;
182
+ border: 1px solid rgba(0,0,0,0.1);
183
+ background: rgba(0, 0, 0, 0.02);
184
+ padding: 10px 18px;
185
+ border-radius: 3px;
186
+ color: rgba(150, 150, 150, 1);
187
+ overflow: hidden;
188
+ margin-top: -12px;
189
+ white-space: pre-wrap;
190
+ word-wrap: break-word;
191
+ }
192
+
193
+ .citation a {
194
+ color: rgba(0, 0, 0, 0.6);
195
+ text-decoration: underline;
196
+ }
197
+
198
+ .citation.short {
199
+ margin-top: -4px;
200
+ }
201
+
202
+ .references-block h3 {
203
+ margin: 0;
204
+ }
205
+
206
+ /* Distill-like list styling for references/footnotes */
207
+ .references-block ol {
208
+ padding: 0 0 0 15px;
209
+ }
210
+
211
+ @media (min-width: 768px) {
212
+ .references-block ol {
213
+ padding: 0 0 0 30px;
214
+ margin-left: -30px;
215
+ }
216
+ }
217
+
218
+ .references-block li {
219
+ margin-bottom: 1em;
220
+ }
221
+
222
+ .references-block a {
223
+ color: var(--text-color);
224
+ }
225
+
226
+ [data-theme="dark"] .footer { border-top-color: rgba(255,255,255,.15); color: rgba(200,200,200,.8); }
227
+ [data-theme="dark"] .citation { background: rgba(255,255,255,0.04); border-color: rgba(255,255,255,.15); color: rgba(200,200,200,1); }
228
+ [data-theme="dark"] .citation a { color: rgba(255,255,255,0.75); }
229
+
230
+
231
+ /* Footer links: use primary color consistently */
232
+ .footer a {
233
+ color: var(--primary-color);
234
+ border-bottom: 1px solid var(--link-underline);
235
+ text-decoration: none;
236
+ }
237
+ .footer a:hover {
238
+ color: var(--primary-color-hover);
239
+ border-bottom-color: var(--link-underline-hover);
240
+ }
241
+ [data-theme="dark"] .footer a {
242
+ color: var(--primary-color);
243
+ }
244
+ </style>
app/src/components/Hero.astro CHANGED
@@ -5,12 +5,45 @@ interface Props {
5
  title: string; // may contain HTML (e.g., <br/>)
6
  titleRaw?: string; // plain title for slug/PDF (optional)
7
  description?: string;
8
- authors?: string[];
9
- affiliation?: string;
 
10
  published?: string;
 
11
  }
12
 
13
- const { title, titleRaw, description, authors = [], affiliation, published } = Astro.props as Props;
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
 
15
  function stripHtml(text: string): string {
16
  return String(text || '').replace(/<[^>]*>/g, '');
@@ -37,69 +70,169 @@ const pdfFilename = `${slugify(pdfBase)}.pdf`;
37
  </div>
38
  </section>
39
 
40
- <header class="meta">
41
  <div class="meta-container">
42
- {authors.length > 0 && (
43
  <div class="meta-container-cell">
44
- <h3>Authors</h3>
45
- <p>{authors.join(', ')}</p>
 
 
 
 
 
 
 
 
 
 
 
46
  </div>
47
  )}
48
- {affiliation && (
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  <div class="meta-container-cell">
50
  <h3>Affiliation</h3>
51
  <p>{affiliation}</p>
52
  </div>
53
  )}
54
  {published && (
55
- <div class="meta-container-cell">
56
  <h3>Published</h3>
57
  <p>{published}</p>
58
  </div>
59
  )}
 
 
 
 
 
 
60
  <div class="meta-container-cell meta-container-cell--pdf">
61
  <h3>PDF</h3>
62
- <p><button id="download-pdf-btn" data-pdf-filename={pdfFilename}>Download PDF</button></p>
 
 
 
 
63
  </div>
64
  </div>
65
  </header>
66
 
67
- <script>
68
- // Attach a handler to trigger a programmatic download
69
- (() => {
70
- const ready = () => {
71
- const btn = document.getElementById('download-pdf-btn');
72
- if (!btn) return;
73
- btn.addEventListener('click', () => {
74
- const a = document.createElement('a');
75
- const pdf = btn.getAttribute('data-pdf-filename') || 'article.pdf';
76
- a.href = `/${pdf}`;
77
- a.setAttribute('download', pdf);
78
- document.body.appendChild(a);
79
- a.click();
80
- a.remove();
81
- });
82
- };
83
- if (document.readyState === 'loading') {
84
- document.addEventListener('DOMContentLoaded', ready, { once: true });
85
- } else { ready(); }
86
- })();
87
- </script>
88
 
89
  <style>
90
  /* Hero (full-width) */
91
- .hero { width: 100%; padding: 48px 16px 16px; text-align: center; }
92
- .hero-title { font-size: clamp(28px, 4vw, 48px); font-weight: 800; line-height: 1.1; margin: 0 0 8px; max-width: 60%; margin: auto; }
93
- .hero-banner { max-width: 980px; margin: 0 auto; }
94
- .hero-desc { color: var(--muted-color); font-style: italic; margin: 0 0 16px 0; }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
 
96
  /* Meta (byline-like header) */
97
- .meta { border-top: 1px solid var(--border-color); border-bottom: 1px solid var(--border-color); padding: 1rem 0; font-size: 0.9rem; line-height: 1.8em; }
98
- .meta-container { max-width: 720px; display: flex; flex-direction: row; justify-content: space-between; margin: 0 auto; gap: 8px; }
99
- .meta-container-cell { display: flex; flex-direction: column; gap: 8px; }
100
- .meta-container-cell h3 { margin: 0; font-size: 12px; font-weight: 400; color: var(--muted-color); text-transform: uppercase; letter-spacing: .02em; }
101
- .meta-container-cell p { margin: 0; }
102
- @media print { .meta-container-cell--pdf { display: none !important; } }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
  </style>
104
 
105
 
 
5
  title: string; // may contain HTML (e.g., <br/>)
6
  titleRaw?: string; // plain title for slug/PDF (optional)
7
  description?: string;
8
+ authors?: Array<string | { name: string; url?: string; affiliationIndices?: number[] }>;
9
+ affiliations?: Array<{ id: number; name: string; url?: string }>;
10
+ affiliation?: string; // legacy single affiliation
11
  published?: string;
12
+ doi?: string;
13
  }
14
 
15
+ const { title, titleRaw, description, authors = [], affiliations = [], affiliation, published, doi } = Astro.props as Props;
16
+
17
+ type Author = { name: string; url?: string; affiliationIndices?: number[] };
18
+
19
+ function normalizeAuthors(input: Array<string | { name?: string; url?: string; link?: string; affiliationIndices?: number[] }>): Author[] {
20
+ return (Array.isArray(input) ? input : [])
21
+ .map((a) => {
22
+ if (typeof a === 'string') {
23
+ return { name: a } as Author;
24
+ }
25
+ const name = (a?.name ?? '').toString();
26
+ const url = (a?.url ?? a?.link) as string | undefined;
27
+ const affiliationIndices = Array.isArray((a as any)?.affiliationIndices) ? (a as any).affiliationIndices : undefined;
28
+ return { name, url, affiliationIndices } as Author;
29
+ })
30
+ .filter((a) => a.name && a.name.trim().length > 0);
31
+ }
32
+
33
+ const normalizedAuthors: Author[] = normalizeAuthors(authors as any);
34
+
35
+ // Determine if affiliation superscripts should be shown (only when there are multiple distinct affiliations referenced by authors)
36
+ const authorAffiliationIndexSet = new Set<number>();
37
+ for (const author of normalizedAuthors) {
38
+ const indices = Array.isArray(author.affiliationIndices) ? author.affiliationIndices : [];
39
+ for (const idx of indices) {
40
+ if (typeof idx === 'number') {
41
+ authorAffiliationIndexSet.add(idx);
42
+ }
43
+ }
44
+ }
45
+ const shouldShowAffiliationSupers = authorAffiliationIndexSet.size > 1;
46
+ const hasMultipleAffiliations = Array.isArray(affiliations) && affiliations.length > 1;
47
 
48
  function stripHtml(text: string): string {
49
  return String(text || '').replace(/<[^>]*>/g, '');
 
70
  </div>
71
  </section>
72
 
73
+ <header class="meta" aria-label="Article meta information">
74
  <div class="meta-container">
75
+ {normalizedAuthors.length > 0 && (
76
  <div class="meta-container-cell">
77
+ <h3>Author{normalizedAuthors.length > 1 ? 's' : ''}</h3>
78
+ <ul class="authors">
79
+ {normalizedAuthors.map((a, i) => {
80
+ const supers = shouldShowAffiliationSupers && Array.isArray(a.affiliationIndices) && a.affiliationIndices.length
81
+ ? <sup>{a.affiliationIndices.join(',')}</sup>
82
+ : null;
83
+ return (
84
+ <li>
85
+ {a.url ? <a href={a.url}>{a.name}</a> : a.name}{supers}
86
+ </li>
87
+ );
88
+ })}
89
+ </ul>
90
  </div>
91
  )}
92
+ {(Array.isArray(affiliations) && affiliations.length > 0) && (
93
+ <div class="meta-container-cell">
94
+ <h3>Affiliation{affiliations.length > 1 ? 's' : ''}</h3>
95
+ {hasMultipleAffiliations ? (
96
+ <ol class="affiliations">
97
+ {affiliations.map((af) => (
98
+ <li value={af.id}>{af.url ? <a href={af.url} target="_blank" rel="noopener noreferrer">{af.name}</a> : af.name}</li>
99
+ ))}
100
+ </ol>
101
+ ) : (
102
+ <p>
103
+ {affiliations[0]?.url
104
+ ? <a href={affiliations[0].url} target="_blank" rel="noopener noreferrer">{affiliations[0].name}</a>
105
+ : affiliations[0]?.name}
106
+ </p>
107
+ )}
108
+ </div>
109
+ )}
110
+ {(!affiliations || affiliations.length === 0) && affiliation && (
111
  <div class="meta-container-cell">
112
  <h3>Affiliation</h3>
113
  <p>{affiliation}</p>
114
  </div>
115
  )}
116
  {published && (
117
+ <div class="meta-container-cell meta-container-cell--published">
118
  <h3>Published</h3>
119
  <p>{published}</p>
120
  </div>
121
  )}
122
+ <!-- {doi && (
123
+ <div class="meta-container-cell">
124
+ <h3>DOI</h3>
125
+ <p><a href={`https://doi.org/${doi}`} target="_blank" rel="noopener noreferrer">{doi}</a></p>
126
+ </div>
127
+ )} -->
128
  <div class="meta-container-cell meta-container-cell--pdf">
129
  <h3>PDF</h3>
130
+ <p>
131
+ <a class="button" href={`/${pdfFilename}`} download={pdfFilename} aria-label={`Download PDF ${pdfFilename}`}>
132
+ Download PDF
133
+ </a>
134
+ </p>
135
  </div>
136
  </div>
137
  </header>
138
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
139
 
140
  <style>
141
  /* Hero (full-width) */
142
+ .hero {
143
+ width: 100%;
144
+ padding: 48px 16px 16px;
145
+ text-align: center;
146
+ }
147
+ .hero-title {
148
+ font-size: clamp(28px, 4vw, 48px);
149
+ font-weight: 800;
150
+ line-height: 1.1;
151
+ margin: 0 0 8px;
152
+ max-width: 100%;
153
+ margin: auto;
154
+ }
155
+ .hero-banner {
156
+ max-width: 980px;
157
+ margin: 0 auto;
158
+ }
159
+ .hero-desc {
160
+ color: var(--muted-color);
161
+ font-style: italic;
162
+ margin: 0 0 16px 0;
163
+ }
164
 
165
  /* Meta (byline-like header) */
166
+ .meta {
167
+ border-top: 1px solid var(--border-color);
168
+ border-bottom: 1px solid var(--border-color);
169
+ padding: 1rem 0;
170
+ font-size: 0.9rem;
171
+ }
172
+ .meta-container {
173
+ max-width: 760px;
174
+ display: flex;
175
+ flex-direction: row;
176
+ justify-content: space-between;
177
+ margin: 0 auto;
178
+ padding: 0 var(--content-padding-x);
179
+ gap: 8px;
180
+ }
181
+ /* Subtle underline for links in meta; keep buttons without underline */
182
+ .meta-container a {
183
+ color: var(--primary-color);
184
+ text-decoration: underline;
185
+ text-underline-offset: 2px;
186
+ text-decoration-thickness: 0.06em;
187
+ text-decoration-color: var(--link-underline);
188
+ transition: text-decoration-color .15s ease-in-out;
189
+ }
190
+ .meta-container a:hover {
191
+ text-decoration-color: var(--link-underline-hover);
192
+ }
193
+ .meta-container a.button,
194
+ .meta-container .button {
195
+ text-decoration: none;
196
+ }
197
+ .meta-container-cell {
198
+ display: flex;
199
+ flex-direction: column;
200
+ gap: 8px;
201
+ }
202
+ .meta-container-cell h3 {
203
+ margin: 0;
204
+ font-size: 12px;
205
+ font-weight: 400;
206
+ color: var(--muted-color);
207
+ text-transform: uppercase;
208
+ letter-spacing: .02em;
209
+ }
210
+ .meta-container-cell p {
211
+ margin: 0;
212
+ }
213
+ .authors {
214
+ margin: 0;
215
+ list-style-type: none;
216
+ padding-left: 0;
217
+ }
218
+ .affiliations {
219
+ margin: 0;
220
+ padding-left: 1.25em;
221
+ }
222
+ .affiliations li {
223
+ margin: 0;
224
+ }
225
+
226
+ header.meta .meta-container {
227
+ flex-wrap: wrap;
228
+ row-gap: 12px;
229
+ }
230
+
231
+ @media print {
232
+ .meta-container-cell--pdf {
233
+ display: none !important;
234
+ }
235
+ }
236
  </style>
237
 
238
 
app/src/components/HtmlEmbed.astro CHANGED
@@ -31,6 +31,12 @@ const mountId = `frag-${Math.random().toString(36).slice(2)}`;
31
  <div><!-- Fragment not found: {src} --></div>
32
  ) }
33
 
 
 
 
 
 
 
34
  <script>
35
  // Re-execute <script> tags inside the injected fragment (innerHTML doesn't run scripts)
36
  const scriptEl = document.currentScript;
@@ -45,7 +51,7 @@ const mountId = `frag-${Math.random().toString(36).slice(2)}`;
45
  old.dataset.executed = 'true';
46
  if (old.src) {
47
  const s = document.createElement('script');
48
- Array.from(old.attributes).forEach(({ name, value }) => s.setAttribute(name, value));
49
  document.body.appendChild(s);
50
  } else {
51
  try {
@@ -57,14 +63,13 @@ const mountId = `frag-${Math.random().toString(36).slice(2)}`;
57
  }
58
  });
59
  };
60
- // Ensure execution when ready: run now if Plotly or D3 is present, or when document is ready; otherwise wait for 'load'
61
- // @ts-expect-error: Plotly/d3 are attached globally at runtime via embeds
62
- if (window.Plotly || window.d3 || document.readyState === 'complete') execute();
63
- else window.addEventListener('load', execute, { once: true });
64
  </script>
65
 
66
- <style>
67
- .html-embed { margin: 0; }
68
  .html-embed__title {
69
  text-align: left;
70
  font-weight: 600;
@@ -89,9 +94,38 @@ const mountId = `frag-${Math.random().toString(36).slice(2)}`;
89
  color: var(--muted-color);
90
  margin: 6px 0 0 0;
91
  }
92
- @media (prefers-color-scheme: dark) {
93
- [data-theme="dark"] .html-embed__card:not(.is-frameless) { background: #12151b; border-color: rgba(255,255,255,.15); }
94
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  @media print {
96
  .html-embed, .html-embed__card { max-width: 100% !important; width: 100% !important; margin-left: 0 !important; margin-right: 0 !important; }
97
  .html-embed__card { padding: 6px; }
 
31
  <div><!-- Fragment not found: {src} --></div>
32
  ) }
33
 
34
+ <script type="module" is:inline>
35
+ // Ensure global color palettes generator is loaded once per page
36
+ import '../scripts/color-palettes.js';
37
+ export {};
38
+ </script>
39
+
40
  <script>
41
  // Re-execute <script> tags inside the injected fragment (innerHTML doesn't run scripts)
42
  const scriptEl = document.currentScript;
 
51
  old.dataset.executed = 'true';
52
  if (old.src) {
53
  const s = document.createElement('script');
54
+ Array.from(old.attributes).forEach(attr => s.setAttribute(attr.name, attr.value));
55
  document.body.appendChild(s);
56
  } else {
57
  try {
 
63
  }
64
  });
65
  };
66
+ // Execute after DOM is parsed (ensures deferred module scripts are executed first)
67
+ if (document.readyState === 'loading') document.addEventListener('DOMContentLoaded', execute, { once: true });
68
+ else execute();
 
69
  </script>
70
 
71
+ <style is:global>
72
+ .html-embed { margin: 0 0 var(--block-spacing-y); overflow: hidden; }
73
  .html-embed__title {
74
  text-align: left;
75
  font-weight: 600;
 
94
  color: var(--muted-color);
95
  margin: 6px 0 0 0;
96
  }
97
+ /* Plotly fragments & controls */
98
+ .html-embed__card svg text { fill: var(--text-color) !important; }
99
+ .html-embed__card label { color: var(--text-color) !important; }
100
+ .plotly-graph-div { width: 100% !important; min-height: 320px; }
101
+ @media (max-width: 768px) { .plotly-graph-div { min-height: 260px; } }
102
+ [id^="plot-"] { display: flex; flex-direction: column; align-items: center; gap: 15px; }
103
+ .plotly_caption { font-style: italic; margin-top: 10px; }
104
+ .plotly_controls { display: flex; flex-wrap: wrap; justify-content: center; gap: 30px; }
105
+ .plotly_input_container { display: flex; align-items: center; flex-direction: column; gap: 10px; }
106
+ .plotly_input_container > select { padding: 2px 4px; line-height: 1.5em; text-align: center; border-radius: 4px; font-size: 12px; background-color: var(--neutral-200); outline: none; border: 1px solid var(--neutral-300); }
107
+ .plotly_slider { display: flex; align-items: center; gap: 10px; }
108
+ .plotly_slider > input[type="range"] { -webkit-appearance: none; appearance: none; height: 2px; background: var(--neutral-400); border-radius: 5px; outline: none; }
109
+ .plotly_slider > input[type="range"]::-webkit-slider-thumb { -webkit-appearance: none; width: 18px; height: 18px; border-radius: 50%; background: var(--primary-color); cursor: pointer; }
110
+ .plotly_slider > input[type="range"]::-moz-range-thumb { width: 18px; height: 18px; border-radius: 50%; background: var(--primary-color); cursor: pointer; }
111
+ .plotly_slider > span { font-size: 14px; line-height: 1.6em; min-width: 16px; }
112
+ /* Dark mode overrides for Plotly readability */
113
+ [data-theme="dark"] .html-embed__card:not(.is-frameless) { background: #12151b; border-color: rgba(255,255,255,.15); }
114
+ [data-theme="dark"] .html-embed__card .xaxislayer-above text,
115
+ [data-theme="dark"] .html-embed__card .yaxislayer-above text,
116
+ [data-theme="dark"] .html-embed__card .infolayer text,
117
+ [data-theme="dark"] .html-embed__card .legend text,
118
+ [data-theme="dark"] .html-embed__card .annotation text,
119
+ [data-theme="dark"] .html-embed__card .colorbar text,
120
+ [data-theme="dark"] .html-embed__card .hoverlayer text { fill: #fff !important; }
121
+ [data-theme="dark"] .html-embed__card .xaxislayer-above path,
122
+ [data-theme="dark"] .html-embed__card .yaxislayer-above path,
123
+ [data-theme="dark"] .html-embed__card .xlines-above,
124
+ [data-theme="dark"] .html-embed__card .ylines-above { stroke: rgba(255,255,255,.35) !important; }
125
+ [data-theme="dark"] .html-embed__card .gridlayer path { stroke: rgba(255,255,255,.15) !important; }
126
+ [data-theme="dark"] .html-embed__card .legend rect.bg { fill: rgba(0,0,0,.25) !important; stroke: rgba(255,255,255,.2) !important; }
127
+ [data-theme="dark"] .html-embed__card .hoverlayer .bg { fill: rgba(0,0,0,.8) !important; stroke: rgba(255,255,255,.2) !important; }
128
+ [data-theme="dark"] .html-embed__card .colorbar .cbbg { fill: rgba(0,0,0,.25) !important; stroke: rgba(255,255,255,.2) !important; }
129
  @media print {
130
  .html-embed, .html-embed__card { max-width: 100% !important; width: 100% !important; margin-left: 0 !important; margin-right: 0 !important; }
131
  .html-embed__card { padding: 6px; }
app/src/components/Note.astro CHANGED
@@ -1,24 +1,43 @@
1
  ---
2
- const { title, emoji, class: className, ...props } = Astro.props;
3
- const wrapperClass = ["note", className].filter(Boolean).join(" ");
 
 
 
 
 
 
4
  const hasHeader = (emoji && String(emoji).length > 0) || (title && String(title).length > 0);
5
  ---
6
  <div class={wrapperClass} {...props}>
7
- {hasHeader && <div class="note__header">
8
- {emoji && <span class="note__emoji">{emoji}</span>}
9
- {title && <span class="note__title">{title}</span>}
10
- </div>}
11
- <div class="note__content">
12
- <slot />
 
 
 
 
13
  </div>
14
  </div>
15
 
16
  <style>
17
- .note { background: var(--surface-bg); border-left: 2px solid var(--border-color); border-radius: 4px; padding: 10px 14px; margin: 12px 0; }
18
- .note__header { display: flex; align-items: center; gap: 6px; font-weight: 600; color: var(--text-color); margin-bottom: 6px; }
19
- .note__emoji { font-size: 24px; line-height: 1; }
20
- .note__title { font-size: 13px; letter-spacing: .2px; }
21
- .note__content { color: var(--text-color); font-size: 0.95rem; }
22
- .note__content > p:last-of-type { margin-bottom: 0 !important; }
 
 
 
 
 
 
 
 
 
23
  </style>
24
 
 
1
  ---
2
+ interface Props {
3
+ title?: string;
4
+ emoji?: string;
5
+ class?: string;
6
+ variant?: 'neutral' | 'info' | 'success' | 'danger';
7
+ }
8
+ const { title, emoji, class: className, variant = 'neutral', ...props } = Astro.props as Props;
9
+ const wrapperClass = ["note", `note--${variant}`, className].filter(Boolean).join(" ");
10
  const hasHeader = (emoji && String(emoji).length > 0) || (title && String(title).length > 0);
11
  ---
12
  <div class={wrapperClass} {...props}>
13
+ <div class="note__layout">
14
+ {emoji && <div class="note__icon" aria-hidden="true">
15
+ <span class="note__emoji">{emoji}</span>
16
+ </div>}
17
+ <div class="note__body">
18
+ {title && <div class="note__title">{title}</div>}
19
+ <div class="note__content">
20
+ <slot />
21
+ </div>
22
+ </div>
23
  </div>
24
  </div>
25
 
26
  <style>
27
+ .note { background: var(--surface-bg); border-left: 2px solid var(--border-color); border-radius: 4px; padding: 10px 14px; margin: var(--block-spacing-y) 0; }
28
+ .note__layout { display: flex; align-items: center; gap: 10px; }
29
+ .note__icon { flex: 0 0 auto; line-height: 1; }
30
+ .note__emoji { font-size: 32px; line-height: 1; display: block; }
31
+ .note__body { flex: 1 1 auto; min-width: 0; }
32
+ .note__title { font-size: 13px; letter-spacing: .2px; font-weight: 600; color: var(--text-color); margin-bottom: 4px; text-align: left; }
33
+ .note__content { color: var(--text-color); font-size: 0.95rem; text-align: left; }
34
+ /* Ensure the very last slotted element has no bottom margin */
35
+ .note .note__content > :global(*:last-child) { margin-bottom: 0 !important; }
36
+
37
+ /* Variants */
38
+ .note.note--neutral { border-left-color: var(--border-color); background: var(--surface-bg); }
39
+ .note.note--info { border-left-color: #f39c12; background: color-mix(in oklab, #f39c12 10%, var(--surface-bg)); }
40
+ .note.note--success { border-left-color: #2ecc71; background: color-mix(in oklab, #2ecc71 8%, var(--surface-bg)); }
41
+ .note.note--danger { border-left-color: #e74c3c; background: color-mix(in oklab, #e74c3c 8%, var(--surface-bg)); }
42
  </style>
43
 
app/src/components/ResponsiveImage.astro ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ // @ts-ignore - types provided by Astro at runtime
3
+ import { Image } from 'astro:assets';
4
+
5
+ interface Props {
6
+ /** Source image imported via astro:assets */
7
+ src: any;
8
+ /** Alt text for accessibility */
9
+ alt: string;
10
+ /** Optional HTML string caption (use slot caption for rich content) */
11
+ caption?: string;
12
+ /** Optional class to apply on the <figure> wrapper when caption is used */
13
+ figureClass?: string;
14
+ /** Enable medium-zoom behavior on this image */
15
+ zoomable?: boolean;
16
+ /** Show a download button overlay and enable download flow */
17
+ downloadable?: boolean;
18
+ /** Optional explicit file name to use on download */
19
+ downloadName?: string;
20
+ /** Optional explicit source URL to download instead of currentSrc */
21
+ downloadSrc?: string;
22
+ /** Any additional attributes should be forwarded to the underlying <Image> */
23
+ [key: string]: any;
24
+ }
25
+
26
+ const { caption, figureClass, zoomable, downloadable, downloadName, downloadSrc, ...imgProps } = Astro.props as Props;
27
+ const hasCaptionSlot = Astro.slots.has('caption');
28
+ const hasCaption = hasCaptionSlot || (typeof caption === 'string' && caption.length > 0);
29
+ const uid = `ri_${Math.random().toString(36).slice(2)}`;
30
+ const dataZoomable = (zoomable === true || (imgProps as any)['data-zoomable']) ? '1' : undefined;
31
+ const dataDownloadable = (downloadable === true || (imgProps as any)['data-downloadable']) ? '1' : undefined;
32
+ ---
33
+ <div class="ri-root" data-ri-root={uid}>
34
+ {hasCaption ? (
35
+ <figure class={(figureClass || '') + (dataDownloadable ? ' has-dl-btn' : '')}>
36
+ {dataDownloadable ? (
37
+ <span class="img-dl-wrap">
38
+ <Image {...imgProps} data-zoomable={dataZoomable} data-downloadable={dataDownloadable} data-download-name={downloadName} data-download-src={downloadSrc} />
39
+ <button type="button" class="button button--ghost img-dl-btn" aria-label="Download image" title={downloadName ? `Download ${downloadName}` : 'Download image'}>
40
+ <svg viewBox="0 0 24 24" aria-hidden="true" focusable="false"><path d="M12 16c-.26 0-.52-.11-.71-.29l-5-5a1 1 0 0 1 1.42-1.42L11 12.59V4a1 1 0 1 1 2 0v8.59l3.29-3.3a1 1 0 1 1 1.42 1.42l-5 5c-.19.18-.45.29-.71.29zM5 20a1 1 0 1 1 0-2h14a1 1 0 1 1 0 2H5z"/></svg>
41
+ </button>
42
+ </span>
43
+ ) : (
44
+ <Image {...imgProps} data-zoomable={dataZoomable} />
45
+ )}
46
+ <figcaption>
47
+ {hasCaptionSlot ? (
48
+ <slot name="caption" />
49
+ ) : (
50
+ caption && <span set:html={caption} />
51
+ )}
52
+ </figcaption>
53
+ </figure>
54
+ ) : (
55
+ dataDownloadable ? (
56
+ <span class="img-dl-wrap">
57
+ <Image {...imgProps} data-zoomable={dataZoomable} data-downloadable={dataDownloadable} data-download-name={downloadName} data-download-src={downloadSrc} />
58
+ <button type="button" class="button button--ghost img-dl-btn" aria-label="Download image" title={downloadName ? `Download ${downloadName}` : 'Download image'}>
59
+ <svg viewBox="0 0 24 24" aria-hidden="true" focusable="false"><path d="M12 16c-.26 0-.52-.11-.71-.29l-5-5a1 1 0 0 1 1.42-1.42L11 12.59V4a1 1 0 1 1 2 0v8.59l3.29-3.3a1 1 0 1 1 1.42 1.42l-5 5c-.19.18-.45.29-.71.29zM5 20a1 1 0 1 1 0-2h14a1 1 0 1 1 0 2H5z"/></svg>
60
+ </button>
61
+ </span>
62
+ ) : (
63
+ <Image {...imgProps} data-zoomable={dataZoomable} />
64
+ )
65
+ )}
66
+ </div>
67
+
68
+ <script is:inline>
69
+ (() => {
70
+ const scriptEl = document.currentScript;
71
+ const root = scriptEl ? scriptEl.previousElementSibling : null;
72
+ if (!root) return;
73
+ const img = (root.tagName === 'IMG' ? root : (root.querySelector ? root.querySelector('img') : null));
74
+ if (!img) return;
75
+
76
+ // medium-zoom integration scoped to this image only
77
+ const ensureMediumZoomReady = (cb) => {
78
+ // @ts-ignore
79
+ if (window.mediumZoom) return cb();
80
+ const retry = () => {
81
+ // @ts-ignore
82
+ if (window.mediumZoom) cb(); else setTimeout(retry, 30);
83
+ };
84
+ retry();
85
+ };
86
+
87
+ const initZoomIfNeeded = () => {
88
+ if (img.getAttribute('data-zoomable') !== '1') return;
89
+ const isDark = document.documentElement.getAttribute('data-theme') === 'dark';
90
+ const background = isDark ? 'rgba(0,0,0,.9)' : 'rgba(0,0,0,.85)';
91
+ ensureMediumZoomReady(() => {
92
+ // @ts-ignore
93
+ const instance = window.mediumZoom ? window.mediumZoom(img, { background, margin: 24, scrollOffset: 0 }) : null;
94
+ if (!instance) return;
95
+ let onScrollLike;
96
+ const attachCloseOnScroll = () => {
97
+ if (onScrollLike) return;
98
+ onScrollLike = () => { try { instance.close && instance.close(); } catch {} };
99
+ window.addEventListener('wheel', onScrollLike, { passive: true });
100
+ window.addEventListener('touchmove', onScrollLike, { passive: true });
101
+ window.addEventListener('scroll', onScrollLike, { passive: true });
102
+ };
103
+ const detachCloseOnScroll = () => {
104
+ if (!onScrollLike) return;
105
+ window.removeEventListener('wheel', onScrollLike);
106
+ window.removeEventListener('touchmove', onScrollLike);
107
+ window.removeEventListener('scroll', onScrollLike);
108
+ onScrollLike = null;
109
+ };
110
+ try { instance.on && instance.on('open', attachCloseOnScroll); } catch {}
111
+ try { instance.on && instance.on('close', detachCloseOnScroll); } catch {}
112
+ const themeObserver = new MutationObserver(() => {
113
+ const dark = document.documentElement.getAttribute('data-theme') === 'dark';
114
+ try { instance.update && instance.update({ background: dark ? 'rgba(0,0,0,.9)' : 'rgba(0,0,0,.85)' }); } catch {}
115
+ });
116
+ themeObserver.observe(document.documentElement, { attributes: true, attributeFilter: ['data-theme'] });
117
+ });
118
+ };
119
+
120
+ // Download button handler
121
+ const dlBtn = (root.querySelector ? root.querySelector('.img-dl-btn') : null);
122
+ if (dlBtn) {
123
+ dlBtn.addEventListener('click', async (ev) => {
124
+ try {
125
+ ev.preventDefault();
126
+ ev.stopPropagation();
127
+ const pickHrefAndName = () => {
128
+ const current = img.currentSrc || img.src || '';
129
+ let href = img.getAttribute('data-download-src') || current;
130
+ const deriveName = () => {
131
+ try {
132
+ const u = new URL(current, location.href);
133
+ const rawHref = u.searchParams.get('href');
134
+ const candidate = rawHref ? decodeURIComponent(rawHref) : u.pathname;
135
+ const last = String(candidate).split('/').pop() || '';
136
+ const base = last.split('?')[0].split('#')[0];
137
+ const m = base.match(/^(.+?\.(?:png|jpe?g|webp|avif|gif|svg))(?:[._-].*)?$/i);
138
+ if (m && m[1]) return m[1];
139
+ return base || 'image';
140
+ } catch { return 'image'; }
141
+ };
142
+ const name = img.getAttribute('data-download-name') || deriveName();
143
+ return { href, name };
144
+ };
145
+ const picked = pickHrefAndName();
146
+ const res = await fetch(picked.href, { credentials: 'same-origin' });
147
+ const blob = await res.blob();
148
+ const objectUrl = URL.createObjectURL(blob);
149
+ const tmp = document.createElement('a');
150
+ tmp.href = objectUrl;
151
+ tmp.download = picked.name || 'image';
152
+ tmp.target = '_self';
153
+ tmp.rel = 'noopener';
154
+ tmp.style.display = 'none';
155
+ document.body.appendChild(tmp);
156
+ tmp.click();
157
+ setTimeout(() => { URL.revokeObjectURL(objectUrl); tmp.remove(); }, 1000);
158
+ } catch {}
159
+ });
160
+ }
161
+
162
+ if (document.readyState === 'complete') initZoomIfNeeded();
163
+ else window.addEventListener('load', initZoomIfNeeded, { once: true });
164
+ })();
165
+ </script>
166
+
167
+
168
+ <style>
169
+
170
+ figure { margin: var(--block-spacing-y) 0; }
171
+ figcaption { text-align: left; font-size: 0.9rem; color: var(--muted-color); margin-top: 6px; }
172
+ .image-credit { display: block; margin-top: 4px; font-size: 12px; color: var(--muted-color); }
173
+ .image-credit a { color: inherit; text-decoration: underline; text-underline-offset: 2px; }
174
+
175
+ /* Zoomable overlay container (if used by any lightbox implementation) */
176
+ [data-zoom-overlay],
177
+ .zoom-overlay {
178
+ position: fixed;
179
+ inset: 0;
180
+ z-index: var(--z-overlay);
181
+ }
182
+
183
+ /* Download link inside figures */
184
+ figure .download-link { position: relative; z-index: var(--z-elevated); }
185
+
186
+ /* Opt-in zoomable images */
187
+ img[data-zoomable] { cursor: zoom-in; }
188
+ .medium-zoom--opened img[data-zoomable] { cursor: zoom-out; }
189
+
190
+ /* Download button for img[data-downloadable] */
191
+ figure.has-dl-btn { position: relative; }
192
+ .dl-host { position: relative; }
193
+ .img-dl-wrap { position: relative; display: inline-block; }
194
+ .img-dl-btn {
195
+ position: absolute;
196
+ right: 8px;
197
+ bottom: 8px;
198
+ align-items: center;
199
+ justify-content: center;
200
+ width: 30px;
201
+ height: 30px;
202
+ border-radius: 6px;
203
+ color: white;
204
+ text-decoration: none;
205
+ border: 1px solid rgba(255,255,255,0.25);
206
+ z-index: var(--z-elevated);
207
+ display: none;
208
+ }
209
+ .img-dl-btn svg { width: 18px; height: 18px; fill: currentColor; }
210
+ .img-dl-wrap:hover .img-dl-btn { display: inline-flex; }
211
+ [data-theme="dark"] .img-dl-btn { background: rgba(255,255,255,0.15); color: white; border-color: rgba(255,255,255,0.25); }
212
+ [data-theme="dark"] .img-dl-btn:hover { background: rgba(255,255,255,0.25); }
213
+ </style>
app/src/components/Sidenote.astro CHANGED
@@ -1,12 +1,37 @@
1
  ---
2
  ---
3
- <div class="margin-aside">
4
- <div class="margin-aside__main">
5
  <slot />
6
  </div>
7
- <aside class="margin-aside__aside">
8
  <slot name="aside" />
9
  </aside>
10
  </div>
11
 
12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  ---
3
+ <div class="aside">
4
+ <div class="aside__main">
5
  <slot />
6
  </div>
7
+ <aside class="aside__aside">
8
  <slot name="aside" />
9
  </aside>
10
  </div>
11
 
12
 
13
+ <style is:global>
14
+ .aside {
15
+ position: relative;
16
+ margin: 12px 0;
17
+ }
18
+
19
+ .aside__aside {
20
+ position: absolute;
21
+ top: 0;
22
+ right: -260px; /* push into the right grid column (width 260 + gap 32) */
23
+ width: 260px;
24
+ border-radius: 8px;
25
+ padding: 0 30px;
26
+ font-size: 0.9rem;
27
+ color: var(--muted-color);
28
+ }
29
+
30
+ @media (--bp-content-collapse) {
31
+ .aside__aside {
32
+ position: static;
33
+ width: auto;
34
+ margin-top: 8px;
35
+ }
36
+ }
37
+ </style>
app/src/components/TableOfContents.astro ADDED
@@ -0,0 +1,396 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ export interface Props { tableOfContentAutoCollapse?: boolean }
3
+ const { tableOfContentAutoCollapse = false } = Astro.props as Props;
4
+ ---
5
+ <nav class="table-of-contents" aria-label="Table of Contents" data-auto-collapse={tableOfContentAutoCollapse ? '1' : '0'}>
6
+ <div class="title">Table of Contents</div>
7
+ <div id="article-toc-placeholder"></div>
8
+ </nav>
9
+ <details class="table-of-contents-mobile">
10
+ <summary>Table of Contents</summary>
11
+ <div id="article-toc-mobile-placeholder"></div>
12
+ </details>
13
+
14
+ <script is:inline>
15
+ // Build TOC from article headings (h2/h3/h4) and render into the sticky aside
16
+ const buildTOC = () => {
17
+ const holder = document.getElementById('article-toc-placeholder');
18
+ const holderMobile = document.getElementById('article-toc-mobile-placeholder');
19
+ // Always rebuild TOC to avoid stale entries
20
+ if (holder) holder.innerHTML = '';
21
+ if (holderMobile) holderMobile.innerHTML = '';
22
+ const articleRoot = document.querySelector('section.content-grid main');
23
+ if (!articleRoot) return;
24
+ const headings = articleRoot.querySelectorAll('h2, h3, h4');
25
+ if (!headings.length) return;
26
+
27
+ // Filter out headings that should not appear in TOC
28
+ const normalize = (s) => String(s || '')
29
+ .toLowerCase()
30
+ .replace(/[^a-z0-9]+/g, ' ')
31
+ .trim();
32
+ const isTocLabel = (s) => /^(table\s+of\s+contents?)$|^toc$/i.test(String(s || '').replace(/[^a-zA-Z0-9]+/g, ' ').trim());
33
+ const shouldSkip = (h) => {
34
+ const t = h.textContent || '';
35
+ const id = String(h.id || '');
36
+ const slug = normalize(t).replace(/\s+/g, '_');
37
+ if (isTocLabel(t)) return true;
38
+ if (isTocLabel(id.replace(/[_-]+/g, ' '))) return true;
39
+ if (isTocLabel(slug.replace(/[_-]+/g, ' '))) return true;
40
+ return false;
41
+ };
42
+ const headingsArr = Array.from(headings).filter(h => !shouldSkip(h));
43
+ if (!headingsArr.length) return;
44
+
45
+ // Ensure unique ids for headings (deduplicate duplicates)
46
+ const usedIds = new Set();
47
+ const slugify = (s) => String(s || '')
48
+ .toLowerCase()
49
+ .trim()
50
+ .replace(/\s+/g, '_')
51
+ .replace(/[^a-z0-9_\-]/g, '');
52
+ headingsArr.forEach((h) => {
53
+ let id = (h.id || '').trim();
54
+ if (!id) {
55
+ const base = slugify(h.textContent || '');
56
+ id = base || 'section';
57
+ }
58
+ let candidate = id;
59
+ let n = 2;
60
+ while (usedIds.has(candidate)) {
61
+ candidate = `${id}-${n++}`;
62
+ }
63
+ if (h.id !== candidate) h.id = candidate;
64
+ usedIds.add(candidate);
65
+ });
66
+
67
+ const nav = document.createElement('nav');
68
+ let ulStack = [document.createElement('ul')];
69
+ nav.appendChild(ulStack[0]);
70
+
71
+ const levelOf = (tag) => tag === 'H2' ? 2 : tag === 'H3' ? 3 : 4;
72
+ let prev = 2;
73
+ let h2Count = -1;
74
+ const h2List = headingsArr.filter(h => h.tagName === 'H2');
75
+ headingsArr.forEach((h) => {
76
+ const lvl = levelOf(h.tagName);
77
+ // adjust depth
78
+ while (lvl > prev) { const ul = document.createElement('ul'); ulStack[ulStack.length-1].lastElementChild?.appendChild(ul); ulStack.push(ul); prev++; }
79
+ while (lvl < prev) { ulStack.pop(); prev--; }
80
+ const li = document.createElement('li');
81
+ const a = document.createElement('a');
82
+ a.href = '#' + h.id; a.textContent = h.textContent; a.target = '_self';
83
+ li.appendChild(a);
84
+ if (lvl === 2) {
85
+ h2Count += 1;
86
+ li.setAttribute('data-h2-idx', String(h2Count));
87
+ }
88
+ ulStack[ulStack.length-1].appendChild(li);
89
+ });
90
+
91
+ if (holder) holder.appendChild(nav);
92
+ const navClone = nav.cloneNode(true);
93
+ if (holderMobile) holderMobile.appendChild(navClone);
94
+
95
+ // active link on scroll
96
+ const links = [
97
+ ...(holder ? holder.querySelectorAll('a') : []),
98
+ ...(holderMobile ? holderMobile.querySelectorAll('a') : [])
99
+ ];
100
+ // Read breakpoint from CSS var and set autoCollapse only on desktop (disabled on mobile)
101
+ const getCollapsePx = () => {
102
+ const root = document.documentElement;
103
+ const raw = getComputedStyle(root).getPropertyValue('--bp-content-collapse').trim();
104
+ return raw || '1100px';
105
+ };
106
+ const mq = window.matchMedia(`(max-width: ${getCollapsePx()})`);
107
+ const attrEnabled = (document.querySelector('.table-of-contents')?.getAttribute('data-auto-collapse') === '1');
108
+ let autoCollapse = attrEnabled && !mq.matches;
109
+
110
+ // Inject styles for collapsible & animation
111
+ const ensureStyles = () => {
112
+ if (document.getElementById('toc-collapse-style')) return;
113
+ const style = document.createElement('style');
114
+ style.id = 'toc-collapse-style';
115
+ style.textContent = `
116
+ .table-of-contents nav.table-of-contents-collapsible > ul > li > ul,
117
+ details.table-of-contents-mobile nav.table-of-contents-collapsible > ul > li > ul { overflow: hidden; transition: height 200ms ease; }
118
+ .table-of-contents nav.table-of-contents-collapsible > ul > li.collapsed > ul,
119
+ details.table-of-contents-mobile nav.table-of-contents-collapsible > ul > li.collapsed > ul { display: block; }
120
+ `;
121
+ document.head.appendChild(style);
122
+ };
123
+ ensureStyles();
124
+
125
+ const getTopLevelItems = () => {
126
+ const sideNav = holder ? holder.querySelector('nav') : null;
127
+ const mobileNav = holderMobile ? holderMobile.querySelector('nav') : null;
128
+ const q = (navEl) => navEl ? Array.from(navEl.querySelectorAll(':scope > ul > li[data-h2-idx]')) : [];
129
+ return { sideNav, mobileNav, sideTop: q(sideNav), mobileTop: q(mobileNav) };
130
+ };
131
+
132
+ const setNavCollapsible = () => {
133
+ const sideNav = holder ? holder.querySelector('nav') : null;
134
+ const mobileNav = holderMobile ? holderMobile.querySelector('nav') : null;
135
+ if (sideNav) sideNav.classList.add('table-of-contents-collapsible');
136
+ if (mobileNav) mobileNav.classList.add('table-of-contents-collapsible');
137
+ };
138
+
139
+ const measure = (el) => {
140
+ if (!el) return 0;
141
+ // Temporarily set height to auto to measure scrollHeight reliably
142
+ const prev = el.style.height;
143
+ el.style.height = 'auto';
144
+ const h = el.scrollHeight;
145
+ el.style.height = prev || '';
146
+ return h;
147
+ };
148
+
149
+ const animateTo = (el, target) => {
150
+ if (!el) return;
151
+ const current = parseFloat(getComputedStyle(el).height) || 0;
152
+ if (Math.abs(current - target) < 1) {
153
+ el.style.height = target ? 'auto' : '0px';
154
+ return;
155
+ }
156
+ el.style.height = current + 'px';
157
+ // Force reflow
158
+ void el.offsetHeight;
159
+ el.style.height = target + 'px';
160
+ const onEnd = (e) => {
161
+ if (e.propertyName !== 'height') return;
162
+ el.removeEventListener('transitionend', onEnd);
163
+ if (target > 0) el.style.height = 'auto';
164
+ };
165
+ el.addEventListener('transitionend', onEnd);
166
+ };
167
+
168
+ let prevActiveIdx = -1;
169
+ const setCollapsedState = (activeIdx) => {
170
+ if (!autoCollapse) return;
171
+ if (activeIdx == null || activeIdx < 0) activeIdx = 0;
172
+ const { sideTop, mobileTop } = getTopLevelItems();
173
+ const update = (items) => items.forEach((li) => {
174
+ const idx = Number(li.getAttribute('data-h2-idx') || '-1');
175
+ const sub = li.querySelector(':scope > ul');
176
+ if (!sub) return;
177
+ if (idx === activeIdx) {
178
+ li.classList.remove('collapsed');
179
+ const target = measure(sub);
180
+ animateTo(sub, target);
181
+ } else {
182
+ li.classList.add('collapsed');
183
+ animateTo(sub, 0);
184
+ }
185
+ });
186
+ update(sideTop);
187
+ update(mobileTop);
188
+ setNavCollapsible();
189
+ prevActiveIdx = activeIdx;
190
+ };
191
+
192
+ // When switching between desktop/mobile, refresh autoCollapse and expand all on mobile
193
+ const expandAll = () => {
194
+ const { sideTop, mobileTop } = getTopLevelItems();
195
+ const expand = (items) => items.forEach((li) => {
196
+ li.classList.remove('collapsed');
197
+ const sub = li.querySelector(':scope > ul');
198
+ if (sub) sub.style.height = 'auto';
199
+ });
200
+ expand(sideTop);
201
+ expand(mobileTop);
202
+ };
203
+
204
+ const onMqChange = () => {
205
+ autoCollapse = attrEnabled && !mq.matches;
206
+ if (!autoCollapse) {
207
+ expandAll();
208
+ } else {
209
+ setCollapsedState(prevActiveIdx);
210
+ }
211
+ };
212
+ if (mq.addEventListener) mq.addEventListener('change', onMqChange);
213
+ else if (mq.addListener) mq.addListener(onMqChange);
214
+
215
+ const onScroll = () => {
216
+ // active link highlight
217
+ let activeIdx = -1;
218
+ for (let i = headingsArr.length - 1; i >= 0; i--) {
219
+ const top = headingsArr[i].getBoundingClientRect().top;
220
+ if (top - 60 <= 0) {
221
+ links.forEach(l => l.classList.remove('active'));
222
+ const id = '#' + headingsArr[i].id;
223
+ const actives = Array.from(links).filter(l => l.getAttribute('href') === id);
224
+ actives.forEach(a => a.classList.add('active'));
225
+ if (headingsArr[i].tagName === 'H2') {
226
+ activeIdx = h2List.indexOf(headingsArr[i]);
227
+ } else {
228
+ for (let j = i; j >= 0; j--) {
229
+ if (headingsArr[j].tagName === 'H2') { activeIdx = h2List.indexOf(headingsArr[j]); break; }
230
+ }
231
+ }
232
+ break;
233
+ }
234
+ }
235
+ if (activeIdx !== prevActiveIdx) setCollapsedState(activeIdx);
236
+ };
237
+
238
+ // If auto-collapse, collapse immediately (expand first section) before any scroll
239
+ if (autoCollapse) setCollapsedState(0);
240
+
241
+ window.addEventListener('scroll', onScroll);
242
+ // Initialize state
243
+ onScroll();
244
+
245
+ // Close mobile accordion when a link inside it is clicked
246
+ if (holderMobile) {
247
+ const details = holderMobile.closest('details');
248
+ holderMobile.addEventListener('click', (ev) => {
249
+ const target = ev.target;
250
+ const anchor = target && 'closest' in target ? target.closest('a') : null;
251
+ if (anchor instanceof HTMLAnchorElement && details && details.open) {
252
+ details.open = false;
253
+ }
254
+ });
255
+ }
256
+ };
257
+
258
+ if (document.readyState === 'loading') {
259
+ document.addEventListener('DOMContentLoaded', buildTOC, { once: true });
260
+ } else { buildTOC(); }
261
+ </script>
262
+
263
+ <style is:global>
264
+ /* Sticky aside */
265
+ .table-of-contents {
266
+ position: sticky;
267
+ top: 32px;
268
+ }
269
+
270
+ .table-of-contents nav {
271
+ border-left: 1px solid var(--border-color);
272
+ padding-left: 16px;
273
+ font-size: 13px;
274
+ }
275
+
276
+ .table-of-contents .title {
277
+ font-weight: 600;
278
+ font-size: 14px;
279
+ margin-bottom: 8px;
280
+ }
281
+
282
+ /* Look & feel */
283
+ .table-of-contents nav ul {
284
+ margin: 0 0 6px;
285
+ padding-left: 1em;
286
+ }
287
+
288
+ .table-of-contents nav li {
289
+ list-style: none;
290
+ margin: .25em 0;
291
+ }
292
+
293
+ .table-of-contents nav a,
294
+ .table-of-contents nav a:link,
295
+ .table-of-contents nav a:visited {
296
+ color: var(--text-color);
297
+ text-decoration: none;
298
+ border-bottom: none;
299
+ }
300
+
301
+ .table-of-contents nav > ul > li > a {
302
+ font-weight: 700;
303
+ }
304
+
305
+ .table-of-contents nav a:hover {
306
+ text-decoration: underline solid var(--muted-color);
307
+ }
308
+
309
+ .table-of-contents nav a.active {
310
+ text-decoration: underline;
311
+ }
312
+
313
+ /* Mobile accordion */
314
+ .table-of-contents-mobile {
315
+ display: none;
316
+ margin: 8px 0 16px;
317
+ }
318
+
319
+ .table-of-contents-mobile > summary {
320
+ cursor: pointer;
321
+ list-style: none;
322
+ padding: var(--spacing-3) var(--spacing-4);
323
+ border: 1px solid var(--border-color);
324
+ border-radius: 8px;
325
+ color: var(--text-color);
326
+ font-weight: 600;
327
+ position: relative;
328
+ }
329
+
330
+ .table-of-contents-mobile[open] > summary {
331
+ border-bottom-left-radius: 0;
332
+ border-bottom-right-radius: 0;
333
+ }
334
+
335
+ /* Disclosure arrow for mobile summary */
336
+ .table-of-contents-mobile > summary::after {
337
+ content: '';
338
+ position: absolute;
339
+ right: var(--spacing-4);
340
+ top: 50%;
341
+ width: 8px;
342
+ height: 8px;
343
+ border-right: 2px solid currentColor;
344
+ border-bottom: 2px solid currentColor;
345
+ transform: translateY(-70%) rotate(45deg);
346
+ transition: transform 150ms ease;
347
+ opacity: .7;
348
+ }
349
+
350
+ .table-of-contents-mobile[open] > summary::after {
351
+ transform: translateY(-30%) rotate(-135deg);
352
+ }
353
+
354
+ .table-of-contents-mobile nav {
355
+ border-left: none;
356
+ padding: 10px 12px;
357
+ font-size: 14px;
358
+ border: 1px solid var(--border-color);
359
+ border-top: none;
360
+ border-bottom-left-radius: 8px;
361
+ border-bottom-right-radius: 8px;
362
+ }
363
+
364
+ .table-of-contents-mobile nav ul {
365
+ margin: 0 0 6px;
366
+ padding-left: 1em;
367
+ }
368
+
369
+ .table-of-contents-mobile nav li {
370
+ list-style: none;
371
+ margin: .25em 0;
372
+ }
373
+
374
+ .table-of-contents-mobile nav a,
375
+ .table-of-contents-mobile nav a:link,
376
+ .table-of-contents-mobile nav a:visited {
377
+ color: var(--text-color);
378
+ text-decoration: none;
379
+ border-bottom: none;
380
+ }
381
+
382
+ .table-of-contents-mobile nav > ul > li > a {
383
+ font-weight: 700;
384
+ }
385
+
386
+ .table-of-contents-mobile nav a:hover {
387
+ text-decoration: underline solid var(--muted-color);
388
+ }
389
+
390
+ .table-of-contents-mobile nav a.active {
391
+ text-decoration: underline;
392
+ }
393
+
394
+
395
+
396
+ </style>
app/src/components/ThemeToggle.astro CHANGED
@@ -44,3 +44,10 @@
44
  </button>
45
 
46
 
 
 
 
 
 
 
 
 
44
  </button>
45
 
46
 
47
+ <style>
48
+ #theme-toggle { display: inline-flex; align-items: center; gap: 8px; border: none; background: transparent; padding: 6px 10px; border-radius: 8px; cursor: pointer; margin: 12px 16px; color: var(--text-color) !important; }
49
+ #theme-toggle .icon.dark { display: none; }
50
+ [data-theme="dark"] #theme-toggle .icon.light { display: none; }
51
+ [data-theme="dark"] #theme-toggle .icon.dark { display: inline; }
52
+ #theme-toggle .icon { filter: none !important; }
53
+ </style>
app/src/content/article.mdx CHANGED
@@ -3,12 +3,24 @@ title: "FineVision:<br/> Open Data is all you need"
3
  subtitle: "A new open dataset for data-centric training of Vision Language Models"
4
  description: "A new open dataset for data-centric training of Vision Language Models"
5
  authors:
6
- - "Luis Wiedmann"
7
- - "Orr Zohar"
8
- - "Andi Marafioti"
9
- - "Amir Mahla"
10
- - "Thibaud Frere"
11
- affiliation: "Hugging Face"
 
 
 
 
 
 
 
 
 
 
 
 
12
  published: "Sep 4, 2025"
13
  tags:
14
  - research
@@ -33,6 +45,8 @@ import Accordion from '../components/Accordion.astro'
33
  Additionally, we ran extensive ablations and compared the performance of models trained on our dataset with common open source alternatives. Our dataset is both more divers, and achieves an average improvement of **35%** in **10 common benchmarks** over all baselines.
34
 
35
  To use the dataset, simply load it with:
 
 
36
  ```python
37
  from datasets import load_dataset
38
 
@@ -51,7 +65,6 @@ Projects like The Cauldron, LLaVa and Cambrian aim to provide such datasets, but
51
  ### Data Collection
52
  We manually collect **over 180** image-text datasets from the recent literature and create new subsets in lacking domains.
53
 
54
- <Wide>
55
  <Accordion title="FineVision Subsets">
56
  |Subset Name |Total Images|Total Samples|Total Turns|Total Question Tokens|Total Answer Tokens|Category |Source |
57
  |--------------------------------------|------------|-------------|-----------|---------------------|-------------------|----------------------|------- |
@@ -242,7 +255,6 @@ We manually collect **over 180** image-text datasets from the recent literature
242
  |text_OpenMathInstruct-2 |0 |1,000,000 |1,000,000 |74,905,850 |413,132,418 |Text-only |[@toshniwal_openmathinstruct-2_2024] |
243
 
244
  </Accordion>
245
- </Wide>
246
 
247
  ### Cleaning
248
  After gathering all the sub-datasets, every turn is cleaned.
 
3
  subtitle: "A new open dataset for data-centric training of Vision Language Models"
4
  description: "A new open dataset for data-centric training of Vision Language Models"
5
  authors:
6
+ - name: "Luis Wiedmann"
7
+ url: "https://huggingface.co/lusxvr"
8
+ affiliations: [1]
9
+ - name: "Orr Zohar"
10
+ url: "https://huggingface.co/orrzohar"
11
+ affiliations: [1]
12
+ - name: "Andi Marafioti"
13
+ url: "https://huggingface.co/andito"
14
+ affiliations: [1]
15
+ - name: "Amir Mahla"
16
+ url: "https://huggingface.co/A-Mahla"
17
+ affiliations: [1]
18
+ - name: "Thibaud Frere"
19
+ url: "https://huggingface.co/tfrere"
20
+ affiliations: [1]
21
+ affiliations:
22
+ - name: "Hugging Face"
23
+ url: "https://huggingface.co"
24
  published: "Sep 4, 2025"
25
  tags:
26
  - research
 
45
  Additionally, we ran extensive ablations and compared the performance of models trained on our dataset with common open source alternatives. Our dataset is both more divers, and achieves an average improvement of **35%** in **10 common benchmarks** over all baselines.
46
 
47
  To use the dataset, simply load it with:
48
+
49
+ <small class="muted">python</small>
50
  ```python
51
  from datasets import load_dataset
52
 
 
65
  ### Data Collection
66
  We manually collect **over 180** image-text datasets from the recent literature and create new subsets in lacking domains.
67
 
 
68
  <Accordion title="FineVision Subsets">
69
  |Subset Name |Total Images|Total Samples|Total Turns|Total Question Tokens|Total Answer Tokens|Category |Source |
70
  |--------------------------------------|------------|-------------|-----------|---------------------|-------------------|----------------------|------- |
 
255
  |text_OpenMathInstruct-2 |0 |1,000,000 |1,000,000 |74,905,850 |413,132,418 |Text-only |[@toshniwal_openmathinstruct-2_2024] |
256
 
257
  </Accordion>
 
258
 
259
  ### Cleaning
260
  After gathering all the sub-datasets, every turn is cleaned.
app/src/content/assets/data/against_baselines.csv CHANGED
@@ -1,961 +1,3 @@
1
- run,step,metric,value,stderr
2
- FineVision,1000,ai2d_exact_match,0.2548575129533679,0.007843322436924496
3
- FineVision,1000,average,0.27120689295763617,
4
- FineVision,1000,average_rank,2.8,
5
- FineVision,1000,chartqa_relaxed_overall,0.3308,0.009411906161401973
6
- FineVision,1000,docvqa_val_anls,0.3528553494243383,0.005852289239342309
7
- FineVision,1000,infovqa_val_anls,0.17320578642581314,0.006297063452679795
8
- FineVision,1000,mme_total_score,977.4280712284914,
9
- FineVision,1000,mmmu_val_mmmu_acc,0.25222,
10
- FineVision,1000,mmstar_average,0.23215874078908072,
11
- FineVision,1000,ocrbench_ocrbench_accuracy,0.286,
12
- FineVision,1000,seedbench_seed_all,0.2563646470261256,
13
- FineVision,1000,textvqa_val_exact_match,0.3024,0.00628900296642181
14
- FineVision,2000,ai2d_exact_match,0.26295336787564766,0.007923526907377255
15
- FineVision,2000,average,0.3202068275596269,
16
- FineVision,2000,average_rank,2.6,
17
- FineVision,2000,chartqa_relaxed_overall,0.4688,0.009982508912777261
18
- FineVision,2000,docvqa_val_anls,0.4452261510942785,0.00614755494712251
19
- FineVision,2000,infovqa_val_anls,0.1820547866557169,0.006217861455795791
20
- FineVision,2000,mme_total_score,1049.3036214485794,
21
- FineVision,2000,mmmu_val_mmmu_acc,0.24556,
22
- FineVision,2000,mmstar_average,0.21305462434540698,
23
- FineVision,2000,ocrbench_ocrbench_accuracy,0.395,
24
- FineVision,2000,seedbench_seed_all,0.258532518065592,
25
- FineVision,2000,textvqa_val_exact_match,0.41068000000000005,0.006697862330024289
26
- FineVision,3000,ai2d_exact_match,0.25226683937823835,0.007816909588794397
27
- FineVision,3000,average,0.3507423834414229,
28
- FineVision,3000,average_rank,2.6,
29
- FineVision,3000,chartqa_relaxed_overall,0.5028,0.010001843767601082
30
- FineVision,3000,docvqa_val_anls,0.502653993831009,0.006267072346683124
31
- FineVision,3000,infovqa_val_anls,0.21728617578189535,0.006796941784959762
32
- FineVision,3000,mme_total_score,1170.2383953581434,
33
- FineVision,3000,mmmu_val_mmmu_acc,0.27556,
34
- FineVision,3000,mmstar_average,0.25432376938577683,
35
- FineVision,3000,ocrbench_ocrbench_accuracy,0.436,
36
- FineVision,3000,seedbench_seed_all,0.2792106725958866,
37
- FineVision,3000,textvqa_val_exact_match,0.43658,0.006766885462882726
38
- FineVision,4000,ai2d_exact_match,0.2645725388601036,0.007939149662089447
39
- FineVision,4000,average,0.36961781722974835,
40
- FineVision,4000,average_rank,2.7,
41
- FineVision,4000,chartqa_relaxed_overall,0.5312,0.009982508912777261
42
- FineVision,4000,docvqa_val_anls,0.5374434618615119,0.0062905728113059655
43
- FineVision,4000,infovqa_val_anls,0.2287924838861707,0.006994568698639919
44
- FineVision,4000,mme_total_score,1155.203781512605,
45
- FineVision,4000,mmmu_val_mmmu_acc,0.25556,
46
- FineVision,4000,mmstar_average,0.2575590188757354,
47
- FineVision,4000,ocrbench_ocrbench_accuracy,0.453,
48
- FineVision,4000,seedbench_seed_all,0.33913285158421347,
49
- FineVision,4000,textvqa_val_exact_match,0.4593,0.006791695475025738
50
- FineVision,5000,ai2d_exact_match,0.3125,0.008342439145556371
51
- FineVision,5000,average,0.3974627910380972,
52
- FineVision,5000,average_rank,2.6,
53
- FineVision,5000,chartqa_relaxed_overall,0.5488,0.00995424828018316
54
- FineVision,5000,docvqa_val_anls,0.552360266782429,0.006300308519952055
55
- FineVision,5000,infovqa_val_anls,0.23425555286643698,0.007002254622066442
56
- FineVision,5000,mme_total_score,1181.4653861544618,
57
- FineVision,5000,mmmu_val_mmmu_acc,0.26667,
58
- FineVision,5000,mmstar_average,0.29596648146165705,
59
- FineVision,5000,ocrbench_ocrbench_accuracy,0.462,
60
- FineVision,5000,seedbench_seed_all,0.43107281823235133,
61
- FineVision,5000,textvqa_val_exact_match,0.47354000000000007,0.0068172185364497985
62
- FineVision,6000,ai2d_exact_match,0.358160621761658,0.008629463221867162
63
- FineVision,6000,average,0.4161227404571003,
64
- FineVision,6000,average_rank,2.1,
65
- FineVision,6000,chartqa_relaxed_overall,0.5628,0.00992279440175477
66
- FineVision,6000,docvqa_val_anls,0.5747451497228876,0.00625495440870239
67
- FineVision,6000,infovqa_val_anls,0.22152017368968838,0.006604546680525351
68
- FineVision,6000,mme_total_score,1284.1648659463785,
69
- FineVision,6000,mmmu_val_mmmu_acc,0.27111,
70
- FineVision,6000,mmstar_average,0.2978489412854164,
71
- FineVision,6000,ocrbench_ocrbench_accuracy,0.495,
72
- FineVision,6000,seedbench_seed_all,0.4795997776542524,
73
- FineVision,6000,textvqa_val_exact_match,0.48432,0.006800535050670284
74
- FineVision,7000,ai2d_exact_match,0.3707901554404145,0.00869347755587734
75
- FineVision,7000,average,0.4291083177345374,
76
- FineVision,7000,average_rank,2.4,
77
- FineVision,7000,chartqa_relaxed_overall,0.5656,0.009915542506251351
78
- FineVision,7000,docvqa_val_anls,0.5940907049431567,0.006224236305767187
79
- FineVision,7000,infovqa_val_anls,0.2515675215816963,0.007105097396092786
80
- FineVision,7000,mme_total_score,1185.875650260104,
81
- FineVision,7000,mmmu_val_mmmu_acc,0.26556,
82
- FineVision,7000,mmstar_average,0.31372400960777047,
83
- FineVision,7000,ocrbench_ocrbench_accuracy,0.504,
84
- FineVision,7000,seedbench_seed_all,0.4964424680377988,
85
- FineVision,7000,textvqa_val_exact_match,0.5002,0.006794794025220267
86
- FineVision,8000,ai2d_exact_match,0.37759067357512954,0.008725299846043883
87
- FineVision,8000,average,0.43846759477995995,
88
- FineVision,8000,average_rank,2.2,
89
- FineVision,8000,chartqa_relaxed_overall,0.5832,0.009862556058385773
90
- FineVision,8000,docvqa_val_anls,0.6017336419437208,0.006231612198089698
91
- FineVision,8000,infovqa_val_anls,0.2449256624147254,0.006992518502948913
92
- FineVision,8000,mme_total_score,1199.2409963985594,
93
- FineVision,8000,mmmu_val_mmmu_acc,0.28111,
94
- FineVision,8000,mmstar_average,0.33512257186205047,
95
- FineVision,8000,ocrbench_ocrbench_accuracy,0.51,
96
- FineVision,8000,seedbench_seed_all,0.5024458032240133,
97
- FineVision,8000,textvqa_val_exact_match,0.51008,0.006796301690135059
98
- FineVision,9000,ai2d_exact_match,0.4067357512953368,0.008841214921078996
99
- FineVision,9000,average,0.4422510732201056,
100
- FineVision,9000,average_rank,2.0,
101
- FineVision,9000,chartqa_relaxed_overall,0.5912,0.009834211136815875
102
- FineVision,9000,docvqa_val_anls,0.6170968481662739,0.00617235763542544
103
- FineVision,9000,infovqa_val_anls,0.23537031288570615,0.00670318154156447
104
- FineVision,9000,mme_total_score,1231.5195078031213,
105
- FineVision,9000,mmmu_val_mmmu_acc,0.25889,
106
- FineVision,9000,mmstar_average,0.3216444898242951,
107
- FineVision,9000,ocrbench_ocrbench_accuracy,0.515,
108
- FineVision,9000,seedbench_seed_all,0.5120622568093385,
109
- FineVision,9000,textvqa_val_exact_match,0.52226,0.006792711289708482
110
- FineVision,10000,ai2d_exact_match,0.39993523316062174,0.008817096257082848
111
- FineVision,10000,average,0.4523875703250908,
112
- FineVision,10000,average_rank,1.7,
113
- FineVision,10000,chartqa_relaxed_overall,0.5996,0.00980154906867574
114
- FineVision,10000,docvqa_val_anls,0.6262613496433054,0.006147756371688175
115
- FineVision,10000,infovqa_val_anls,0.263290074230132,0.007186788766942786
116
- FineVision,10000,mme_total_score,1240.8218287314926,
117
- FineVision,10000,mmmu_val_mmmu_acc,0.28778,
118
- FineVision,10000,mmstar_average,0.32972717906018517,
119
- FineVision,10000,ocrbench_ocrbench_accuracy,0.517,
120
- FineVision,10000,seedbench_seed_all,0.5217342968315731,
121
- FineVision,10000,textvqa_val_exact_match,0.5261600000000001,0.006785774843600811
122
- FineVision,11000,ai2d_exact_match,0.422279792746114,0.008889771831066474
123
- FineVision,11000,average,0.4561398159525099,
124
- FineVision,11000,average_rank,1.7,
125
- FineVision,11000,chartqa_relaxed_overall,0.6104,0.009755142291143075
126
- FineVision,11000,docvqa_val_anls,0.6373130149166712,0.006128022584995044
127
- FineVision,11000,infovqa_val_anls,0.24419378339723755,0.006897644885887063
128
- FineVision,11000,mme_total_score,1322.9488795518205,
129
- FineVision,11000,mmmu_val_mmmu_acc,0.27778,
130
- FineVision,11000,mmstar_average,0.3298563439522548,
131
- FineVision,11000,ocrbench_ocrbench_accuracy,0.521,
132
- FineVision,11000,seedbench_seed_all,0.5237354085603113,
133
- FineVision,11000,textvqa_val_exact_match,0.5387,0.006770851562852138
134
- FineVision,12000,ai2d_exact_match,0.42001295336787564,0.008883255931688034
135
- FineVision,12000,average,0.4582751140055433,
136
- FineVision,12000,average_rank,1.6,
137
- FineVision,12000,chartqa_relaxed_overall,0.618,0.009719474639861454
138
- FineVision,12000,docvqa_val_anls,0.6393961983751871,0.0061228747388476674
139
- FineVision,12000,infovqa_val_anls,0.24798874058574302,0.006855374548993139
140
- FineVision,12000,mme_total_score,1225.6453581432572,
141
- FineVision,12000,mmmu_val_mmmu_acc,0.27889,
142
- FineVision,12000,mmstar_average,0.34010867846816534,
143
- FineVision,12000,ocrbench_ocrbench_accuracy,0.512,
144
- FineVision,12000,seedbench_seed_all,0.5350194552529183,
145
- FineVision,12000,textvqa_val_exact_match,0.5330600000000001,0.006777713092109446
146
- FineVision,13000,ai2d_exact_match,0.4375,0.008928571428571428
147
- FineVision,13000,average,0.4692868662590049,
148
- FineVision,13000,average_rank,1.5,
149
- FineVision,13000,chartqa_relaxed_overall,0.6148,0.00973479791861169
150
- FineVision,13000,docvqa_val_anls,0.6511374872549951,0.006086953065248391
151
- FineVision,13000,infovqa_val_anls,0.24465055100441893,0.006808432538374664
152
- FineVision,13000,mme_total_score,1281.7122849139657,
153
- FineVision,13000,mmmu_val_mmmu_acc,0.28222,
154
- FineVision,13000,mmstar_average,0.3453069542917521,
155
- FineVision,13000,ocrbench_ocrbench_accuracy,0.549,
156
- FineVision,13000,seedbench_seed_all,0.5442468037798777,
157
- FineVision,13000,textvqa_val_exact_match,0.55472,0.0067416788982325
158
- FineVision,14000,ai2d_exact_match,0.4572538860103627,0.00896620675297095
159
- FineVision,14000,average,0.47352486841689195,
160
- FineVision,14000,average_rank,1.4,
161
- FineVision,14000,chartqa_relaxed_overall,0.6172,0.009723347231923635
162
- FineVision,14000,docvqa_val_anls,0.6502269393708169,0.006057950730638126
163
- FineVision,14000,infovqa_val_anls,0.25805460837190913,0.007037735231659539
164
- FineVision,14000,mme_total_score,1309.1444577831132,
165
- FineVision,14000,mmmu_val_mmmu_acc,0.28111,
166
- FineVision,14000,mmstar_average,0.34575818188776586,
167
- FineVision,14000,ocrbench_ocrbench_accuracy,0.551,
168
- FineVision,14000,seedbench_seed_all,0.5483602001111729,
169
- FineVision,14000,textvqa_val_exact_match,0.55276,0.006751206724612103
170
- FineVision,15000,ai2d_exact_match,0.45045336787564766,0.008954861634252399
171
- FineVision,15000,average,0.47878665012878824,
172
- FineVision,15000,average_rank,1.3,
173
- FineVision,15000,chartqa_relaxed_overall,0.612,0.009747841205275417
174
- FineVision,15000,docvqa_val_anls,0.6621413031955148,0.006056838050222495
175
- FineVision,15000,infovqa_val_anls,0.2706898598157733,0.007200315730154543
176
- FineVision,15000,mme_total_score,1384.2171868747498,
177
- FineVision,15000,mmmu_val_mmmu_acc,0.30222,
178
- FineVision,15000,mmstar_average,0.35408135695920684,
179
- FineVision,15000,ocrbench_ocrbench_accuracy,0.558,
180
- FineVision,15000,seedbench_seed_all,0.5411339633129516,
181
- FineVision,15000,textvqa_val_exact_match,0.5583600000000001,0.0067279027203879065
182
- FineVision,16000,ai2d_exact_match,0.45077720207253885,0.008955440137395838
183
- FineVision,16000,average,0.47665128022935843,
184
- FineVision,16000,average_rank,1.5,
185
- FineVision,16000,chartqa_relaxed_overall,0.632,0.00964715642305132
186
- FineVision,16000,docvqa_val_anls,0.6709415729142987,0.005999818105621502
187
- FineVision,16000,infovqa_val_anls,0.26050032542402035,0.006997451875879188
188
- FineVision,16000,mme_total_score,1317.8491396558625,
189
- FineVision,16000,mmmu_val_mmmu_acc,0.27556,
190
- FineVision,16000,mmstar_average,0.33214333327093315,
191
- FineVision,16000,ocrbench_ocrbench_accuracy,0.56,
192
- FineVision,16000,seedbench_seed_all,0.5463590883824346,
193
- FineVision,16000,textvqa_val_exact_match,0.56158,0.006723854754867398
194
- FineVision,17000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
195
- FineVision,17000,average,0.4777141780162423,
196
- FineVision,17000,average_rank,1.3,
197
- FineVision,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
198
- FineVision,17000,docvqa_val_anls,0.6796338519136422,0.005948761388267941
199
- FineVision,17000,infovqa_val_anls,0.28070956072505215,0.007298333094144192
200
- FineVision,17000,mme_total_score,1381.9161664665867,
201
- FineVision,17000,mmmu_val_mmmu_acc,0.27667,
202
- FineVision,17000,mmstar_average,0.3370289492329521,
203
- FineVision,17000,ocrbench_ocrbench_accuracy,0.519,
204
- FineVision,17000,seedbench_seed_all,0.5510283490828238,
205
- FineVision,17000,textvqa_val_exact_match,0.56416,0.006724830373229479
206
- FineVision,18000,ai2d_exact_match,0.46567357512953367,0.008977921602780726
207
- FineVision,18000,average,0.4819834595278701,
208
- FineVision,18000,average_rank,1.2,
209
- FineVision,18000,chartqa_relaxed_overall,0.6376,0.009615793331418735
210
- FineVision,18000,docvqa_val_anls,0.6775884603912571,0.005972234236435759
211
- FineVision,18000,infovqa_val_anls,0.27154318420389256,0.007164903131667027
212
- FineVision,18000,mme_total_score,1336.922769107643,
213
- FineVision,18000,mmmu_val_mmmu_acc,0.28667,
214
- FineVision,18000,mmstar_average,0.34482796716566916,
215
- FineVision,18000,ocrbench_ocrbench_accuracy,0.533,
216
- FineVision,18000,seedbench_seed_all,0.5543079488604781,
217
- FineVision,18000,textvqa_val_exact_match,0.5666399999999999,0.006713392287599574
218
- FineVision,19000,ai2d_exact_match,0.4682642487046632,0.008981008686994101
219
- FineVision,19000,average,0.4899006713916878,
220
- FineVision,19000,average_rank,1.2,
221
- FineVision,19000,chartqa_relaxed_overall,0.6444,0.009575809858898698
222
- FineVision,19000,docvqa_val_anls,0.678226526479947,0.005970619221588814
223
- FineVision,19000,infovqa_val_anls,0.26993847247278,0.0071348470764911525
224
- FineVision,19000,mme_total_score,1406.6628651460583,
225
- FineVision,19000,mmmu_val_mmmu_acc,0.28333,
226
- FineVision,19000,mmstar_average,0.356220913822775,
227
- FineVision,19000,ocrbench_ocrbench_accuracy,0.577,
228
- FineVision,19000,seedbench_seed_all,0.554585881045025,
229
- FineVision,19000,textvqa_val_exact_match,0.57714,0.0066918487914812905
230
- FineVision,20000,ai2d_exact_match,0.47571243523316065,0.00898853090258662
231
- FineVision,20000,average,0.4873169067639118,
232
- FineVision,20000,average_rank,1.2,
233
- FineVision,20000,chartqa_relaxed_overall,0.6336,0.009638338810708618
234
- FineVision,20000,docvqa_val_anls,0.6895214454380043,0.005896462073053767
235
- FineVision,20000,infovqa_val_anls,0.2655657550458317,0.007033265532032538
236
- FineVision,20000,mme_total_score,1324.6738695478193,
237
- FineVision,20000,mmmu_val_mmmu_acc,0.30111,
238
- FineVision,20000,mmstar_average,0.33806766134497995,
239
- FineVision,20000,ocrbench_ocrbench_accuracy,0.555,
240
- FineVision,20000,seedbench_seed_all,0.5587548638132296,
241
- FineVision,20000,textvqa_val_exact_match,0.56852,0.006720151338087659
242
- Cauldron,1000,ai2d_exact_match,0.28886010362694303,0.008157423105367313
243
- Cauldron,1000,average,0.29904301214549334,
244
- Cauldron,1000,average_rank,1.9,
245
- Cauldron,1000,chartqa_relaxed_overall,0.1936,0.007903961351247664
246
- Cauldron,1000,docvqa_val_anls,0.32153744261519257,0.005317068996930092
247
- Cauldron,1000,infovqa_val_anls,0.1431990055083018,0.005424936025458022
248
- Cauldron,1000,mme_total_score,1172.0779311724689,
249
- Cauldron,1000,mmmu_val_mmmu_acc,0.27667,
250
- Cauldron,1000,mmstar_average,0.2911329978035828,
251
- Cauldron,1000,ocrbench_ocrbench_accuracy,0.337,
252
- Cauldron,1000,seedbench_seed_all,0.39360755975541967,
253
- Cauldron,1000,textvqa_val_exact_match,0.44578,0.0067711747933144
254
- Cauldron,2000,ai2d_exact_match,0.41871761658031087,0.008879446246519871
255
- Cauldron,2000,average,0.34894207663644056,
256
- Cauldron,2000,average_rank,1.9,
257
- Cauldron,2000,chartqa_relaxed_overall,0.2056,0.00808440468059435
258
- Cauldron,2000,docvqa_val_anls,0.37496112947656884,0.005489559822643159
259
- Cauldron,2000,infovqa_val_anls,0.14667060624395192,0.005473110880489631
260
- Cauldron,2000,mme_total_score,1248.6002400960383,
261
- Cauldron,2000,mmmu_val_mmmu_acc,0.28667,
262
- Cauldron,2000,mmstar_average,0.34478967650439835,
263
- Cauldron,2000,ocrbench_ocrbench_accuracy,0.368,
264
- Cauldron,2000,seedbench_seed_all,0.5013896609227348,
265
- Cauldron,2000,textvqa_val_exact_match,0.49368,0.0068081481840761415
266
- Cauldron,3000,ai2d_exact_match,0.4653497409326425,0.00897751861457722
267
- Cauldron,3000,average,0.3647655686453986,
268
- Cauldron,3000,average_rank,2.4,
269
- Cauldron,3000,chartqa_relaxed_overall,0.2192,0.008275744025504309
270
- Cauldron,3000,docvqa_val_anls,0.3999560247980121,0.005545460541574292
271
- Cauldron,3000,infovqa_val_anls,0.15452276899525894,0.005625373377223539
272
- Cauldron,3000,mme_total_score,1164.4316726690677,
273
- Cauldron,3000,mmmu_val_mmmu_acc,0.27667,
274
- Cauldron,3000,mmstar_average,0.34444117730168444,
275
- Cauldron,3000,ocrbench_ocrbench_accuracy,0.403,
276
- Cauldron,3000,seedbench_seed_all,0.5147304057809894,
277
- Cauldron,3000,textvqa_val_exact_match,0.50502,0.006802809387533405
278
- Cauldron,4000,ai2d_exact_match,0.48121761658031087,0.008992802471886854
279
- Cauldron,4000,average,0.3694904966669109,
280
- Cauldron,4000,average_rank,2.3,
281
- Cauldron,4000,chartqa_relaxed_overall,0.2184,0.008264859294607735
282
- Cauldron,4000,docvqa_val_anls,0.40927640030259055,0.005557758057811595
283
- Cauldron,4000,infovqa_val_anls,0.15259984907145144,0.005629341537638722
284
- Cauldron,4000,mme_total_score,1238.5236094437776,
285
- Cauldron,4000,mmmu_val_mmmu_acc,0.26667,
286
- Cauldron,4000,mmstar_average,0.36056167686607765,
287
- Cauldron,4000,ocrbench_ocrbench_accuracy,0.414,
288
- Cauldron,4000,seedbench_seed_all,0.5240689271817677,
289
- Cauldron,4000,textvqa_val_exact_match,0.49862,0.006804563140709856
290
- Cauldron,5000,ai2d_exact_match,0.48607512953367876,0.008995663534025174
291
- Cauldron,5000,average,0.3715613183242104,
292
- Cauldron,5000,average_rank,2.3,
293
- Cauldron,5000,chartqa_relaxed_overall,0.2236,0.008334806752495259
294
- Cauldron,5000,docvqa_val_anls,0.42332206291362884,0.005573327842684563
295
- Cauldron,5000,infovqa_val_anls,0.15868297927477548,0.005670852175948406
296
- Cauldron,5000,mme_total_score,1159.8522408963586,
297
- Cauldron,5000,mmmu_val_mmmu_acc,0.26889,
298
- Cauldron,5000,mmstar_average,0.360337335219157,
299
- Cauldron,5000,ocrbench_ocrbench_accuracy,0.401,
300
- Cauldron,5000,seedbench_seed_all,0.5198443579766537,
301
- Cauldron,5000,textvqa_val_exact_match,0.5023,0.0068036313744923
302
- Cauldron,6000,ai2d_exact_match,0.5025906735751295,0.008999033321198393
303
- Cauldron,6000,average,0.3678206000506273,
304
- Cauldron,6000,average_rank,2.2,
305
- Cauldron,6000,chartqa_relaxed_overall,0.2228,0.008324168469720259
306
- Cauldron,6000,docvqa_val_anls,0.4147154618557465,0.005557478918091434
307
- Cauldron,6000,infovqa_val_anls,0.14825798330117057,0.005517775162348899
308
- Cauldron,6000,mme_total_score,1182.059923969588,
309
- Cauldron,6000,mmmu_val_mmmu_acc,0.27111,
310
- Cauldron,6000,mmstar_average,0.3484854117958612,
311
- Cauldron,6000,ocrbench_ocrbench_accuracy,0.391,
312
- Cauldron,6000,seedbench_seed_all,0.5185658699277377,
313
- Cauldron,6000,textvqa_val_exact_match,0.49285999999999996,0.0068052528515312825
314
- Cauldron,7000,ai2d_exact_match,0.49838082901554404,0.008999106932714641
315
- Cauldron,7000,average,0.3749288136256422,
316
- Cauldron,7000,average_rank,2.0,
317
- Cauldron,7000,chartqa_relaxed_overall,0.2276,0.00838733777631434
318
- Cauldron,7000,docvqa_val_anls,0.42525461500166023,0.005595478547875609
319
- Cauldron,7000,infovqa_val_anls,0.14305767989732765,0.005444282186253047
320
- Cauldron,7000,mme_total_score,1262.065426170468,
321
- Cauldron,7000,mmmu_val_mmmu_acc,0.29333,
322
- Cauldron,7000,mmstar_average,0.35012603751558075,
323
- Cauldron,7000,ocrbench_ocrbench_accuracy,0.403,
324
- Cauldron,7000,seedbench_seed_all,0.5222901612006671,
325
- Cauldron,7000,textvqa_val_exact_match,0.51132,0.00682164778449453
326
- Cauldron,8000,ai2d_exact_match,0.49028497409326427,0.008997455247470544
327
- Cauldron,8000,average,0.3674367285685282,
328
- Cauldron,8000,average_rank,2.8,
329
- Cauldron,8000,chartqa_relaxed_overall,0.2256,0.008361209238380008
330
- Cauldron,8000,docvqa_val_anls,0.40937518311359955,0.005568234588180622
331
- Cauldron,8000,infovqa_val_anls,0.14953110986986237,0.005518589617885333
332
- Cauldron,8000,mme_total_score,1210.7711084433772,
333
- Cauldron,8000,mmmu_val_mmmu_acc,0.28889,
334
- Cauldron,8000,mmstar_average,0.32742675529850473,
335
- Cauldron,8000,ocrbench_ocrbench_accuracy,0.406,
336
- Cauldron,8000,seedbench_seed_all,0.512562534741523,
337
- Cauldron,8000,textvqa_val_exact_match,0.49726000000000004,0.006823680165585169
338
- Cauldron,9000,ai2d_exact_match,0.49287564766839376,0.008998240543632314
339
- Cauldron,9000,average,0.3635862393983371,
340
- Cauldron,9000,average_rank,3.0,
341
- Cauldron,9000,chartqa_relaxed_overall,0.2264,0.008371693383064148
342
- Cauldron,9000,docvqa_val_anls,0.4019142603693516,0.005557969721056488
343
- Cauldron,9000,infovqa_val_anls,0.15576345355793061,0.005631711679425604
344
- Cauldron,9000,mme_total_score,1161.06112444978,
345
- Cauldron,9000,mmmu_val_mmmu_acc,0.27,
346
- Cauldron,9000,mmstar_average,0.33510800699714055,
347
- Cauldron,9000,ocrbench_ocrbench_accuracy,0.401,
348
- Cauldron,9000,seedbench_seed_all,0.5066147859922179,
349
- Cauldron,9000,textvqa_val_exact_match,0.4825999999999999,0.006824717089570126
350
- Cauldron,10000,ai2d_exact_match,0.4951424870466321,0.008998729431386465
351
- Cauldron,10000,average,0.3613896970671388,
352
- Cauldron,10000,average_rank,3.2,
353
- Cauldron,10000,chartqa_relaxed_overall,0.2276,0.00838733777631434
354
- Cauldron,10000,docvqa_val_anls,0.400968382089468,0.005551850287661274
355
- Cauldron,10000,infovqa_val_anls,0.15155496077062244,0.0055346119867504375
356
- Cauldron,10000,mme_total_score,1230.2276910764306,
357
- Cauldron,10000,mmmu_val_mmmu_acc,0.26,
358
- Cauldron,10000,mmstar_average,0.32908517910608676,
359
- Cauldron,10000,ocrbench_ocrbench_accuracy,0.395,
360
- Cauldron,10000,seedbench_seed_all,0.4972762645914397,
361
- Cauldron,10000,textvqa_val_exact_match,0.49588000000000004,0.006836984276038533
362
- Cauldron,11000,ai2d_exact_match,0.49676165803108807,0.008998965371572357
363
- Cauldron,11000,average,0.36198497174992383,
364
- Cauldron,11000,average_rank,3.0,
365
- Cauldron,11000,chartqa_relaxed_overall,0.2284,0.008397713059747491
366
- Cauldron,11000,docvqa_val_anls,0.4051111426655002,0.0055740680205303966
367
- Cauldron,11000,infovqa_val_anls,0.14954437197310022,0.005537262124650125
368
- Cauldron,11000,mme_total_score,1210.5605242096838,
369
- Cauldron,11000,mmmu_val_mmmu_acc,0.27111,
370
- Cauldron,11000,mmstar_average,0.33316183100069335,
371
- Cauldron,11000,ocrbench_ocrbench_accuracy,0.383,
372
- Cauldron,11000,seedbench_seed_all,0.5043357420789327,
373
- Cauldron,11000,textvqa_val_exact_match,0.48644,0.006834542228525236
374
- Cauldron,12000,ai2d_exact_match,0.5009715025906736,0.008999137132137068
375
- Cauldron,12000,average,0.3661893496614986,
376
- Cauldron,12000,average_rank,3.2,
377
- Cauldron,12000,chartqa_relaxed_overall,0.2332,0.008459061785476934
378
- Cauldron,12000,docvqa_val_anls,0.40826612382074784,0.0055749766883040515
379
- Cauldron,12000,infovqa_val_anls,0.1451043668322714,0.0054346014264420334
380
- Cauldron,12000,mme_total_score,1204.859843937575,
381
- Cauldron,12000,mmmu_val_mmmu_acc,0.29222,
382
- Cauldron,12000,mmstar_average,0.3322773065724958,
383
- Cauldron,12000,ocrbench_ocrbench_accuracy,0.386,
384
- Cauldron,12000,seedbench_seed_all,0.5047248471372985,
385
- Cauldron,12000,textvqa_val_exact_match,0.49294000000000004,0.006824466715369768
386
- Cauldron,13000,ai2d_exact_match,0.4880181347150259,0.00899656981935399
387
- Cauldron,13000,average,0.3609903418270159,
388
- Cauldron,13000,average_rank,3.2,
389
- Cauldron,13000,chartqa_relaxed_overall,0.23,0.008418334000200726
390
- Cauldron,13000,docvqa_val_anls,0.39428463826041577,0.005550710740937849
391
- Cauldron,13000,infovqa_val_anls,0.15077272156398794,0.005555043265840396
392
- Cauldron,13000,mme_total_score,1199.0380152060825,
393
- Cauldron,13000,mmmu_val_mmmu_acc,0.27667,
394
- Cauldron,13000,mmstar_average,0.3323119954668039,
395
- Cauldron,13000,ocrbench_ocrbench_accuracy,0.39,
396
- Cauldron,13000,seedbench_seed_all,0.5000555864369094,
397
- Cauldron,13000,textvqa_val_exact_match,0.4868,0.006822203492428118
398
- Cauldron,14000,ai2d_exact_match,0.49060880829015546,0.00899756662777987
399
- Cauldron,14000,average,0.36202481121184005,
400
- Cauldron,14000,average_rank,2.9,
401
- Cauldron,14000,chartqa_relaxed_overall,0.2264,0.008371693383064148
402
- Cauldron,14000,docvqa_val_anls,0.40917044569115923,0.0055666808292464285
403
- Cauldron,14000,infovqa_val_anls,0.1424839907142797,0.0054301311838352165
404
- Cauldron,14000,mme_total_score,1183.6356542617045,
405
- Cauldron,14000,mmmu_val_mmmu_acc,0.29,
406
- Cauldron,14000,mmstar_average,0.31528335804531843,
407
- Cauldron,14000,ocrbench_ocrbench_accuracy,0.393,
408
- Cauldron,14000,seedbench_seed_all,0.5020566981656476,
409
- Cauldron,14000,textvqa_val_exact_match,0.48922,0.006837726904596613
410
- Cauldron,15000,ai2d_exact_match,0.4896373056994819,0.008997221155546275
411
- Cauldron,15000,average,0.3560155869130515,
412
- Cauldron,15000,average_rank,3.2,
413
- Cauldron,15000,chartqa_relaxed_overall,0.2264,0.008371693383064148
414
- Cauldron,15000,docvqa_val_anls,0.39997251595677663,0.0055655493795707745
415
- Cauldron,15000,infovqa_val_anls,0.13834600428667498,0.005423970029609658
416
- Cauldron,15000,mme_total_score,1171.8512404961984,
417
- Cauldron,15000,mmmu_val_mmmu_acc,0.27667,
418
- Cauldron,15000,mmstar_average,0.31369390041016126,
419
- Cauldron,15000,ocrbench_ocrbench_accuracy,0.385,
420
- Cauldron,15000,seedbench_seed_all,0.5010005558643691,
421
- Cauldron,15000,textvqa_val_exact_match,0.47342,0.006818885551175648
422
- Cauldron,16000,ai2d_exact_match,0.4838082901554404,0.008994434238637765
423
- Cauldron,16000,average,0.3566345947908368,
424
- Cauldron,16000,average_rank,3.4,
425
- Cauldron,16000,chartqa_relaxed_overall,0.22,0.008286583553358689
426
- Cauldron,16000,docvqa_val_anls,0.40446794741098796,0.005565712054024941
427
- Cauldron,16000,infovqa_val_anls,0.1414810779340465,0.005414255001486301
428
- Cauldron,16000,mme_total_score,1163.921468587435,
429
- Cauldron,16000,mmmu_val_mmmu_acc,0.26444,
430
- Cauldron,16000,mmstar_average,0.3211159497904861,
431
- Cauldron,16000,ocrbench_ocrbench_accuracy,0.392,
432
- Cauldron,16000,seedbench_seed_all,0.5045580878265703,
433
- Cauldron,16000,textvqa_val_exact_match,0.47784,0.0068411071493878735
434
- Cauldron,17000,ai2d_exact_match,0.4795984455958549,0.008991659681159872
435
- Cauldron,17000,average,0.35664663136828295,
436
- Cauldron,17000,average_rank,3.3,
437
- Cauldron,17000,chartqa_relaxed_overall,0.2232,0.008329493152795851
438
- Cauldron,17000,docvqa_val_anls,0.39683521379075226,0.0055483771434975925
439
- Cauldron,17000,infovqa_val_anls,0.14519383287788715,0.005493162839439223
440
- Cauldron,17000,mme_total_score,1216.2439975990396,
441
- Cauldron,17000,mmmu_val_mmmu_acc,0.27667,
442
- Cauldron,17000,mmstar_average,0.3294722845469949,
443
- Cauldron,17000,ocrbench_ocrbench_accuracy,0.386,
444
- Cauldron,17000,seedbench_seed_all,0.4938299055030573,
445
- Cauldron,17000,textvqa_val_exact_match,0.47902,0.006822615153700749
446
- Cauldron,18000,ai2d_exact_match,0.48575129533678757,0.008995499260034972
447
- Cauldron,18000,average,0.3559572601168983,
448
- Cauldron,18000,average_rank,3.3,
449
- Cauldron,18000,chartqa_relaxed_overall,0.22,0.008286583553358689
450
- Cauldron,18000,docvqa_val_anls,0.39553075414155453,0.005560094600545488
451
- Cauldron,18000,infovqa_val_anls,0.1441200977793978,0.005482620397489444
452
- Cauldron,18000,mme_total_score,1146.935774309724,
453
- Cauldron,18000,mmmu_val_mmmu_acc,0.28333,
454
- Cauldron,18000,mmstar_average,0.31718334943636844,
455
- Cauldron,18000,ocrbench_ocrbench_accuracy,0.393,
456
- Cauldron,18000,seedbench_seed_all,0.49571984435797667,
457
- Cauldron,18000,textvqa_val_exact_match,0.46897999999999995,0.006834829544251984
458
- Cauldron,19000,ai2d_exact_match,0.47506476683937826,0.00898795641911507
459
- Cauldron,19000,average,0.35389113555756785,
460
- Cauldron,19000,average_rank,3.4,
461
- Cauldron,19000,chartqa_relaxed_overall,0.2196,0.008281169428700436
462
- Cauldron,19000,docvqa_val_anls,0.3927677091095705,0.005557918115613283
463
- Cauldron,19000,infovqa_val_anls,0.14242963523056748,0.005420426599891758
464
- Cauldron,19000,mme_total_score,1156.7713085234095,
465
- Cauldron,19000,mmmu_val_mmmu_acc,0.26667,
466
- Cauldron,19000,mmstar_average,0.3300183589775604,
467
- Cauldron,19000,ocrbench_ocrbench_accuracy,0.393,
468
- Cauldron,19000,seedbench_seed_all,0.4895497498610339,
469
- Cauldron,19000,textvqa_val_exact_match,0.47591999999999995,0.0068329619195279245
470
- Cauldron,20000,ai2d_exact_match,0.48218911917098445,0.008993442748995703
471
- Cauldron,20000,average,0.35315414152261965,
472
- Cauldron,20000,average_rank,3.1,
473
- Cauldron,20000,chartqa_relaxed_overall,0.2228,0.008324168469720259
474
- Cauldron,20000,docvqa_val_anls,0.3995019956467228,0.005554102577571356
475
- Cauldron,20000,infovqa_val_anls,0.13561089161386572,0.005312619238987202
476
- Cauldron,20000,mme_total_score,1205.715886354542,
477
- Cauldron,20000,mmmu_val_mmmu_acc,0.27667,
478
- Cauldron,20000,mmstar_average,0.3019064734976851,
479
- Cauldron,20000,ocrbench_ocrbench_accuracy,0.392,
480
- Cauldron,20000,seedbench_seed_all,0.49182879377431904,
481
- Cauldron,20000,textvqa_val_exact_match,0.4758799999999999,0.0068345144112400185
482
- Cambrian,1000,ai2d_exact_match,0.2969559585492228,0.00822373246069825
483
- Cambrian,1000,average,0.2927820669039429,
484
- Cambrian,1000,average_rank,2.3,
485
- Cambrian,1000,chartqa_relaxed_overall,0.3652,0.009631650506356148
486
- Cambrian,1000,docvqa_val_anls,0.3321611875422322,0.005779917542014128
487
- Cambrian,1000,infovqa_val_anls,0.14245417507906105,0.005737797137238206
488
- Cambrian,1000,mme_total_score,1199.468087234894,
489
- Cambrian,1000,mmmu_val_mmmu_acc,0.24556,
490
- Cambrian,1000,mmstar_average,0.25503356223234036,
491
- Cambrian,1000,ocrbench_ocrbench_accuracy,0.257,
492
- Cambrian,1000,seedbench_seed_all,0.3486937187326292,
493
- Cambrian,1000,textvqa_val_exact_match,0.39198,0.0066503820519040295
494
- Cambrian,2000,ai2d_exact_match,0.36204663212435234,0.008649846657326264
495
- Cambrian,2000,average,0.34977426052091565,
496
- Cambrian,2000,average_rank,2.3,
497
- Cambrian,2000,chartqa_relaxed_overall,0.4272,0.009895414680177737
498
- Cambrian,2000,docvqa_val_anls,0.4044005302893221,0.006099745172446295
499
- Cambrian,2000,infovqa_val_anls,0.16067123444748188,0.005906486800204124
500
- Cambrian,2000,mme_total_score,1191.6502601040415,
501
- Cambrian,2000,mmmu_val_mmmu_acc,0.27,
502
- Cambrian,2000,mmstar_average,0.3140124492167455,
503
- Cambrian,2000,ocrbench_ocrbench_accuracy,0.293,
504
- Cambrian,2000,seedbench_seed_all,0.4954974986103391,
505
- Cambrian,2000,textvqa_val_exact_match,0.42113999999999996,0.006720777771268006
506
- Cambrian,3000,ai2d_exact_match,0.3954015544041451,0.008800034697838395
507
- Cambrian,3000,average,0.36894910100121225,
508
- Cambrian,3000,average_rank,1.9,
509
- Cambrian,3000,chartqa_relaxed_overall,0.4512,0.00995424828018316
510
- Cambrian,3000,docvqa_val_anls,0.4317442116227413,0.006203480507897517
511
- Cambrian,3000,infovqa_val_anls,0.17555075927653038,0.006227695613801885
512
- Cambrian,3000,mme_total_score,1311.187975190076,
513
- Cambrian,3000,mmmu_val_mmmu_acc,0.28222,
514
- Cambrian,3000,mmstar_average,0.3241666733128301,
515
- Cambrian,3000,ocrbench_ocrbench_accuracy,0.289,
516
- Cambrian,3000,seedbench_seed_all,0.5216787103946637,
517
- Cambrian,3000,textvqa_val_exact_match,0.4495799999999999,0.006762330259763156
518
- Cambrian,4000,ai2d_exact_match,0.3960492227979275,0.00880252039912977
519
- Cambrian,4000,average,0.38270567946732525,
520
- Cambrian,4000,average_rank,2.2,
521
- Cambrian,4000,chartqa_relaxed_overall,0.4764,0.009990852959439592
522
- Cambrian,4000,docvqa_val_anls,0.46350742276594625,0.006276498296530657
523
- Cambrian,4000,infovqa_val_anls,0.17819320935276328,0.006230849386066924
524
- Cambrian,4000,mme_total_score,1239.0667266906762,
525
- Cambrian,4000,mmmu_val_mmmu_acc,0.26778,
526
- Cambrian,4000,mmstar_average,0.3298927333298682,
527
- Cambrian,4000,ocrbench_ocrbench_accuracy,0.334,
528
- Cambrian,4000,seedbench_seed_all,0.5273485269594219,
529
- Cambrian,4000,textvqa_val_exact_match,0.47118000000000004,0.0067854764061200295
530
- Cambrian,5000,ai2d_exact_match,0.40382124352331605,0.00883109414387431
531
- Cambrian,5000,average,0.3896927239658996,
532
- Cambrian,5000,average_rank,2.2,
533
- Cambrian,5000,chartqa_relaxed_overall,0.4912,0.01000045137036546
534
- Cambrian,5000,docvqa_val_anls,0.47067674424138894,0.006257580396259991
535
- Cambrian,5000,infovqa_val_anls,0.19432385292037085,0.00653326869729313
536
- Cambrian,5000,mme_total_score,1214.843337334934,
537
- Cambrian,5000,mmmu_val_mmmu_acc,0.26556,
538
- Cambrian,5000,mmstar_average,0.3255942091936794,
539
- Cambrian,5000,ocrbench_ocrbench_accuracy,0.348,
540
- Cambrian,5000,seedbench_seed_all,0.5292384658143413,
541
- Cambrian,5000,textvqa_val_exact_match,0.47881999999999997,0.0067962283116337965
542
- Cambrian,6000,ai2d_exact_match,0.4183937823834197,0.00887848400426025
543
- Cambrian,6000,average,0.39990121640985093,
544
- Cambrian,6000,average_rank,2.4,
545
- Cambrian,6000,chartqa_relaxed_overall,0.5048,0.010001539697392967
546
- Cambrian,6000,docvqa_val_anls,0.5016482570925722,0.006248476976439708
547
- Cambrian,6000,infovqa_val_anls,0.19206925076752404,0.006399951499514914
548
- Cambrian,6000,mme_total_score,1176.5368147258905,
549
- Cambrian,6000,mmmu_val_mmmu_acc,0.26667,
550
- Cambrian,6000,mmstar_average,0.33910121942401966,
551
- Cambrian,6000,ocrbench_ocrbench_accuracy,0.349,
552
- Cambrian,6000,seedbench_seed_all,0.5391884380211228,
553
- Cambrian,6000,textvqa_val_exact_match,0.48823999999999995,0.006792935247288521
554
- Cambrian,7000,ai2d_exact_match,0.4326424870466321,0.008917121282993509
555
- Cambrian,7000,average,0.40874111160527243,
556
- Cambrian,7000,average_rank,2.2,
557
- Cambrian,7000,chartqa_relaxed_overall,0.5088,0.01000045137036546
558
- Cambrian,7000,docvqa_val_anls,0.5036441729071615,0.006331057466984081
559
- Cambrian,7000,infovqa_val_anls,0.21047690542452482,0.0067248622097179815
560
- Cambrian,7000,mme_total_score,1226.7814125650261,
561
- Cambrian,7000,mmmu_val_mmmu_acc,0.29,
562
- Cambrian,7000,mmstar_average,0.338458434622219,
563
- Cambrian,7000,ocrbench_ocrbench_accuracy,0.366,
564
- Cambrian,7000,seedbench_seed_all,0.5344080044469149,
565
- Cambrian,7000,textvqa_val_exact_match,0.49423999999999996,0.006789004536492761
566
- Cambrian,8000,ai2d_exact_match,0.4375,0.008928571428571428
567
- Cambrian,8000,average,0.4145399236017655,
568
- Cambrian,8000,average_rank,2.2,
569
- Cambrian,8000,chartqa_relaxed_overall,0.5312,0.009982508912777261
570
- Cambrian,8000,docvqa_val_anls,0.5139425879433994,0.006316907313170543
571
- Cambrian,8000,infovqa_val_anls,0.20402472511542052,0.00665285157736885
572
- Cambrian,8000,mme_total_score,1243.7800120048018,
573
- Cambrian,8000,mmmu_val_mmmu_acc,0.28222,
574
- Cambrian,8000,mmstar_average,0.3300028831814166,
575
- Cambrian,8000,ocrbench_ocrbench_accuracy,0.397,
576
- Cambrian,8000,seedbench_seed_all,0.5364091161756531,
577
- Cambrian,8000,textvqa_val_exact_match,0.49855999999999995,0.006793174127235705
578
- Cambrian,9000,ai2d_exact_match,0.4251943005181347,0.008897867521411106
579
- Cambrian,9000,average,0.41587431550154147,
580
- Cambrian,9000,average_rank,2.0,
581
- Cambrian,9000,chartqa_relaxed_overall,0.5316,0.009982005418395102
582
- Cambrian,9000,docvqa_val_anls,0.524278096798472,0.006327817979288962
583
- Cambrian,9000,infovqa_val_anls,0.2075069347958689,0.006574086714467312
584
- Cambrian,9000,mme_total_score,1196.0997398959585,
585
- Cambrian,9000,mmmu_val_mmmu_acc,0.28556,
586
- Cambrian,9000,mmstar_average,0.33833745626187595,
587
- Cambrian,9000,ocrbench_ocrbench_accuracy,0.381,
588
- Cambrian,9000,seedbench_seed_all,0.5456920511395219,
589
- Cambrian,9000,textvqa_val_exact_match,0.5036999999999999,0.006790970877355565
590
- Cambrian,10000,ai2d_exact_match,0.44559585492227977,0.008945723914357835
591
- Cambrian,10000,average,0.41659534392300923,
592
- Cambrian,10000,average_rank,2.0,
593
- Cambrian,10000,chartqa_relaxed_overall,0.5416,0.00996732235888869
594
- Cambrian,10000,docvqa_val_anls,0.5215772912722147,0.006314944464077694
595
- Cambrian,10000,infovqa_val_anls,0.18925972424188112,0.006302599390246784
596
- Cambrian,10000,mme_total_score,1241.6579631852742,
597
- Cambrian,10000,mmmu_val_mmmu_acc,0.27889,
598
- Cambrian,10000,mmstar_average,0.34495128935097424,
599
- Cambrian,10000,ocrbench_ocrbench_accuracy,0.373,
600
- Cambrian,10000,seedbench_seed_all,0.5510839355197332,
601
- Cambrian,10000,textvqa_val_exact_match,0.5034000000000001,0.0067932111363852585
602
- Cambrian,11000,ai2d_exact_match,0.4481865284974093,0.008950704796242765
603
- Cambrian,11000,average,0.42096531591252645,
604
- Cambrian,11000,average_rank,2.0,
605
- Cambrian,11000,chartqa_relaxed_overall,0.5388,0.0099718403035556
606
- Cambrian,11000,docvqa_val_anls,0.5266496382012209,0.006315639724937912
607
- Cambrian,11000,infovqa_val_anls,0.210453542763111,0.006757501751011823
608
- Cambrian,11000,mme_total_score,1288.1182472989194,
609
- Cambrian,11000,mmmu_val_mmmu_acc,0.28556,
610
- Cambrian,11000,mmstar_average,0.33813173019346515,
611
- Cambrian,11000,ocrbench_ocrbench_accuracy,0.372,
612
- Cambrian,11000,seedbench_seed_all,0.547526403557532,
613
- Cambrian,11000,textvqa_val_exact_match,0.5213800000000001,0.00677771101429669
614
- Cambrian,12000,ai2d_exact_match,0.4566062176165803,0.008965198879336198
615
- Cambrian,12000,average,0.42647137409223257,
616
- Cambrian,12000,average_rank,2.1,
617
- Cambrian,12000,chartqa_relaxed_overall,0.5488,0.00995424828018316
618
- Cambrian,12000,docvqa_val_anls,0.5432685128640529,0.006286968775744768
619
- Cambrian,12000,infovqa_val_anls,0.214068867667478,0.006728697021311144
620
- Cambrian,12000,mme_total_score,1272.0885354141656,
621
- Cambrian,12000,mmmu_val_mmmu_acc,0.27556,
622
- Cambrian,12000,mmstar_average,0.3364706975313428,
623
- Cambrian,12000,ocrbench_ocrbench_accuracy,0.396,
624
- Cambrian,12000,seedbench_seed_all,0.5505280711506393,
625
- Cambrian,12000,textvqa_val_exact_match,0.51694,0.00676817323313926
626
- Cambrian,13000,ai2d_exact_match,0.44591968911917096,0.008946359966425538
627
- Cambrian,13000,average,0.42595033048849396,
628
- Cambrian,13000,average_rank,2.1,
629
- Cambrian,13000,chartqa_relaxed_overall,0.5484,0.009955029736109216
630
- Cambrian,13000,docvqa_val_anls,0.5438384263330651,0.006322105329987294
631
- Cambrian,13000,infovqa_val_anls,0.2206834922799479,0.006931006985711701
632
- Cambrian,13000,mme_total_score,1294.3567426970787,
633
- Cambrian,13000,mmmu_val_mmmu_acc,0.27889,
634
- Cambrian,13000,mmstar_average,0.3258043460972802,
635
- Cambrian,13000,ocrbench_ocrbench_accuracy,0.404,
636
- Cambrian,13000,seedbench_seed_all,0.5466370205669816,
637
- Cambrian,13000,textvqa_val_exact_match,0.5193800000000001,0.006779976160381913
638
- Cambrian,14000,ai2d_exact_match,0.452720207253886,0.00895883074213608
639
- Cambrian,14000,average,0.4290628718702856,
640
- Cambrian,14000,average_rank,2.2,
641
- Cambrian,14000,chartqa_relaxed_overall,0.5624,0.009923804147377265
642
- Cambrian,14000,docvqa_val_anls,0.5501582985035621,0.006289139790552158
643
- Cambrian,14000,infovqa_val_anls,0.2108586833777777,0.006694603397438603
644
- Cambrian,14000,mme_total_score,1258.3851540616247,
645
- Cambrian,14000,mmmu_val_mmmu_acc,0.28444,
646
- Cambrian,14000,mmstar_average,0.3392338272359765,
647
- Cambrian,14000,ocrbench_ocrbench_accuracy,0.391,
648
- Cambrian,14000,seedbench_seed_all,0.5506948304613675,
649
- Cambrian,14000,textvqa_val_exact_match,0.5200600000000001,0.006762031077483937
650
- Cambrian,15000,ai2d_exact_match,0.4575777202072539,0.008966704964444827
651
- Cambrian,15000,average,0.4277300448618869,
652
- Cambrian,15000,average_rank,2.2,
653
- Cambrian,15000,chartqa_relaxed_overall,0.5572,0.009936335154498413
654
- Cambrian,15000,docvqa_val_anls,0.550106577844955,0.006305789516584643
655
- Cambrian,15000,infovqa_val_anls,0.2065365477570411,0.006585265308234506
656
- Cambrian,15000,mme_total_score,1191.499399759904,
657
- Cambrian,15000,mmmu_val_mmmu_acc,0.27667,
658
- Cambrian,15000,mmstar_average,0.3287834934674655,
659
- Cambrian,15000,ocrbench_ocrbench_accuracy,0.403,
660
- Cambrian,15000,seedbench_seed_all,0.5489160644802669,
661
- Cambrian,15000,textvqa_val_exact_match,0.52078,0.006761241098810132
662
- Cambrian,16000,ai2d_exact_match,0.45174870466321243,0.008957152666985158
663
- Cambrian,16000,average,0.4283932783055524,
664
- Cambrian,16000,average_rank,2.0,
665
- Cambrian,16000,chartqa_relaxed_overall,0.566,0.00991448025705367
666
- Cambrian,16000,docvqa_val_anls,0.5507111549470696,0.006298722691255348
667
- Cambrian,16000,infovqa_val_anls,0.21185403234992514,0.0065982885956266755
668
- Cambrian,16000,mme_total_score,1242.7407963185274,
669
- Cambrian,16000,mmmu_val_mmmu_acc,0.28111,
670
- Cambrian,16000,mmstar_average,0.32560559611383355,
671
- Cambrian,16000,ocrbench_ocrbench_accuracy,0.394,
672
- Cambrian,16000,seedbench_seed_all,0.5540300166759311,
673
- Cambrian,16000,textvqa_val_exact_match,0.5204799999999999,0.006783488561456611
674
- Cambrian,17000,ai2d_exact_match,0.4585492227979275,0.008968176705111413
675
- Cambrian,17000,average,0.43044446070382536,
676
- Cambrian,17000,average_rank,2.4,
677
- Cambrian,17000,chartqa_relaxed_overall,0.5656,0.009915542506251351
678
- Cambrian,17000,docvqa_val_anls,0.5528747665552118,0.006300095973166064
679
- Cambrian,17000,infovqa_val_anls,0.20960594545383252,0.0066643358201217045
680
- Cambrian,17000,mme_total_score,1292.4750900360143,
681
- Cambrian,17000,mmmu_val_mmmu_acc,0.27111,
682
- Cambrian,17000,mmstar_average,0.3297184661133375,
683
- Cambrian,17000,ocrbench_ocrbench_accuracy,0.409,
684
- Cambrian,17000,seedbench_seed_all,0.555141745414119,
685
- Cambrian,17000,textvqa_val_exact_match,0.5224,0.006774129151791618
686
- Cambrian,18000,ai2d_exact_match,0.4523963730569948,0.008958275210820045
687
- Cambrian,18000,average,0.43086034100304976,
688
- Cambrian,18000,average_rank,2.4,
689
- Cambrian,18000,chartqa_relaxed_overall,0.566,0.00991448025705367
690
- Cambrian,18000,docvqa_val_anls,0.5527950768923724,0.006311862091164367
691
- Cambrian,18000,infovqa_val_anls,0.21943552260393814,0.006848865968629337
692
- Cambrian,18000,mme_total_score,1271.4629851940776,
693
- Cambrian,18000,mmmu_val_mmmu_acc,0.28333,
694
- Cambrian,18000,mmstar_average,0.3399009269355101,
695
- Cambrian,18000,ocrbench_ocrbench_accuracy,0.403,
696
- Cambrian,18000,seedbench_seed_all,0.5493051695386326,
697
- Cambrian,18000,textvqa_val_exact_match,0.5115799999999999,0.0067870754820260944
698
- Cambrian,19000,ai2d_exact_match,0.45012953367875647,0.008954279299902583
699
- Cambrian,19000,average,0.43057935657557483,
700
- Cambrian,19000,average_rank,2.2,
701
- Cambrian,19000,chartqa_relaxed_overall,0.5704,0.009902361269085337
702
- Cambrian,19000,docvqa_val_anls,0.5526262050544066,0.006310038331338026
703
- Cambrian,19000,infovqa_val_anls,0.21937034023427093,0.006858602078113178
704
- Cambrian,19000,mme_total_score,1269.9476790716285,
705
- Cambrian,19000,mmmu_val_mmmu_acc,0.28556,
706
- Cambrian,19000,mmstar_average,0.3314266960826673,
707
- Cambrian,19000,ocrbench_ocrbench_accuracy,0.404,
708
- Cambrian,19000,seedbench_seed_all,0.5465814341300722,
709
- Cambrian,19000,textvqa_val_exact_match,0.51512,0.006773909823053313
710
- Cambrian,20000,ai2d_exact_match,0.45531088082901555,0.008963137311190377
711
- Cambrian,20000,average,0.42817340693945505,
712
- Cambrian,20000,average_rank,2.4,
713
- Cambrian,20000,chartqa_relaxed_overall,0.5684,0.009907968668564455
714
- Cambrian,20000,docvqa_val_anls,0.549188563518089,0.006325944032596611
715
- Cambrian,20000,infovqa_val_anls,0.21755406764942647,0.0068363256354831885
716
- Cambrian,20000,mme_total_score,1290.6296518607442,
717
- Cambrian,20000,mmmu_val_mmmu_acc,0.28444,
718
- Cambrian,20000,mmstar_average,0.32485343172593534,
719
- Cambrian,20000,ocrbench_ocrbench_accuracy,0.392,
720
- Cambrian,20000,seedbench_seed_all,0.5486937187326293,
721
- Cambrian,20000,textvqa_val_exact_match,0.51312,0.006789609184524225
722
- LLaVa,1000,ai2d_exact_match,0.25777202072538863,0.007872600874396432
723
- LLaVa,1000,average,0.2581360512843851,
724
- LLaVa,1000,average_rank,3.0,
725
- LLaVa,1000,chartqa_relaxed_overall,0.1576,0.007288768514542319
726
- LLaVa,1000,docvqa_val_anls,0.2850280465017524,0.005237571860745478
727
- LLaVa,1000,infovqa_val_anls,0.15291302898150733,0.005597827181699182
728
- LLaVa,1000,mme_total_score,844.0894357743098,
729
- LLaVa,1000,mmmu_val_mmmu_acc,0.25333,
730
- LLaVa,1000,mmstar_average,0.22969486173769915,
731
- LLaVa,1000,ocrbench_ocrbench_accuracy,0.35,
732
- LLaVa,1000,seedbench_seed_all,0.2717065036131184,
733
- LLaVa,1000,textvqa_val_exact_match,0.36518,0.006561838543046682
734
- LLaVa,2000,ai2d_exact_match,0.24676165803108807,0.007759553547248649
735
- LLaVa,2000,average,0.28023175511348764,
736
- LLaVa,2000,average_rank,3.2,
737
- LLaVa,2000,chartqa_relaxed_overall,0.19,0.007847587772910948
738
- LLaVa,2000,docvqa_val_anls,0.31839133336930814,0.005353711170722305
739
- LLaVa,2000,infovqa_val_anls,0.1625232406439703,0.005680709103352321
740
- LLaVa,2000,mme_total_score,677.0834333733493,
741
- LLaVa,2000,mmmu_val_mmmu_acc,0.25111,
742
- LLaVa,2000,mmstar_average,0.2602226545829147,
743
- LLaVa,2000,ocrbench_ocrbench_accuracy,0.389,
744
- LLaVa,2000,seedbench_seed_all,0.2864369093941078,
745
- LLaVa,2000,textvqa_val_exact_match,0.41764000000000007,0.006695635323587844
746
- LLaVa,3000,ai2d_exact_match,0.31541450777202074,0.00836346730591157
747
- LLaVa,3000,average,0.3241247472461608,
748
- LLaVa,3000,average_rank,3.1,
749
- LLaVa,3000,chartqa_relaxed_overall,0.2048,0.008072722684486087
750
- LLaVa,3000,docvqa_val_anls,0.33927313841893186,0.005424261898744584
751
- LLaVa,3000,infovqa_val_anls,0.17400826017663457,0.005878416771815313
752
- LLaVa,3000,mme_total_score,674.5895358143258,
753
- LLaVa,3000,mmmu_val_mmmu_acc,0.27778,
754
- LLaVa,3000,mmstar_average,0.28839612401739867,
755
- LLaVa,3000,ocrbench_ocrbench_accuracy,0.428,
756
- LLaVa,3000,seedbench_seed_all,0.4512506948304614,
757
- LLaVa,3000,textvqa_val_exact_match,0.4382,0.006743326070219196
758
- LLaVa,4000,ai2d_exact_match,0.30667098445595853,0.008299228398743067
759
- LLaVa,4000,average,0.34151562451124173,
760
- LLaVa,4000,average_rank,2.8,
761
- LLaVa,4000,chartqa_relaxed_overall,0.2168,0.00824295350666284
762
- LLaVa,4000,docvqa_val_anls,0.36894439928615425,0.005583877165382837
763
- LLaVa,4000,infovqa_val_anls,0.1815741433661475,0.005975096001960774
764
- LLaVa,4000,mme_total_score,660.3387354941976,
765
- LLaVa,4000,mmmu_val_mmmu_acc,0.29444,
766
- LLaVa,4000,mmstar_average,0.3089940618086463,
767
- LLaVa,4000,ocrbench_ocrbench_accuracy,0.439,
768
- LLaVa,4000,seedbench_seed_all,0.48265703168426904,
769
- LLaVa,4000,textvqa_val_exact_match,0.4745599999999999,0.006778004835488831
770
- LLaVa,5000,ai2d_exact_match,0.3176813471502591,0.00837955903737489
771
- LLaVa,5000,average,0.3488971740226244,
772
- LLaVa,5000,average_rank,2.9,
773
- LLaVa,5000,chartqa_relaxed_overall,0.2076,0.008113397986710395
774
- LLaVa,5000,docvqa_val_anls,0.37667351380566144,0.005504553709162657
775
- LLaVa,5000,infovqa_val_anls,0.19157302816202296,0.006066754825254386
776
- LLaVa,5000,mme_total_score,596.045218087235,
777
- LLaVa,5000,mmmu_val_mmmu_acc,0.28889,
778
- LLaVa,5000,mmstar_average,0.30911460927022283,
779
- LLaVa,5000,ocrbench_ocrbench_accuracy,0.471,
780
- LLaVa,5000,seedbench_seed_all,0.49972206781545303,
781
- LLaVa,5000,textvqa_val_exact_match,0.47781999999999997,0.00678922884027701
782
- LLaVa,6000,ai2d_exact_match,0.3626943005181347,0.00865318426683941
783
- LLaVa,6000,average,0.35336013036474917,
784
- LLaVa,6000,average_rank,3.3,
785
- LLaVa,6000,chartqa_relaxed_overall,0.2164,0.00823744852629073
786
- LLaVa,6000,docvqa_val_anls,0.3796381971300078,0.005512363416378596
787
- LLaVa,6000,infovqa_val_anls,0.1911083172357537,0.00606756561226675
788
- LLaVa,6000,mme_total_score,751.7179871948779,
789
- LLaVa,6000,mmmu_val_mmmu_acc,0.27111,
790
- LLaVa,6000,mmstar_average,0.3230226430014031,
791
- LLaVa,6000,ocrbench_ocrbench_accuracy,0.471,
792
- LLaVa,6000,seedbench_seed_all,0.49788771539744303,
793
- LLaVa,6000,textvqa_val_exact_match,0.46738,0.006777431212101451
794
- LLaVa,7000,ai2d_exact_match,0.3636658031088083,0.008658158841882565
795
- LLaVa,7000,average,0.36232264653787655,
796
- LLaVa,7000,average_rank,3.4,
797
- LLaVa,7000,chartqa_relaxed_overall,0.2276,0.00838733777631434
798
- LLaVa,7000,docvqa_val_anls,0.38862032747814834,0.005554025202613156
799
- LLaVa,7000,infovqa_val_anls,0.1987523491607365,0.006169459873730798
800
- LLaVa,7000,mme_total_score,700.0341136454582,
801
- LLaVa,7000,mmmu_val_mmmu_acc,0.28,
802
- LLaVa,7000,mmstar_average,0.32238002502982693,
803
- LLaVa,7000,ocrbench_ocrbench_accuracy,0.469,
804
- LLaVa,7000,seedbench_seed_all,0.5175653140633686,
805
- LLaVa,7000,textvqa_val_exact_match,0.49332,0.006784414578741135
806
- LLaVa,8000,ai2d_exact_match,0.38244818652849744,0.008746910624026853
807
- LLaVa,8000,average,0.36916094621046264,
808
- LLaVa,8000,average_rank,2.8,
809
- LLaVa,8000,chartqa_relaxed_overall,0.2276,0.00838733777631434
810
- LLaVa,8000,docvqa_val_anls,0.4000384036155175,0.005647492303754258
811
- LLaVa,8000,infovqa_val_anls,0.20267340215584623,0.006186451136703468
812
- LLaVa,8000,mme_total_score,787.0998399359744,
813
- LLaVa,8000,mmmu_val_mmmu_acc,0.28333,
814
- LLaVa,8000,mmstar_average,0.33877512170436386,
815
- LLaVa,8000,ocrbench_ocrbench_accuracy,0.47,
816
- LLaVa,8000,seedbench_seed_all,0.5221234018899389,
817
- LLaVa,8000,textvqa_val_exact_match,0.49546,0.006796875545678079
818
- LLaVa,9000,ai2d_exact_match,0.3856865284974093,0.008760803506529557
819
- LLaVa,9000,average,0.3660729124456708,
820
- LLaVa,9000,average_rank,3.0,
821
- LLaVa,9000,chartqa_relaxed_overall,0.2212,0.00830275847651416
822
- LLaVa,9000,docvqa_val_anls,0.3961556104365206,0.005555787005997977
823
- LLaVa,9000,infovqa_val_anls,0.20795411138332273,0.006302696156883479
824
- LLaVa,9000,mme_total_score,697.6510604241697,
825
- LLaVa,9000,mmmu_val_mmmu_acc,0.27444,
826
- LLaVa,9000,mmstar_average,0.33019217959261743,
827
- LLaVa,9000,ocrbench_ocrbench_accuracy,0.47,
828
- LLaVa,9000,seedbench_seed_all,0.5140077821011673,
829
- LLaVa,9000,textvqa_val_exact_match,0.49501999999999996,0.006795224421237829
830
- LLaVa,10000,ai2d_exact_match,0.3636658031088083,0.008658158841882561
831
- LLaVa,10000,average,0.36465272894871764,
832
- LLaVa,10000,average_rank,3.1,
833
- LLaVa,10000,chartqa_relaxed_overall,0.2216,0.008308127706914342
834
- LLaVa,10000,docvqa_val_anls,0.3905169927438113,0.005559588309122447
835
- LLaVa,10000,infovqa_val_anls,0.210842797817216,0.0062742161273205005
836
- LLaVa,10000,mme_total_score,710.1757703081232,
837
- LLaVa,10000,mmmu_val_mmmu_acc,0.25667,
838
- LLaVa,10000,mmstar_average,0.33485115141559363,
839
- LLaVa,10000,ocrbench_ocrbench_accuracy,0.484,
840
- LLaVa,10000,seedbench_seed_all,0.5220678154530295,
841
- LLaVa,10000,textvqa_val_exact_match,0.49766000000000005,0.0067820722630208075
842
- LLaVa,11000,ai2d_exact_match,0.3539507772020725,0.008606685322379343
843
- LLaVa,11000,average,0.3619647158138698,
844
- LLaVa,11000,average_rank,3.3,
845
- LLaVa,11000,chartqa_relaxed_overall,0.226,0.008366456779283321
846
- LLaVa,11000,docvqa_val_anls,0.39615321520069524,0.0055548098783566
847
- LLaVa,11000,infovqa_val_anls,0.20231707967850712,0.006189706400735626
848
- LLaVa,11000,mme_total_score,620.8629451780713,
849
- LLaVa,11000,mmmu_val_mmmu_acc,0.26778,
850
- LLaVa,11000,mmstar_average,0.3504522318333254,
851
- LLaVa,11000,ocrbench_ocrbench_accuracy,0.48,
852
- LLaVa,11000,seedbench_seed_all,0.5084491384102279,
853
- LLaVa,11000,textvqa_val_exact_match,0.47257999999999994,0.0067942373414689025
854
- LLaVa,12000,ai2d_exact_match,0.3963730569948187,0.008803757198545707
855
- LLaVa,12000,average,0.36835635606525785,
856
- LLaVa,12000,average_rank,3.1,
857
- LLaVa,12000,chartqa_relaxed_overall,0.234,0.008469137530835504
858
- LLaVa,12000,docvqa_val_anls,0.3998087503562603,0.005606788206948343
859
- LLaVa,12000,infovqa_val_anls,0.19486992137918643,0.006137557366661157
860
- LLaVa,12000,mme_total_score,707.7871148459384,
861
- LLaVa,12000,mmmu_val_mmmu_acc,0.26444,
862
- LLaVa,12000,mmstar_average,0.34510216846405867,
863
- LLaVa,12000,ocrbench_ocrbench_accuracy,0.466,
864
- LLaVa,12000,seedbench_seed_all,0.5159533073929962,
865
- LLaVa,12000,textvqa_val_exact_match,0.49866000000000005,0.006787787245571138
866
- LLaVa,13000,ai2d_exact_match,0.37661917098445596,0.008720866089740391
867
- LLaVa,13000,average,0.3660925061677603,
868
- LLaVa,13000,average_rank,3.2,
869
- LLaVa,13000,chartqa_relaxed_overall,0.23,0.008418334000200726
870
- LLaVa,13000,docvqa_val_anls,0.39678037656395876,0.005562201990102385
871
- LLaVa,13000,infovqa_val_anls,0.20007389352596994,0.006181717086032354
872
- LLaVa,13000,mme_total_score,762.4510804321728,
873
- LLaVa,13000,mmmu_val_mmmu_acc,0.26111,
874
- LLaVa,13000,mmstar_average,0.3487764851969923,
875
- LLaVa,13000,ocrbench_ocrbench_accuracy,0.487,
876
- LLaVa,13000,seedbench_seed_all,0.5187326292384659,
877
- LLaVa,13000,textvqa_val_exact_match,0.47573999999999994,0.006786037174972445
878
- LLaVa,14000,ai2d_exact_match,0.40382124352331605,0.008831094143874325
879
- LLaVa,14000,average,0.3665520961603681,
880
- LLaVa,14000,average_rank,3.5,
881
- LLaVa,14000,chartqa_relaxed_overall,0.224,0.0083401092900026
882
- LLaVa,14000,docvqa_val_anls,0.39653795108545226,0.0055480083540036754
883
- LLaVa,14000,infovqa_val_anls,0.1966338205713239,0.006145830112184984
884
- LLaVa,14000,mme_total_score,648.8810524209684,
885
- LLaVa,14000,mmmu_val_mmmu_acc,0.27222,
886
- LLaVa,14000,mmstar_average,0.3348780070169728,
887
- LLaVa,14000,ocrbench_ocrbench_accuracy,0.482,
888
- LLaVa,14000,seedbench_seed_all,0.5121178432462479,
889
- LLaVa,14000,textvqa_val_exact_match,0.47676,0.006784540255411228
890
- LLaVa,15000,ai2d_exact_match,0.38374352331606215,0.008752516998880439
891
- LLaVa,15000,average,0.3656314014070533,
892
- LLaVa,15000,average_rank,3.3,
893
- LLaVa,15000,chartqa_relaxed_overall,0.222,0.008313485768211027
894
- LLaVa,15000,docvqa_val_anls,0.3956148602850384,0.005571289516040145
895
- LLaVa,15000,infovqa_val_anls,0.2003939669503818,0.006205919365204143
896
- LLaVa,15000,mme_total_score,744.8995598239295,
897
- LLaVa,15000,mmmu_val_mmmu_acc,0.25111,
898
- LLaVa,15000,mmstar_average,0.34431451447442113,
899
- LLaVa,15000,ocrbench_ocrbench_accuracy,0.491,
900
- LLaVa,15000,seedbench_seed_all,0.5223457476375765,
901
- LLaVa,15000,textvqa_val_exact_match,0.48016000000000003,0.006780152577471598
902
- LLaVa,16000,ai2d_exact_match,0.38244818652849744,0.008746910624026851
903
- LLaVa,16000,average,0.3664952284054124,
904
- LLaVa,16000,average_rank,3.1,
905
- LLaVa,16000,chartqa_relaxed_overall,0.2272,0.008382133861209024
906
- LLaVa,16000,docvqa_val_anls,0.3971604594021061,0.005596507964441207
907
- LLaVa,16000,infovqa_val_anls,0.20130541865614268,0.006177273754737603
908
- LLaVa,16000,mme_total_score,741.5084033613446,
909
- LLaVa,16000,mmmu_val_mmmu_acc,0.25444,
910
- LLaVa,16000,mmstar_average,0.34322789378570057,
911
- LLaVa,16000,ocrbench_ocrbench_accuracy,0.488,
912
- LLaVa,16000,seedbench_seed_all,0.5151750972762645,
913
- LLaVa,16000,textvqa_val_exact_match,0.4895,0.0067890182024819105
914
- LLaVa,17000,ai2d_exact_match,0.36852331606217614,0.008682460781863906
915
- LLaVa,17000,average,0.3659850040618015,
916
- LLaVa,17000,average_rank,3.0,
917
- LLaVa,17000,chartqa_relaxed_overall,0.2264,0.008371693383064148
918
- LLaVa,17000,docvqa_val_anls,0.3895535425900796,0.005559420230793686
919
- LLaVa,17000,infovqa_val_anls,0.19870913061640477,0.0061833458200064835
920
- LLaVa,17000,mme_total_score,738.0654261704681,
921
- LLaVa,17000,mmmu_val_mmmu_acc,0.27667,
922
- LLaVa,17000,mmstar_average,0.3488362957589257,
923
- LLaVa,17000,ocrbench_ocrbench_accuracy,0.486,
924
- LLaVa,17000,seedbench_seed_all,0.514952751528627,
925
- LLaVa,17000,textvqa_val_exact_match,0.48422,0.006797929147037179
926
- LLaVa,18000,ai2d_exact_match,0.3785621761658031,0.008729696327646351
927
- LLaVa,18000,average,0.3667559662544118,
928
- LLaVa,18000,average_rank,3.1,
929
- LLaVa,18000,chartqa_relaxed_overall,0.2268,0.008376919070233621
930
- LLaVa,18000,docvqa_val_anls,0.39054490192374947,0.005557124380968682
931
- LLaVa,18000,infovqa_val_anls,0.19983100041999644,0.006171606410532323
932
- LLaVa,18000,mme_total_score,746.5269107643057,
933
- LLaVa,18000,mmmu_val_mmmu_acc,0.27,
934
- LLaVa,18000,mmstar_average,0.3522401814266279,
935
- LLaVa,18000,ocrbench_ocrbench_accuracy,0.497,
936
- LLaVa,18000,seedbench_seed_all,0.5137854363535297,
937
- LLaVa,18000,textvqa_val_exact_match,0.47203999999999996,0.006793178720998519
938
- LLaVa,19000,ai2d_exact_match,0.3707901554404145,0.008693477555877339
939
- LLaVa,19000,average,0.3627892845719615,
940
- LLaVa,19000,average_rank,3.2,
941
- LLaVa,19000,chartqa_relaxed_overall,0.2284,0.008397713059747491
942
- LLaVa,19000,docvqa_val_anls,0.3886627325813464,0.005572189741680524
943
- LLaVa,19000,infovqa_val_anls,0.18766806187395813,0.006047287494792444
944
- LLaVa,19000,mme_total_score,735.0644257703082,
945
- LLaVa,19000,mmmu_val_mmmu_acc,0.27556,
946
- LLaVa,19000,mmstar_average,0.34617955399790473,
947
- LLaVa,19000,ocrbench_ocrbench_accuracy,0.487,
948
- LLaVa,19000,seedbench_seed_all,0.50550305725403,
949
- LLaVa,19000,textvqa_val_exact_match,0.47534,0.00678734045691651
950
- LLaVa,20000,ai2d_exact_match,0.3746761658031088,0.008711886524907501
951
- LLaVa,20000,average,0.3636232406961286,
952
- LLaVa,20000,average_rank,3.3,
953
- LLaVa,20000,chartqa_relaxed_overall,0.2224,0.00831883268198588
954
- LLaVa,20000,docvqa_val_anls,0.3865323770909091,0.005551659686181904
955
- LLaVa,20000,infovqa_val_anls,0.1967140503390298,0.006138459642690392
956
- LLaVa,20000,mme_total_score,688.5517206882753,
957
- LLaVa,20000,mmmu_val_mmmu_acc,0.27556,
958
- LLaVa,20000,mmstar_average,0.3525069399025931,
959
- LLaVa,20000,ocrbench_ocrbench_accuracy,0.494,
960
- LLaVa,20000,seedbench_seed_all,0.5113396331295164,
961
- LLaVa,20000,textvqa_val_exact_match,0.45888,0.006775175991953595
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e6173a1541b9798278da1729f1e357c0711d2e270f68aa4af8eae962f146dd
3
+ size 53573
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/content/assets/data/all_ratings_luis.csv CHANGED
@@ -1,1201 +1,3 @@
1
- run,step,metric,value,stderr
2
- Baseline,1000,ai2d_exact_match,0.2548575129533679,0.007843322436924496
3
- Baseline,1000,average,0.27120689295763617,
4
- Baseline,1000,average_rank,3.0,
5
- Baseline,1000,chartqa_relaxed_overall,0.3308,0.009411906161401973
6
- Baseline,1000,docvqa_val_anls,0.3528553494243383,0.005852289239342309
7
- Baseline,1000,infovqa_val_anls,0.17320578642581314,0.006297063452679795
8
- Baseline,1000,mme_total_score,977.4280712284914,
9
- Baseline,1000,mmmu_val_mmmu_acc,0.25222,
10
- Baseline,1000,mmstar_average,0.23215874078908072,
11
- Baseline,1000,ocrbench_ocrbench_accuracy,0.286,
12
- Baseline,1000,seedbench_seed_all,0.2563646470261256,
13
- Baseline,1000,textvqa_val_exact_match,0.3024,0.00628900296642181
14
- Baseline,2000,ai2d_exact_match,0.26295336787564766,0.007923526907377255
15
- Baseline,2000,average,0.3202068275596269,
16
- Baseline,2000,average_rank,2.8,
17
- Baseline,2000,chartqa_relaxed_overall,0.4688,0.009982508912777261
18
- Baseline,2000,docvqa_val_anls,0.4452261510942785,0.00614755494712251
19
- Baseline,2000,infovqa_val_anls,0.1820547866557169,0.006217861455795791
20
- Baseline,2000,mme_total_score,1049.3036214485794,
21
- Baseline,2000,mmmu_val_mmmu_acc,0.24556,
22
- Baseline,2000,mmstar_average,0.21305462434540698,
23
- Baseline,2000,ocrbench_ocrbench_accuracy,0.395,
24
- Baseline,2000,seedbench_seed_all,0.258532518065592,
25
- Baseline,2000,textvqa_val_exact_match,0.41068000000000005,0.006697862330024289
26
- Baseline,3000,ai2d_exact_match,0.25226683937823835,0.007816909588794397
27
- Baseline,3000,average,0.3507423834414229,
28
- Baseline,3000,average_rank,2.6,
29
- Baseline,3000,chartqa_relaxed_overall,0.5028,0.010001843767601082
30
- Baseline,3000,docvqa_val_anls,0.502653993831009,0.006267072346683124
31
- Baseline,3000,infovqa_val_anls,0.21728617578189535,0.006796941784959762
32
- Baseline,3000,mme_total_score,1170.2383953581434,
33
- Baseline,3000,mmmu_val_mmmu_acc,0.27556,
34
- Baseline,3000,mmstar_average,0.25432376938577683,
35
- Baseline,3000,ocrbench_ocrbench_accuracy,0.436,
36
- Baseline,3000,seedbench_seed_all,0.2792106725958866,
37
- Baseline,3000,textvqa_val_exact_match,0.43658,0.006766885462882726
38
- Baseline,4000,ai2d_exact_match,0.2645725388601036,0.007939149662089447
39
- Baseline,4000,average,0.36961781722974835,
40
- Baseline,4000,average_rank,2.8,
41
- Baseline,4000,chartqa_relaxed_overall,0.5312,0.009982508912777261
42
- Baseline,4000,docvqa_val_anls,0.5374434618615119,0.0062905728113059655
43
- Baseline,4000,infovqa_val_anls,0.2287924838861707,0.006994568698639919
44
- Baseline,4000,mme_total_score,1155.203781512605,
45
- Baseline,4000,mmmu_val_mmmu_acc,0.25556,
46
- Baseline,4000,mmstar_average,0.2575590188757354,
47
- Baseline,4000,ocrbench_ocrbench_accuracy,0.453,
48
- Baseline,4000,seedbench_seed_all,0.33913285158421347,
49
- Baseline,4000,textvqa_val_exact_match,0.4593,0.006791695475025738
50
- Baseline,5000,ai2d_exact_match,0.3125,0.008342439145556371
51
- Baseline,5000,average,0.3974627910380972,
52
- Baseline,5000,average_rank,2.3,
53
- Baseline,5000,chartqa_relaxed_overall,0.5488,0.00995424828018316
54
- Baseline,5000,docvqa_val_anls,0.552360266782429,0.006300308519952055
55
- Baseline,5000,infovqa_val_anls,0.23425555286643698,0.007002254622066442
56
- Baseline,5000,mme_total_score,1181.4653861544618,
57
- Baseline,5000,mmmu_val_mmmu_acc,0.26667,
58
- Baseline,5000,mmstar_average,0.29596648146165705,
59
- Baseline,5000,ocrbench_ocrbench_accuracy,0.462,
60
- Baseline,5000,seedbench_seed_all,0.43107281823235133,
61
- Baseline,5000,textvqa_val_exact_match,0.47354000000000007,0.0068172185364497985
62
- Baseline,6000,ai2d_exact_match,0.358160621761658,0.008629463221867162
63
- Baseline,6000,average,0.4161227404571003,
64
- Baseline,6000,average_rank,2.3,
65
- Baseline,6000,chartqa_relaxed_overall,0.5628,0.00992279440175477
66
- Baseline,6000,docvqa_val_anls,0.5747451497228876,0.00625495440870239
67
- Baseline,6000,infovqa_val_anls,0.22152017368968838,0.006604546680525351
68
- Baseline,6000,mme_total_score,1284.1648659463785,
69
- Baseline,6000,mmmu_val_mmmu_acc,0.27111,
70
- Baseline,6000,mmstar_average,0.2978489412854164,
71
- Baseline,6000,ocrbench_ocrbench_accuracy,0.495,
72
- Baseline,6000,seedbench_seed_all,0.4795997776542524,
73
- Baseline,6000,textvqa_val_exact_match,0.48432,0.006800535050670284
74
- Baseline,7000,ai2d_exact_match,0.3707901554404145,0.00869347755587734
75
- Baseline,7000,average,0.4291083177345374,
76
- Baseline,7000,average_rank,2.1,
77
- Baseline,7000,chartqa_relaxed_overall,0.5656,0.009915542506251351
78
- Baseline,7000,docvqa_val_anls,0.5940907049431567,0.006224236305767187
79
- Baseline,7000,infovqa_val_anls,0.2515675215816963,0.007105097396092786
80
- Baseline,7000,mme_total_score,1185.875650260104,
81
- Baseline,7000,mmmu_val_mmmu_acc,0.26556,
82
- Baseline,7000,mmstar_average,0.31372400960777047,
83
- Baseline,7000,ocrbench_ocrbench_accuracy,0.504,
84
- Baseline,7000,seedbench_seed_all,0.4964424680377988,
85
- Baseline,7000,textvqa_val_exact_match,0.5002,0.006794794025220267
86
- Baseline,8000,ai2d_exact_match,0.37759067357512954,0.008725299846043883
87
- Baseline,8000,average,0.43846759477995995,
88
- Baseline,8000,average_rank,1.9,
89
- Baseline,8000,chartqa_relaxed_overall,0.5832,0.009862556058385773
90
- Baseline,8000,docvqa_val_anls,0.6017336419437208,0.006231612198089698
91
- Baseline,8000,infovqa_val_anls,0.2449256624147254,0.006992518502948913
92
- Baseline,8000,mme_total_score,1199.2409963985594,
93
- Baseline,8000,mmmu_val_mmmu_acc,0.28111,
94
- Baseline,8000,mmstar_average,0.33512257186205047,
95
- Baseline,8000,ocrbench_ocrbench_accuracy,0.51,
96
- Baseline,8000,seedbench_seed_all,0.5024458032240133,
97
- Baseline,8000,textvqa_val_exact_match,0.51008,0.006796301690135059
98
- Baseline,9000,ai2d_exact_match,0.4067357512953368,0.008841214921078996
99
- Baseline,9000,average,0.4422510732201056,
100
- Baseline,9000,average_rank,2.5,
101
- Baseline,9000,chartqa_relaxed_overall,0.5912,0.009834211136815875
102
- Baseline,9000,docvqa_val_anls,0.6170968481662739,0.00617235763542544
103
- Baseline,9000,infovqa_val_anls,0.23537031288570615,0.00670318154156447
104
- Baseline,9000,mme_total_score,1231.5195078031213,
105
- Baseline,9000,mmmu_val_mmmu_acc,0.25889,
106
- Baseline,9000,mmstar_average,0.3216444898242951,
107
- Baseline,9000,ocrbench_ocrbench_accuracy,0.515,
108
- Baseline,9000,seedbench_seed_all,0.5120622568093385,
109
- Baseline,9000,textvqa_val_exact_match,0.52226,0.006792711289708482
110
- Baseline,10000,ai2d_exact_match,0.39993523316062174,0.008817096257082848
111
- Baseline,10000,average,0.4523875703250908,
112
- Baseline,10000,average_rank,1.9,
113
- Baseline,10000,chartqa_relaxed_overall,0.5996,0.00980154906867574
114
- Baseline,10000,docvqa_val_anls,0.6262613496433054,0.006147756371688175
115
- Baseline,10000,infovqa_val_anls,0.263290074230132,0.007186788766942786
116
- Baseline,10000,mme_total_score,1240.8218287314926,
117
- Baseline,10000,mmmu_val_mmmu_acc,0.28778,
118
- Baseline,10000,mmstar_average,0.32972717906018517,
119
- Baseline,10000,ocrbench_ocrbench_accuracy,0.517,
120
- Baseline,10000,seedbench_seed_all,0.5217342968315731,
121
- Baseline,10000,textvqa_val_exact_match,0.5261600000000001,0.006785774843600811
122
- Baseline,11000,ai2d_exact_match,0.422279792746114,0.008889771831066474
123
- Baseline,11000,average,0.4561398159525099,
124
- Baseline,11000,average_rank,2.3,
125
- Baseline,11000,chartqa_relaxed_overall,0.6104,0.009755142291143075
126
- Baseline,11000,docvqa_val_anls,0.6373130149166712,0.006128022584995044
127
- Baseline,11000,infovqa_val_anls,0.24419378339723755,0.006897644885887063
128
- Baseline,11000,mme_total_score,1322.9488795518205,
129
- Baseline,11000,mmmu_val_mmmu_acc,0.27778,
130
- Baseline,11000,mmstar_average,0.3298563439522548,
131
- Baseline,11000,ocrbench_ocrbench_accuracy,0.521,
132
- Baseline,11000,seedbench_seed_all,0.5237354085603113,
133
- Baseline,11000,textvqa_val_exact_match,0.5387,0.006770851562852138
134
- Baseline,12000,ai2d_exact_match,0.42001295336787564,0.008883255931688034
135
- Baseline,12000,average,0.4582751140055433,
136
- Baseline,12000,average_rank,2.4,
137
- Baseline,12000,chartqa_relaxed_overall,0.618,0.009719474639861454
138
- Baseline,12000,docvqa_val_anls,0.6393961983751871,0.0061228747388476674
139
- Baseline,12000,infovqa_val_anls,0.24798874058574302,0.006855374548993139
140
- Baseline,12000,mme_total_score,1225.6453581432572,
141
- Baseline,12000,mmmu_val_mmmu_acc,0.27889,
142
- Baseline,12000,mmstar_average,0.34010867846816534,
143
- Baseline,12000,ocrbench_ocrbench_accuracy,0.512,
144
- Baseline,12000,seedbench_seed_all,0.5350194552529183,
145
- Baseline,12000,textvqa_val_exact_match,0.5330600000000001,0.006777713092109446
146
- Baseline,13000,ai2d_exact_match,0.4375,0.008928571428571428
147
- Baseline,13000,average,0.4692868662590049,
148
- Baseline,13000,average_rank,1.7,
149
- Baseline,13000,chartqa_relaxed_overall,0.6148,0.00973479791861169
150
- Baseline,13000,docvqa_val_anls,0.6511374872549951,0.006086953065248391
151
- Baseline,13000,infovqa_val_anls,0.24465055100441893,0.006808432538374664
152
- Baseline,13000,mme_total_score,1281.7122849139657,
153
- Baseline,13000,mmmu_val_mmmu_acc,0.28222,
154
- Baseline,13000,mmstar_average,0.3453069542917521,
155
- Baseline,13000,ocrbench_ocrbench_accuracy,0.549,
156
- Baseline,13000,seedbench_seed_all,0.5442468037798777,
157
- Baseline,13000,textvqa_val_exact_match,0.55472,0.0067416788982325
158
- Baseline,14000,ai2d_exact_match,0.4572538860103627,0.00896620675297095
159
- Baseline,14000,average,0.47352486841689195,
160
- Baseline,14000,average_rank,1.9,
161
- Baseline,14000,chartqa_relaxed_overall,0.6172,0.009723347231923635
162
- Baseline,14000,docvqa_val_anls,0.6502269393708169,0.006057950730638126
163
- Baseline,14000,infovqa_val_anls,0.25805460837190913,0.007037735231659539
164
- Baseline,14000,mme_total_score,1309.1444577831132,
165
- Baseline,14000,mmmu_val_mmmu_acc,0.28111,
166
- Baseline,14000,mmstar_average,0.34575818188776586,
167
- Baseline,14000,ocrbench_ocrbench_accuracy,0.551,
168
- Baseline,14000,seedbench_seed_all,0.5483602001111729,
169
- Baseline,14000,textvqa_val_exact_match,0.55276,0.006751206724612103
170
- Baseline,15000,ai2d_exact_match,0.45045336787564766,0.008954861634252399
171
- Baseline,15000,average,0.47878665012878824,
172
- Baseline,15000,average_rank,1.4,
173
- Baseline,15000,chartqa_relaxed_overall,0.612,0.009747841205275417
174
- Baseline,15000,docvqa_val_anls,0.6621413031955148,0.006056838050222495
175
- Baseline,15000,infovqa_val_anls,0.2706898598157733,0.007200315730154543
176
- Baseline,15000,mme_total_score,1384.2171868747498,
177
- Baseline,15000,mmmu_val_mmmu_acc,0.30222,
178
- Baseline,15000,mmstar_average,0.35408135695920684,
179
- Baseline,15000,ocrbench_ocrbench_accuracy,0.558,
180
- Baseline,15000,seedbench_seed_all,0.5411339633129516,
181
- Baseline,15000,textvqa_val_exact_match,0.5583600000000001,0.0067279027203879065
182
- Baseline,16000,ai2d_exact_match,0.45077720207253885,0.008955440137395838
183
- Baseline,16000,average,0.47665128022935843,
184
- Baseline,16000,average_rank,2.1,
185
- Baseline,16000,chartqa_relaxed_overall,0.632,0.00964715642305132
186
- Baseline,16000,docvqa_val_anls,0.6709415729142987,0.005999818105621502
187
- Baseline,16000,infovqa_val_anls,0.26050032542402035,0.006997451875879188
188
- Baseline,16000,mme_total_score,1317.8491396558625,
189
- Baseline,16000,mmmu_val_mmmu_acc,0.27556,
190
- Baseline,16000,mmstar_average,0.33214333327093315,
191
- Baseline,16000,ocrbench_ocrbench_accuracy,0.56,
192
- Baseline,16000,seedbench_seed_all,0.5463590883824346,
193
- Baseline,16000,textvqa_val_exact_match,0.56158,0.006723854754867398
194
- Baseline,17000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
195
- Baseline,17000,average,0.4777141780162423,
196
- Baseline,17000,average_rank,1.8,
197
- Baseline,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
198
- Baseline,17000,docvqa_val_anls,0.6796338519136422,0.005948761388267941
199
- Baseline,17000,infovqa_val_anls,0.28070956072505215,0.007298333094144192
200
- Baseline,17000,mme_total_score,1381.9161664665867,
201
- Baseline,17000,mmmu_val_mmmu_acc,0.27667,
202
- Baseline,17000,mmstar_average,0.3370289492329521,
203
- Baseline,17000,ocrbench_ocrbench_accuracy,0.519,
204
- Baseline,17000,seedbench_seed_all,0.5510283490828238,
205
- Baseline,17000,textvqa_val_exact_match,0.56416,0.006724830373229479
206
- Baseline,18000,ai2d_exact_match,0.46567357512953367,0.008977921602780726
207
- Baseline,18000,average,0.4819834595278701,
208
- Baseline,18000,average_rank,1.6,
209
- Baseline,18000,chartqa_relaxed_overall,0.6376,0.009615793331418735
210
- Baseline,18000,docvqa_val_anls,0.6775884603912571,0.005972234236435759
211
- Baseline,18000,infovqa_val_anls,0.27154318420389256,0.007164903131667027
212
- Baseline,18000,mme_total_score,1336.922769107643,
213
- Baseline,18000,mmmu_val_mmmu_acc,0.28667,
214
- Baseline,18000,mmstar_average,0.34482796716566916,
215
- Baseline,18000,ocrbench_ocrbench_accuracy,0.533,
216
- Baseline,18000,seedbench_seed_all,0.5543079488604781,
217
- Baseline,18000,textvqa_val_exact_match,0.5666399999999999,0.006713392287599574
218
- Baseline,19000,ai2d_exact_match,0.4682642487046632,0.008981008686994101
219
- Baseline,19000,average,0.4899006713916878,
220
- Baseline,19000,average_rank,1.4,
221
- Baseline,19000,chartqa_relaxed_overall,0.6444,0.009575809858898698
222
- Baseline,19000,docvqa_val_anls,0.678226526479947,0.005970619221588814
223
- Baseline,19000,infovqa_val_anls,0.26993847247278,0.0071348470764911525
224
- Baseline,19000,mme_total_score,1406.6628651460583,
225
- Baseline,19000,mmmu_val_mmmu_acc,0.28333,
226
- Baseline,19000,mmstar_average,0.356220913822775,
227
- Baseline,19000,ocrbench_ocrbench_accuracy,0.577,
228
- Baseline,19000,seedbench_seed_all,0.554585881045025,
229
- Baseline,19000,textvqa_val_exact_match,0.57714,0.0066918487914812905
230
- Baseline,20000,ai2d_exact_match,0.47571243523316065,0.00898853090258662
231
- Baseline,20000,average,0.4873169067639118,
232
- Baseline,20000,average_rank,1.4,
233
- Baseline,20000,chartqa_relaxed_overall,0.6336,0.009638338810708618
234
- Baseline,20000,docvqa_val_anls,0.6895214454380043,0.005896462073053767
235
- Baseline,20000,infovqa_val_anls,0.2655657550458317,0.007033265532032538
236
- Baseline,20000,mme_total_score,1324.6738695478193,
237
- Baseline,20000,mmmu_val_mmmu_acc,0.30111,
238
- Baseline,20000,mmstar_average,0.33806766134497995,
239
- Baseline,20000,ocrbench_ocrbench_accuracy,0.555,
240
- Baseline,20000,seedbench_seed_all,0.5587548638132296,
241
- Baseline,20000,textvqa_val_exact_match,0.56852,0.006720151338087659
242
- ≥2,1000,ai2d_exact_match,0.27331606217616583,0.008021157484423315
243
- ≥2,1000,average,0.2964817591841572,
244
- ≥2,1000,average_rank,2.0,
245
- ≥2,1000,chartqa_relaxed_overall,0.4016,0.009806398022560107
246
- ≥2,1000,docvqa_val_anls,0.38703197724603455,0.0059317827343935035
247
- ≥2,1000,infovqa_val_anls,0.17280000404070578,0.006201144732918485
248
- ≥2,1000,mme_total_score,961.9496798719488,
249
- ≥2,1000,mmmu_val_mmmu_acc,0.27556,
250
- ≥2,1000,mmstar_average,0.20051212493658782,
251
- ≥2,1000,ocrbench_ocrbench_accuracy,0.331,
252
- ≥2,1000,seedbench_seed_all,0.25219566425792106,
253
- ≥2,1000,textvqa_val_exact_match,0.37432,0.006614110432353112
254
- ≥2,2000,ai2d_exact_match,0.27428756476683935,0.008030027397236182
255
- ≥2,2000,average,0.3376151239444176,
256
- ≥2,2000,average_rank,1.8,
257
- ≥2,2000,chartqa_relaxed_overall,0.4984,0.010001949389825897
258
- ≥2,2000,docvqa_val_anls,0.47035044389194575,0.006171152822696564
259
- ≥2,2000,infovqa_val_anls,0.21264444578610614,0.006798221032077756
260
- ≥2,2000,mme_total_score,995.0442176870747,
261
- ≥2,2000,mmmu_val_mmmu_acc,0.26111,
262
- ≥2,2000,mmstar_average,0.2371410151404708,
263
- ≥2,2000,ocrbench_ocrbench_accuracy,0.386,
264
- ≥2,2000,seedbench_seed_all,0.27276264591439686,
265
- ≥2,2000,textvqa_val_exact_match,0.42583999999999994,0.006752390527477444
266
- ≥2,3000,ai2d_exact_match,0.28886010362694303,0.008157423105367313
267
- ≥2,3000,average,0.3650476191493284,
268
- ≥2,3000,average_rank,2.1,
269
- ≥2,3000,chartqa_relaxed_overall,0.5296,0.009984458511341809
270
- ≥2,3000,docvqa_val_anls,0.5084048093337913,0.006266409805144786
271
- ≥2,3000,infovqa_val_anls,0.226696840609911,0.0070183318907300766
272
- ≥2,3000,mme_total_score,966.6394557823129,
273
- ≥2,3000,mmmu_val_mmmu_acc,0.27556,
274
- ≥2,3000,mmstar_average,0.25798680765602255,
275
- ≥2,3000,ocrbench_ocrbench_accuracy,0.423,
276
- ≥2,3000,seedbench_seed_all,0.3360200111172874,
277
- ≥2,3000,textvqa_val_exact_match,0.4393,0.0067683280101374045
278
- ≥2,4000,ai2d_exact_match,0.3180051813471503,0.00838183912252989
279
- ≥2,4000,average,0.3939919625964655,
280
- ≥2,4000,average_rank,2.0,
281
- ≥2,4000,chartqa_relaxed_overall,0.5392,0.009971214271372281
282
- ≥2,4000,docvqa_val_anls,0.5318426170932731,0.006287567577266625
283
- ≥2,4000,infovqa_val_anls,0.24176968468370258,0.007226680233814427
284
- ≥2,4000,mme_total_score,1052.9128651460585,
285
- ≥2,4000,mmmu_val_mmmu_acc,0.27778,
286
- ≥2,4000,mmstar_average,0.30433696178936676,
287
- ≥2,4000,ocrbench_ocrbench_accuracy,0.447,
288
- ≥2,4000,seedbench_seed_all,0.42779321845469703,
289
- ≥2,4000,textvqa_val_exact_match,0.4581999999999999,0.006800867765254084
290
- ≥2,5000,ai2d_exact_match,0.3448834196891192,0.008555140353607655
291
- ≥2,5000,average,0.40963271881608265,
292
- ≥2,5000,average_rank,2.1,
293
- ≥2,5000,chartqa_relaxed_overall,0.548,0.009955804699716018
294
- ≥2,5000,docvqa_val_anls,0.575799913178854,0.006211088978189562
295
- ≥2,5000,infovqa_val_anls,0.25711323262099633,0.0073775881337487925
296
- ≥2,5000,mme_total_score,1010.4850940376151,
297
- ≥2,5000,mmmu_val_mmmu_acc,0.27667,
298
- ≥2,5000,mmstar_average,0.2871021117490485,
299
- ≥2,5000,ocrbench_ocrbench_accuracy,0.455,
300
- ≥2,5000,seedbench_seed_all,0.46642579210672597,
301
- ≥2,5000,textvqa_val_exact_match,0.4757,0.006785477915527278
302
- ≥2,6000,ai2d_exact_match,0.3795336787564767,0.008734055590837087
303
- ≥2,6000,average,0.423161039572533,
304
- ≥2,6000,average_rank,1.4,
305
- ≥2,6000,chartqa_relaxed_overall,0.5668,0.009912336039617753
306
- ≥2,6000,docvqa_val_anls,0.5827000147792567,0.006217654063020532
307
- ≥2,6000,infovqa_val_anls,0.24558020684647988,0.0071473774205313935
308
- ≥2,6000,mme_total_score,1096.4623849539817,
309
- ≥2,6000,mmmu_val_mmmu_acc,0.27222,
310
- ≥2,6000,mmstar_average,0.3026938215293386,
311
- ≥2,6000,ocrbench_ocrbench_accuracy,0.475,
312
- ≥2,6000,seedbench_seed_all,0.49494163424124515,
313
- ≥2,6000,textvqa_val_exact_match,0.4889799999999999,0.006798040496416463
314
- ≥2,7000,ai2d_exact_match,0.3863341968911917,0.00876353292332671
315
- ≥2,7000,average,0.43260201849012403,
316
- ≥2,7000,average_rank,2.1,
317
- ≥2,7000,chartqa_relaxed_overall,0.572,0.009897756626351943
318
- ≥2,7000,docvqa_val_anls,0.5958889673096114,0.006197986096231253
319
- ≥2,7000,infovqa_val_anls,0.24831461076228495,0.0071830066608344805
320
- ≥2,7000,mme_total_score,1098.0422168867549,
321
- ≥2,7000,mmmu_val_mmmu_acc,0.28333,
322
- ≥2,7000,mmstar_average,0.31254705626181345,
323
- ≥2,7000,ocrbench_ocrbench_accuracy,0.493,
324
- ≥2,7000,seedbench_seed_all,0.5060033351862145,
325
- ≥2,7000,textvqa_val_exact_match,0.496,0.006798444216786202
326
- ≥2,8000,ai2d_exact_match,0.4025259067357513,0.00882649222855129
327
- ≥2,8000,average,0.4423608272909927,
328
- ≥2,8000,average_rank,2.1,
329
- ≥2,8000,chartqa_relaxed_overall,0.5832,0.009862556058385773
330
- ≥2,8000,docvqa_val_anls,0.6081292058298197,0.006190473638311687
331
- ≥2,8000,infovqa_val_anls,0.25707448915865344,0.007179410853014501
332
- ≥2,8000,mme_total_score,1100.4132653061224,
333
- ≥2,8000,mmmu_val_mmmu_acc,0.28,
334
- ≥2,8000,mmstar_average,0.3170263263849818,
335
- ≥2,8000,ocrbench_ocrbench_accuracy,0.504,
336
- ≥2,8000,seedbench_seed_all,0.5167315175097277,
337
- ≥2,8000,textvqa_val_exact_match,0.5125600000000001,0.006790351320381798
338
- ≥2,9000,ai2d_exact_match,0.4106217616580311,0.008854207883828036
339
- ≥2,9000,average,0.4477239927349069,
340
- ≥2,9000,average_rank,1.8,
341
- ≥2,9000,chartqa_relaxed_overall,0.5884,0.009844437067525526
342
- ≥2,9000,docvqa_val_anls,0.6233981201771228,0.006152789393932141
343
- ≥2,9000,infovqa_val_anls,0.25099979430746866,0.006997337550850154
344
- ≥2,9000,mme_total_score,1100.9423769507803,
345
- ≥2,9000,mmmu_val_mmmu_acc,0.27778,
346
- ≥2,9000,mmstar_average,0.3172130122236236,
347
- ≥2,9000,ocrbench_ocrbench_accuracy,0.518,
348
- ≥2,9000,seedbench_seed_all,0.5178432462479156,
349
- ≥2,9000,textvqa_val_exact_match,0.5252600000000001,0.006790435073078627
350
- ≥2,10000,ai2d_exact_match,0.41904145077720206,0.008880404559123598
351
- ≥2,10000,average,0.450650749528602,
352
- ≥2,10000,average_rank,2.2,
353
- ≥2,10000,chartqa_relaxed_overall,0.5956,0.009817474681589429
354
- ≥2,10000,docvqa_val_anls,0.6254308760372823,0.006142114135609194
355
- ≥2,10000,infovqa_val_anls,0.23792853517114784,0.006776022015067822
356
- ≥2,10000,mme_total_score,1157.0735294117646,
357
- ≥2,10000,mmmu_val_mmmu_acc,0.27667,
358
- ≥2,10000,mmstar_average,0.31479930233765546,
359
- ≥2,10000,ocrbench_ocrbench_accuracy,0.53,
360
- ≥2,10000,seedbench_seed_all,0.5238465814341301,
361
- ≥2,10000,textvqa_val_exact_match,0.53254,0.006777862315178193
362
- ≥2,11000,ai2d_exact_match,0.43555699481865284,0.008924095913829727
363
- ≥2,11000,average,0.4613124059808435,
364
- ≥2,11000,average_rank,1.8,
365
- ≥2,11000,chartqa_relaxed_overall,0.5984,0.009806398022560106
366
- ≥2,11000,docvqa_val_anls,0.6453200065413649,0.0060722869307158955
367
- ≥2,11000,infovqa_val_anls,0.24059820801450565,0.006814633527776416
368
- ≥2,11000,mme_total_score,1262.6299519807922,
369
- ≥2,11000,mmmu_val_mmmu_acc,0.3,
370
- ≥2,11000,mmstar_average,0.33559717819403534,
371
- ≥2,11000,ocrbench_ocrbench_accuracy,0.527,
372
- ≥2,11000,seedbench_seed_all,0.5226792662590328,
373
- ≥2,11000,textvqa_val_exact_match,0.54666,0.0067526356704400645
374
- ≥2,12000,ai2d_exact_match,0.44073834196891193,0.008935721506916777
375
- ≥2,12000,average,0.46516707040731664,
376
- ≥2,12000,average_rank,1.9,
377
- ≥2,12000,chartqa_relaxed_overall,0.598,0.009808000752013664
378
- ≥2,12000,docvqa_val_anls,0.6402481933825662,0.006107198073878916
379
- ≥2,12000,infovqa_val_anls,0.2601009880983462,0.0070991293032872695
380
- ≥2,12000,mme_total_score,1112.7142857142858,
381
- ≥2,12000,mmmu_val_mmmu_acc,0.31,
382
- ≥2,12000,mmstar_average,0.32603422027717016,
383
- ≥2,12000,ocrbench_ocrbench_accuracy,0.547,
384
- ≥2,12000,seedbench_seed_all,0.523401889938855,
385
- ≥2,12000,textvqa_val_exact_match,0.54098,0.006767635340177507
386
- ≥2,13000,ai2d_exact_match,0.44041450777202074,0.008935023865613881
387
- ≥2,13000,average,0.46553651974650545,
388
- ≥2,13000,average_rank,2.2,
389
- ≥2,13000,chartqa_relaxed_overall,0.6092,0.009760545645634788
390
- ≥2,13000,docvqa_val_anls,0.6433035796450283,0.006095519860378371
391
- ≥2,13000,infovqa_val_anls,0.2594356954563223,0.007105630672634776
392
- ≥2,13000,mme_total_score,1207.9944977991197,
393
- ≥2,13000,mmmu_val_mmmu_acc,0.28111,
394
- ≥2,13000,mmstar_average,0.3383640832831994,
395
- ≥2,13000,ocrbench_ocrbench_accuracy,0.539,
396
- ≥2,13000,seedbench_seed_all,0.5294608115619789,
397
- ≥2,13000,textvqa_val_exact_match,0.5495399999999999,0.006753508692222968
398
- ≥2,14000,ai2d_exact_match,0.44462435233160624,0.008943792697097361
399
- ≥2,14000,average,0.46921726913331274,
400
- ≥2,14000,average_rank,2.1,
401
- ≥2,14000,chartqa_relaxed_overall,0.612,0.009747841205275417
402
- ≥2,14000,docvqa_val_anls,0.65515509916543,0.006051151525703575
403
- ≥2,14000,infovqa_val_anls,0.2677755343748415,0.007100955702899581
404
- ≥2,14000,mme_total_score,1163.8374349739895,
405
- ≥2,14000,mmmu_val_mmmu_acc,0.28556,
406
- ≥2,14000,mmstar_average,0.32353974705611904,
407
- ≥2,14000,ocrbench_ocrbench_accuracy,0.543,
408
- ≥2,14000,seedbench_seed_all,0.5332406892718177,
409
- ≥2,14000,textvqa_val_exact_match,0.55806,0.006725656411892758
410
- ≥2,15000,ai2d_exact_match,0.44624352331606215,0.008946992176353901
411
- ≥2,15000,average,0.4737967933693773,
412
- ≥2,15000,average_rank,2.2,
413
- ≥2,15000,chartqa_relaxed_overall,0.618,0.009719474639861454
414
- ≥2,15000,docvqa_val_anls,0.6614354910767699,0.006013191753461033
415
- ≥2,15000,infovqa_val_anls,0.26176573129112124,0.007093151287118967
416
- ≥2,15000,mme_total_score,1229.438475390156,
417
- ≥2,15000,mmmu_val_mmmu_acc,0.29556,
418
- ≥2,15000,mmstar_average,0.32387576651370553,
419
- ≥2,15000,ocrbench_ocrbench_accuracy,0.561,
420
- ≥2,15000,seedbench_seed_all,0.5351306281267371,
421
- ≥2,15000,textvqa_val_exact_match,0.56116,0.006722390124486763
422
- ≥2,16000,ai2d_exact_match,0.4478626943005181,0.0089500956222288
423
- ≥2,16000,average,0.4748174802839308,
424
- ≥2,16000,average_rank,2.2,
425
- ≥2,16000,chartqa_relaxed_overall,0.6192,0.009713613422114641
426
- ≥2,16000,docvqa_val_anls,0.6585392720477772,0.0060616936904167125
427
- ≥2,16000,infovqa_val_anls,0.2653830027853819,0.007108417358601188
428
- ≥2,16000,mme_total_score,1157.8782513005203,
429
- ≥2,16000,mmmu_val_mmmu_acc,0.29889,
430
- ≥2,16000,mmstar_average,0.3217940710425999,
431
- ≥2,16000,ocrbench_ocrbench_accuracy,0.561,
432
- ≥2,16000,seedbench_seed_all,0.5349082823790995,
433
- ≥2,16000,textvqa_val_exact_match,0.5657800000000001,0.006716429140851619
434
- ≥2,17000,ai2d_exact_match,0.4540155440414508,0.00896101461327443
435
- ≥2,17000,average,0.4765363782507968,
436
- ≥2,17000,average_rank,2.2,
437
- ≥2,17000,chartqa_relaxed_overall,0.6184,0.009717527882093043
438
- ≥2,17000,docvqa_val_anls,0.6605538305641464,0.006048170352990264
439
- ≥2,17000,infovqa_val_anls,0.27438351817158263,0.007183740557624646
440
- ≥2,17000,mme_total_score,1231.31512605042,
441
- ≥2,17000,mmmu_val_mmmu_acc,0.30111,
442
- ≥2,17000,mmstar_average,0.3273406426639828,
443
- ≥2,17000,ocrbench_ocrbench_accuracy,0.555,
444
- ≥2,17000,seedbench_seed_all,0.5349638688160089,
445
- ≥2,17000,textvqa_val_exact_match,0.5630599999999999,0.006726822229512349
446
- ≥2,18000,ai2d_exact_match,0.4540155440414508,0.008961014613274428
447
- ≥2,18000,average,0.4749977548559891,
448
- ≥2,18000,average_rank,2.3,
449
- ≥2,18000,chartqa_relaxed_overall,0.614,0.009738559226822298
450
- ≥2,18000,docvqa_val_anls,0.6647865229953943,0.00602531683337989
451
- ≥2,18000,infovqa_val_anls,0.26486387970800995,0.006977819681460442
452
- ≥2,18000,mme_total_score,1245.188775510204,
453
- ≥2,18000,mmmu_val_mmmu_acc,0.29222,
454
- ≥2,18000,mmstar_average,0.32473355790957514,
455
- ≥2,18000,ocrbench_ocrbench_accuracy,0.555,
456
- ≥2,18000,seedbench_seed_all,0.5365202890494719,
457
- ≥2,18000,textvqa_val_exact_match,0.56884,0.006699820027260398
458
- ≥2,19000,ai2d_exact_match,0.45466321243523317,0.00896208360613934
459
- ≥2,19000,average,0.4768734192584572,
460
- ≥2,19000,average_rank,2.6,
461
- ≥2,19000,chartqa_relaxed_overall,0.62,0.009709671008043154
462
- ≥2,19000,docvqa_val_anls,0.6628357233664792,0.006042075311037487
463
- ≥2,19000,infovqa_val_anls,0.2657171063652747,0.007078002720459511
464
- ≥2,19000,mme_total_score,1248.7323929571828,
465
- ≥2,19000,mmmu_val_mmmu_acc,0.28889,
466
- ≥2,19000,mmstar_average,0.32802808302127334,
467
- ≥2,19000,ocrbench_ocrbench_accuracy,0.565,
468
- ≥2,19000,seedbench_seed_all,0.5399666481378543,
469
- ≥2,19000,textvqa_val_exact_match,0.5667599999999999,0.00671422643700147
470
- ≥2,20000,ai2d_exact_match,0.46178756476683935,0.008972834678172942
471
- ≥2,20000,average,0.47802392695549656,
472
- ≥2,20000,average_rank,2.3,
473
- ≥2,20000,chartqa_relaxed_overall,0.618,0.009719474639861454
474
- ≥2,20000,docvqa_val_anls,0.666568303416173,0.0059980334517589756
475
- ≥2,20000,infovqa_val_anls,0.2651324480102521,0.0070565217028431
476
- ≥2,20000,mme_total_score,1233.6009403761504,
477
- ≥2,20000,mmmu_val_mmmu_acc,0.28,
478
- ≥2,20000,mmstar_average,0.33277914424945065,
479
- ≥2,20000,ocrbench_ocrbench_accuracy,0.562,
480
- ≥2,20000,seedbench_seed_all,0.5381878821567537,
481
- ≥2,20000,textvqa_val_exact_match,0.5777599999999999,0.00668799090343766
482
- ≥3,1000,ai2d_exact_match,0.2661917098445596,0.007954634970279362
483
- ≥3,1000,average,0.2680725844272073,
484
- ≥3,1000,average_rank,3.2,
485
- ≥3,1000,chartqa_relaxed_overall,0.3476,0.009526069199715017
486
- ≥3,1000,docvqa_val_anls,0.3752729856163278,0.005939283617489936
487
- ≥3,1000,infovqa_val_anls,0.17325429231808173,0.0062340220795234725
488
- ≥3,1000,mme_total_score,707.53231292517,
489
- ≥3,1000,mmmu_val_mmmu_acc,0.23889,
490
- ≥3,1000,mmstar_average,0.19784737378907616,
491
- ≥3,1000,ocrbench_ocrbench_accuracy,0.288,
492
- ≥3,1000,seedbench_seed_all,0.25041689827682045,
493
- ≥3,1000,textvqa_val_exact_match,0.27518000000000004,0.006128613668775364
494
- ≥3,2000,ai2d_exact_match,0.27266839378238344,0.008015217564479073
495
- ≥3,2000,average,0.31253656058741547,
496
- ≥3,2000,average_rank,3.4,
497
- ≥3,2000,chartqa_relaxed_overall,0.4308,0.00990574548014469
498
- ≥3,2000,docvqa_val_anls,0.4481749259885666,0.00619992092326252
499
- ≥3,2000,infovqa_val_anls,0.19674507942801486,0.006580664003046453
500
- ≥3,2000,mme_total_score,786.0510204081633,
501
- ≥3,2000,mmmu_val_mmmu_acc,0.23556,
502
- ≥3,2000,mmstar_average,0.19768658271923586,
503
- ≥3,2000,ocrbench_ocrbench_accuracy,0.377,
504
- ≥3,2000,seedbench_seed_all,0.2653140633685381,
505
- ≥3,2000,textvqa_val_exact_match,0.38888,0.006660461055234364
506
- ≥3,3000,ai2d_exact_match,0.28270725388601037,0.008104913435481193
507
- ≥3,3000,average,0.34936609328629703,
508
- ≥3,3000,average_rank,3.2,
509
- ≥3,3000,chartqa_relaxed_overall,0.4844,0.009997131241172205
510
- ≥3,3000,docvqa_val_anls,0.49044354643512195,0.0062294371457984315
511
- ≥3,3000,infovqa_val_anls,0.21295743099446893,0.006855571779287104
512
- ≥3,3000,mme_total_score,861.8877551020407,
513
- ≥3,3000,mmmu_val_mmmu_acc,0.24889,
514
- ≥3,3000,mmstar_average,0.258368014597926,
515
- ≥3,3000,ocrbench_ocrbench_accuracy,0.394,
516
- ≥3,3000,seedbench_seed_all,0.3434685936631462,
517
- ≥3,3000,textvqa_val_exact_match,0.42906000000000005,0.0067494454796565755
518
- ≥3,4000,ai2d_exact_match,0.3325777202072539,0.00847966336079129
519
- ≥3,4000,average,0.3855383645559374,
520
- ≥3,4000,average_rank,2.8,
521
- ≥3,4000,chartqa_relaxed_overall,0.508,0.010000720262176365
522
- ≥3,4000,docvqa_val_anls,0.5226854794419781,0.006293466169647169
523
- ≥3,4000,infovqa_val_anls,0.2322658206586996,0.007103396837310004
524
- ≥3,4000,mme_total_score,912.9521808723489,
525
- ≥3,4000,mmmu_val_mmmu_acc,0.26667,
526
- ≥3,4000,mmstar_average,0.3070035703119584,
527
- ≥3,4000,ocrbench_ocrbench_accuracy,0.438,
528
- ≥3,4000,seedbench_seed_all,0.41684269038354643,
529
- ≥3,4000,textvqa_val_exact_match,0.4458,0.006781745381100857
530
- ≥3,5000,ai2d_exact_match,0.34520725388601037,0.008557040186364025
531
- ≥3,5000,average,0.39676974212184324,
532
- ≥3,5000,average_rank,2.7,
533
- ≥3,5000,chartqa_relaxed_overall,0.51,0.01
534
- ≥3,5000,docvqa_val_anls,0.5420071464866951,0.006256421242173299
535
- ≥3,5000,infovqa_val_anls,0.21485812900527704,0.0066319183580626885
536
- ≥3,5000,mme_total_score,957.2279911964786,
537
- ≥3,5000,mmmu_val_mmmu_acc,0.26111,
538
- ≥3,5000,mmstar_average,0.30632830702822333,
539
- ≥3,5000,ocrbench_ocrbench_accuracy,0.44,
540
- ≥3,5000,seedbench_seed_all,0.47031684269038354,
541
- ≥3,5000,textvqa_val_exact_match,0.4811,0.00681344572213808
542
- ≥3,6000,ai2d_exact_match,0.37629533678756477,0.008719379877890884
543
- ≥3,6000,average,0.40447034433869705,
544
- ≥3,6000,average_rank,3.3,
545
- ≥3,6000,chartqa_relaxed_overall,0.5084,0.010000589018267121
546
- ≥3,6000,docvqa_val_anls,0.5540669563018141,0.006258072329892215
547
- ≥3,6000,infovqa_val_anls,0.216535214445592,0.00668611609159469
548
- ≥3,6000,mme_total_score,864.5272108843537,
549
- ≥3,6000,mmmu_val_mmmu_acc,0.26889,
550
- ≥3,6000,mmstar_average,0.2932406887895669,
551
- ≥3,6000,ocrbench_ocrbench_accuracy,0.454,
552
- ≥3,6000,seedbench_seed_all,0.4848249027237354,
553
- ≥3,6000,textvqa_val_exact_match,0.48398,0.006803464510517356
554
- ≥3,7000,ai2d_exact_match,0.3947538860103627,0.008797532848529207
555
- ≥3,7000,average,0.42355543935120793,
556
- ≥3,7000,average_rank,2.7,
557
- ≥3,7000,chartqa_relaxed_overall,0.5488,0.00995424828018316
558
- ≥3,7000,docvqa_val_anls,0.5797391833660968,0.006220930330963092
559
- ≥3,7000,infovqa_val_anls,0.2221619185818123,0.00673372198453672
560
- ≥3,7000,mme_total_score,866.3928571428571,
561
- ≥3,7000,mmmu_val_mmmu_acc,0.28667,
562
- ≥3,7000,mmstar_average,0.3209799250686363,
563
- ≥3,7000,ocrbench_ocrbench_accuracy,0.476,
564
- ≥3,7000,seedbench_seed_all,0.49327404113396334,
565
- ≥3,7000,textvqa_val_exact_match,0.48962000000000006,0.006807769110659733
566
- ≥3,8000,ai2d_exact_match,0.4102979274611399,0.008853146969712133
567
- ≥3,8000,average,0.42791468613133354,
568
- ≥3,8000,average_rank,3.4,
569
- ≥3,8000,chartqa_relaxed_overall,0.5456,0.00996031822662661
570
- ≥3,8000,docvqa_val_anls,0.5824594046059755,0.006268157085435711
571
- ≥3,8000,infovqa_val_anls,0.22074277862778585,0.006618518997755148
572
- ≥3,8000,mme_total_score,788.9880952380953,
573
- ≥3,8000,mmmu_val_mmmu_acc,0.27556,
574
- ≥3,8000,mmstar_average,0.32537357643818443,
575
- ≥3,8000,ocrbench_ocrbench_accuracy,0.5,
576
- ≥3,8000,seedbench_seed_all,0.5012784880489161,
577
- ≥3,8000,textvqa_val_exact_match,0.48991999999999997,0.006810591424473371
578
- ≥3,9000,ai2d_exact_match,0.4251943005181347,0.0088978675214111
579
- ≥3,9000,average,0.4411468725875502,
580
- ≥3,9000,average_rank,2.9,
581
- ≥3,9000,chartqa_relaxed_overall,0.5648,0.009917647296166388
582
- ≥3,9000,docvqa_val_anls,0.6050413765127355,0.006187758928771102
583
- ≥3,9000,infovqa_val_anls,0.23301995192200392,0.00676964747288323
584
- ≥3,9000,mme_total_score,825.0221088435375,
585
- ≥3,9000,mmmu_val_mmmu_acc,0.27556,
586
- ≥3,9000,mmstar_average,0.33219983189483276,
587
- ≥3,9000,ocrbench_ocrbench_accuracy,0.504,
588
- ≥3,9000,seedbench_seed_all,0.5115063924402445,
589
- ≥3,9000,textvqa_val_exact_match,0.519,0.006787356896666665
590
- ≥3,10000,ai2d_exact_match,0.4258419689119171,0.00889962357526378
591
- ≥3,10000,average,0.44419201562479543,
592
- ≥3,10000,average_rank,2.7,
593
- ≥3,10000,chartqa_relaxed_overall,0.576,0.009885782289560632
594
- ≥3,10000,docvqa_val_anls,0.6087522279355707,0.006173079977045839
595
- ≥3,10000,infovqa_val_anls,0.24383042893389267,0.0069221731872859795
596
- ≥3,10000,mme_total_score,915.8061224489795,
597
- ≥3,10000,mmmu_val_mmmu_acc,0.27333,
598
- ≥3,10000,mmstar_average,0.3351679228462254,
599
- ≥3,10000,ocrbench_ocrbench_accuracy,0.489,
600
- ≥3,10000,seedbench_seed_all,0.5180655919955531,
601
- ≥3,10000,textvqa_val_exact_match,0.5277400000000001,0.006769908774345677
602
- ≥3,11000,ai2d_exact_match,0.43426165803108807,0.008921034830887029
603
- ≥3,11000,average,0.45138194167282136,
604
- ≥3,11000,average_rank,2.9,
605
- ≥3,11000,chartqa_relaxed_overall,0.5784,0.009878279615563902
606
- ≥3,11000,docvqa_val_anls,0.6240570866567314,0.006144737191710238
607
- ≥3,11000,infovqa_val_anls,0.2562175057951717,0.0071028888697453095
608
- ≥3,11000,mme_total_score,852.3894557823129,
609
- ≥3,11000,mmmu_val_mmmu_acc,0.28778,
610
- ≥3,11000,mmstar_average,0.3331474836051967,
611
- ≥3,11000,ocrbench_ocrbench_accuracy,0.5,
612
- ≥3,11000,seedbench_seed_all,0.520733740967204,
613
- ≥3,11000,textvqa_val_exact_match,0.5278400000000001,0.00678178334931745
614
- ≥3,12000,ai2d_exact_match,0.4381476683937824,0.008930032335354965
615
- ≥3,12000,average,0.45691171338244096,
616
- ≥3,12000,average_rank,2.5,
617
- ≥3,12000,chartqa_relaxed_overall,0.572,0.009897756626351943
618
- ≥3,12000,docvqa_val_anls,0.6273497290110698,0.006129247411332687
619
- ≥3,12000,infovqa_val_anls,0.268135358118058,0.007380056393275344
620
- ≥3,12000,mme_total_score,893.8265306122448,
621
- ≥3,12000,mmmu_val_mmmu_acc,0.29556,
622
- ≥3,12000,mmstar_average,0.34474290394073753,
623
- ≥3,12000,ocrbench_ocrbench_accuracy,0.508,
624
- ≥3,12000,seedbench_seed_all,0.5255697609783213,
625
- ≥3,12000,textvqa_val_exact_match,0.5327,0.006782133990735781
626
- ≥3,13000,ai2d_exact_match,0.43458549222797926,0.008921805911548512
627
- ≥3,13000,average,0.4607824778908788,
628
- ≥3,13000,average_rank,2.7,
629
- ≥3,13000,chartqa_relaxed_overall,0.5876,0.009847298295140926
630
- ≥3,13000,docvqa_val_anls,0.6386402725745638,0.006069984676680257
631
- ≥3,13000,infovqa_val_anls,0.2536816276782758,0.00704241123014852
632
- ≥3,13000,mme_total_score,941.5953381352541,
633
- ≥3,13000,mmmu_val_mmmu_acc,0.29667,
634
- ≥3,13000,mmstar_average,0.34638755445148733,
635
- ≥3,13000,ocrbench_ocrbench_accuracy,0.53,
636
- ≥3,13000,seedbench_seed_all,0.5272373540856031,
637
- ≥3,13000,textvqa_val_exact_match,0.53224,0.00678673179267349
638
- ≥3,14000,ai2d_exact_match,0.43490932642487046,0.008922573118260885
639
- ≥3,14000,average,0.4621098839598732,
640
- ≥3,14000,average_rank,2.8,
641
- ≥3,14000,chartqa_relaxed_overall,0.5936,0.009825183443166683
642
- ≥3,14000,docvqa_val_anls,0.6373184890679852,0.006105256249191251
643
- ≥3,14000,infovqa_val_anls,0.2624975120280117,0.007131056805776271
644
- ≥3,14000,mme_total_score,901.2585034013605,
645
- ≥3,14000,mmmu_val_mmmu_acc,0.28444,
646
- ≥3,14000,mmstar_average,0.34930389493288816,
647
- ≥3,14000,ocrbench_ocrbench_accuracy,0.517,
648
- ≥3,14000,seedbench_seed_all,0.5355197331851028,
649
- ≥3,14000,textvqa_val_exact_match,0.5444,0.006752217894092123
650
- ≥3,15000,ai2d_exact_match,0.44527202072538863,0.008945084019331405
651
- ≥3,15000,average,0.46643076140543904,
652
- ≥3,15000,average_rank,3.0,
653
- ≥3,15000,chartqa_relaxed_overall,0.5848,0.00985710144918839
654
- ≥3,15000,docvqa_val_anls,0.642316016710227,0.006100312721783546
655
- ≥3,15000,infovqa_val_anls,0.2596632231498878,0.007146587424008848
656
- ≥3,15000,mme_total_score,891.8367346938775,
657
- ≥3,15000,mmmu_val_mmmu_acc,0.29778,
658
- ≥3,15000,mmstar_average,0.34413882163543197,
659
- ≥3,15000,ocrbench_ocrbench_accuracy,0.538,
660
- ≥3,15000,seedbench_seed_all,0.5361867704280155,
661
- ≥3,15000,textvqa_val_exact_match,0.54972,0.006745330549116431
662
- ≥3,16000,ai2d_exact_match,0.4494818652849741,0.008953103134587205
663
- ≥3,16000,average,0.46786516199576034,
664
- ≥3,16000,average_rank,2.7,
665
- ≥3,16000,chartqa_relaxed_overall,0.5976,0.009809596692775395
666
- ≥3,16000,docvqa_val_anls,0.6432815750341822,0.006081847680686157
667
- ≥3,16000,infovqa_val_anls,0.2702450654855036,0.007372825383364985
668
- ≥3,16000,mme_total_score,919.3826530612245,
669
- ≥3,16000,mmmu_val_mmmu_acc,0.28333,
670
- ≥3,16000,mmstar_average,0.3386692973489569,
671
- ≥3,16000,ocrbench_ocrbench_accuracy,0.534,
672
- ≥3,16000,seedbench_seed_all,0.5415786548082268,
673
- ≥3,16000,textvqa_val_exact_match,0.5526,0.006745409410081935
674
- ≥3,17000,ai2d_exact_match,0.4494818652849741,0.008953103134587206
675
- ≥3,17000,average,0.4694732091424512,
676
- ≥3,17000,average_rank,2.8,
677
- ≥3,17000,chartqa_relaxed_overall,0.596,0.009815912634917984
678
- ≥3,17000,docvqa_val_anls,0.6468732282054332,0.006069886071041202
679
- ≥3,17000,infovqa_val_anls,0.2650584835459577,0.0072427928867972455
680
- ≥3,17000,mme_total_score,889.5646258503401,
681
- ≥3,17000,mmmu_val_mmmu_acc,0.29333,
682
- ≥3,17000,mmstar_average,0.342978718252922,
683
- ≥3,17000,ocrbench_ocrbench_accuracy,0.53,
684
- ≥3,17000,seedbench_seed_all,0.5418565869927737,
685
- ≥3,17000,textvqa_val_exact_match,0.5596800000000001,0.006734324743131207
686
- ≥3,18000,ai2d_exact_match,0.45531088082901555,0.008963137311190377
687
- ≥3,18000,average,0.46991408851845295,
688
- ≥3,18000,average_rank,2.7,
689
- ≥3,18000,chartqa_relaxed_overall,0.6036,0.009784943231599163
690
- ≥3,18000,docvqa_val_anls,0.6501128555487647,0.006068985343727089
691
- ≥3,18000,infovqa_val_anls,0.26796275265157754,0.007202201134473747
692
- ≥3,18000,mme_total_score,894.1054421768707,
693
- ≥3,18000,mmmu_val_mmmu_acc,0.28333,
694
- ≥3,18000,mmstar_average,0.33590517144994875,
695
- ≥3,18000,ocrbench_ocrbench_accuracy,0.534,
696
- ≥3,18000,seedbench_seed_all,0.5412451361867704,
697
- ≥3,18000,textvqa_val_exact_match,0.5577599999999999,0.0067408786051132655
698
- ≥3,19000,ai2d_exact_match,0.4498056994818653,0.008953693133598168
699
- ≥3,19000,average,0.47011136523574254,
700
- ≥3,19000,average_rank,3.0,
701
- ≥3,19000,chartqa_relaxed_overall,0.6096,0.009758751420735989
702
- ≥3,19000,docvqa_val_anls,0.6538834113203496,0.006040538366936906
703
- ≥3,19000,infovqa_val_anls,0.2705360277052952,0.007291872911349649
704
- ≥3,19000,mme_total_score,906.3231292517007,
705
- ≥3,19000,mmmu_val_mmmu_acc,0.27556,
706
- ≥3,19000,mmstar_average,0.3356215177081144,
707
- ≥3,19000,ocrbench_ocrbench_accuracy,0.539,
708
- ≥3,19000,seedbench_seed_all,0.5441356309060589,
709
- ≥3,19000,textvqa_val_exact_match,0.5528599999999999,0.006753272200724876
710
- ≥3,20000,ai2d_exact_match,0.44656735751295334,0.008947620544957215
711
- ≥3,20000,average,0.4679556547685855,
712
- ≥3,20000,average_rank,2.9,
713
- ≥3,20000,chartqa_relaxed_overall,0.5976,0.009809596692775395
714
- ≥3,20000,docvqa_val_anls,0.6493769742508846,0.006072933213063366
715
- ≥3,20000,infovqa_val_anls,0.26540905854876357,0.007209592372844281
716
- ≥3,20000,mme_total_score,926.0901360544218,
717
- ≥3,20000,mmmu_val_mmmu_acc,0.27333,
718
- ≥3,20000,mmstar_average,0.34157097675697473,
719
- ≥3,20000,ocrbench_ocrbench_accuracy,0.539,
720
- ≥3,20000,seedbench_seed_all,0.5437465258476931,
721
- ≥3,20000,textvqa_val_exact_match,0.555,0.0067346322137300735
722
- ≥4,1000,ai2d_exact_match,0.25874352331606215,0.00788225861008497
723
- ≥4,1000,average,0.27914578527127093,
724
- ≥4,1000,average_rank,2.6,
725
- ≥4,1000,chartqa_relaxed_overall,0.3512,0.009548816468986268
726
- ≥4,1000,docvqa_val_anls,0.36858592315444033,0.005921151680127505
727
- ≥4,1000,infovqa_val_anls,0.17699311795329079,0.006346227986201575
728
- ≥4,1000,mme_total_score,671.343537414966,
729
- ≥4,1000,mmmu_val_mmmu_acc,0.27111,
730
- ≥4,1000,mmstar_average,0.2086858732233149,
731
- ≥4,1000,ocrbench_ocrbench_accuracy,0.261,
732
- ≥4,1000,seedbench_seed_all,0.2605336297943302,
733
- ≥4,1000,textvqa_val_exact_match,0.35546000000000005,0.006549153835664011
734
- ≥4,2000,ai2d_exact_match,0.280440414507772,0.008085099461783339
735
- ≥4,2000,average,0.320025358717614,
736
- ≥4,2000,average_rank,2.8,
737
- ≥4,2000,chartqa_relaxed_overall,0.4488,0.009949423119365426
738
- ≥4,2000,docvqa_val_anls,0.43140645952438456,0.006042366638541379
739
- ≥4,2000,infovqa_val_anls,0.16528808420419083,0.005907032628809945
740
- ≥4,2000,mme_total_score,705.5901360544218,
741
- ≥4,2000,mmmu_val_mmmu_acc,0.27222,
742
- ≥4,2000,mmstar_average,0.24877125799316246,
743
- ≥4,2000,ocrbench_ocrbench_accuracy,0.329,
744
- ≥4,2000,seedbench_seed_all,0.3196220122290161,
745
- ≥4,2000,textvqa_val_exact_match,0.38468,0.006645983248449226
746
- ≥4,3000,ai2d_exact_match,0.34617875647668395,0.008562713351618977
747
- ≥4,3000,average,0.3596236953408542,
748
- ≥4,3000,average_rank,2.8,
749
- ≥4,3000,chartqa_relaxed_overall,0.468,0.009981495484186743
750
- ≥4,3000,docvqa_val_anls,0.464923009199496,0.006156900593094097
751
- ≥4,3000,infovqa_val_anls,0.18011502045718095,0.0061004080312330325
752
- ≥4,3000,mme_total_score,709.3333333333333,
753
- ≥4,3000,mmmu_val_mmmu_acc,0.27778,
754
- ≥4,3000,mmstar_average,0.30716380934399923,
755
- ≥4,3000,ocrbench_ocrbench_accuracy,0.351,
756
- ≥4,3000,seedbench_seed_all,0.42679266259032794,
757
- ≥4,3000,textvqa_val_exact_match,0.41466,0.006725300202411972
758
- ≥4,4000,ai2d_exact_match,0.36593264248704666,0.008669617940526182
759
- ≥4,4000,average,0.3829150140884673,
760
- ≥4,4000,average_rank,2.7,
761
- ≥4,4000,chartqa_relaxed_overall,0.5136,0.009998299975543861
762
- ≥4,4000,docvqa_val_anls,0.5002844765367886,0.0062258433013991955
763
- ≥4,4000,infovqa_val_anls,0.18808280764611432,0.006209185081756124
764
- ≥4,4000,mme_total_score,700.1989795918367,
765
- ≥4,4000,mmmu_val_mmmu_acc,0.28889,
766
- ≥4,4000,mmstar_average,0.3128795636615537,
767
- ≥4,4000,ocrbench_ocrbench_accuracy,0.379,
768
- ≥4,4000,seedbench_seed_all,0.46214563646470264,
769
- ≥4,4000,textvqa_val_exact_match,0.4354199999999999,0.006770365742739316
770
- ≥4,5000,ai2d_exact_match,0.39702072538860106,0.008806218703419164
771
- ≥4,5000,average,0.3990130243200321,
772
- ≥4,5000,average_rank,3.0,
773
- ≥4,5000,chartqa_relaxed_overall,0.5432,0.009964598400764347
774
- ≥4,5000,docvqa_val_anls,0.5330701388059006,0.006244542429703876
775
- ≥4,5000,infovqa_val_anls,0.20064814149562474,0.006400433745304747
776
- ≥4,5000,mme_total_score,687.6802721088436,
777
- ≥4,5000,mmmu_val_mmmu_acc,0.26333,
778
- ≥4,5000,mmstar_average,0.30889646221740025,
779
- ≥4,5000,ocrbench_ocrbench_accuracy,0.412,
780
- ≥4,5000,seedbench_seed_all,0.47315175097276263,
781
- ≥4,5000,textvqa_val_exact_match,0.4598,0.006799443983716428
782
- ≥4,6000,ai2d_exact_match,0.41224093264248707,0.00885945303235887
783
- ≥4,6000,average,0.4037939250305515,
784
- ≥4,6000,average_rank,3.2,
785
- ≥4,6000,chartqa_relaxed_overall,0.5312,0.009982508912777261
786
- ≥4,6000,docvqa_val_anls,0.5259911309932884,0.006272635836910295
787
- ≥4,6000,infovqa_val_anls,0.22056731437063212,0.00674209963892894
788
- ≥4,6000,mme_total_score,717.0051020408164,
789
- ≥4,6000,mmmu_val_mmmu_acc,0.26667,
790
- ≥4,6000,mmstar_average,0.3316518783413741,
791
- ≥4,6000,ocrbench_ocrbench_accuracy,0.408,
792
- ≥4,6000,seedbench_seed_all,0.48332406892718177,
793
- ≥4,6000,textvqa_val_exact_match,0.4544999999999999,0.006790726970992053
794
- ≥4,7000,ai2d_exact_match,0.4102979274611399,0.008853146969712133
795
- ≥4,7000,average,0.41740315045514464,
796
- ≥4,7000,average_rank,3.1,
797
- ≥4,7000,chartqa_relaxed_overall,0.5588,0.009932597172675325
798
- ≥4,7000,docvqa_val_anls,0.5597972576652357,0.0062571833970283125
799
- ≥4,7000,infovqa_val_anls,0.21665617889681224,0.006562362156515704
800
- ≥4,7000,mme_total_score,716.7908163265306,
801
- ≥4,7000,mmmu_val_mmmu_acc,0.28556,
802
- ≥4,7000,mmstar_average,0.32150517239662685,
803
- ≥4,7000,ocrbench_ocrbench_accuracy,0.431,
804
- ≥4,7000,seedbench_seed_all,0.4892718176764869,
805
- ≥4,7000,textvqa_val_exact_match,0.48374000000000006,0.006820617761268334
806
- ≥4,8000,ai2d_exact_match,0.4213082901554404,0.00888700282309854
807
- ≥4,8000,average,0.4251708917847074,
808
- ≥4,8000,average_rank,2.9,
809
- ≥4,8000,chartqa_relaxed_overall,0.564,0.009919725822025206
810
- ≥4,8000,docvqa_val_anls,0.5702706873242411,0.006237250618852069
811
- ≥4,8000,infovqa_val_anls,0.24000454829818865,0.006935520157929643
812
- ≥4,8000,mme_total_score,705.8180272108843,
813
- ≥4,8000,mmmu_val_mmmu_acc,0.28778,
814
- ≥4,8000,mmstar_average,0.3384645614295773,
815
- ≥4,8000,ocrbench_ocrbench_accuracy,0.42,
816
- ≥4,8000,seedbench_seed_all,0.5018899388549194,
817
- ≥4,8000,textvqa_val_exact_match,0.48281999999999997,0.006811185503977551
818
- ≥4,9000,ai2d_exact_match,0.4319948186528497,0.008915528710615487
819
- ≥4,9000,average,0.4318231930659084,
820
- ≥4,9000,average_rank,2.9,
821
- ≥4,9000,chartqa_relaxed_overall,0.5676,0.009910165515884228
822
- ≥4,9000,docvqa_val_anls,0.5846178021051754,0.006187149390116838
823
- ≥4,9000,infovqa_val_anls,0.2228617948699063,0.0066001763459020155
824
- ≥4,9000,mme_total_score,733.3503401360545,
825
- ≥4,9000,mmmu_val_mmmu_acc,0.28444,
826
- ≥4,9000,mmstar_average,0.3307124653782511,
827
- ≥4,9000,ocrbench_ocrbench_accuracy,0.463,
828
- ≥4,9000,seedbench_seed_all,0.5153418565869927,
829
- ≥4,9000,textvqa_val_exact_match,0.48583999999999994,0.0068269187957708125
830
- ≥4,10000,ai2d_exact_match,0.4410621761658031,0.0089364152923413
831
- ≥4,10000,average,0.436822457787989,
832
- ≥4,10000,average_rank,3.4,
833
- ≥4,10000,chartqa_relaxed_overall,0.5756,0.009887009516677585
834
- ≥4,10000,docvqa_val_anls,0.591441723638793,0.0062031994384821754
835
- ≥4,10000,infovqa_val_anls,0.22327754225685992,0.00649750251357461
836
- ≥4,10000,mme_total_score,695.8112244897959,
837
- ≥4,10000,mmmu_val_mmmu_acc,0.28778,
838
- ≥4,10000,mmstar_average,0.33369690927002266,
839
- ≥4,10000,ocrbench_ocrbench_accuracy,0.472,
840
- ≥4,10000,seedbench_seed_all,0.5107837687604224,
841
- ≥4,10000,textvqa_val_exact_match,0.49576000000000003,0.006808118284439173
842
- ≥4,11000,ai2d_exact_match,0.44332901554404147,0.008941163900483134
843
- ≥4,11000,average,0.44624717945755144,
844
- ≥4,11000,average_rank,3.0,
845
- ≥4,11000,chartqa_relaxed_overall,0.5868,0.009850132691777215
846
- ≥4,11000,docvqa_val_anls,0.60625861922937,0.006159202385167996
847
- ≥4,11000,infovqa_val_anls,0.2435454505191485,0.006860039872881237
848
- ≥4,11000,mme_total_score,751.1462585034014,
849
- ≥4,11000,mmmu_val_mmmu_acc,0.29222,
850
- ≥4,11000,mmstar_average,0.3470954764624236,
851
- ≥4,11000,ocrbench_ocrbench_accuracy,0.486,
852
- ≥4,11000,seedbench_seed_all,0.5128960533629794,
853
- ≥4,11000,textvqa_val_exact_match,0.49808,0.006799508024988012
854
- ≥4,12000,ai2d_exact_match,0.45142487046632124,0.008956585653027465
855
- ≥4,12000,average,0.44514971381341617,
856
- ≥4,12000,average_rank,3.3,
857
- ≥4,12000,chartqa_relaxed_overall,0.5868,0.009850132691777215
858
- ≥4,12000,docvqa_val_anls,0.6047188055272135,0.0061847009209673315
859
- ≥4,12000,infovqa_val_anls,0.2506217753279014,0.006972909032069362
860
- ≥4,12000,mme_total_score,742.969387755102,
861
- ≥4,12000,mmmu_val_mmmu_acc,0.28556,
862
- ≥4,12000,mmstar_average,0.33917912697374,
863
- ≥4,12000,ocrbench_ocrbench_accuracy,0.459,
864
- ≥4,12000,seedbench_seed_all,0.5211228460255698,
865
- ≥4,12000,textvqa_val_exact_match,0.5079199999999999,0.006798462954205747
866
- ≥4,13000,ai2d_exact_match,0.44689119170984454,0.00894824507304496
867
- ≥4,13000,average,0.4478540374461813,
868
- ≥4,13000,average_rank,3.5,
869
- ≥4,13000,chartqa_relaxed_overall,0.5936,0.009825183443166683
870
- ≥4,13000,docvqa_val_anls,0.6123877664020703,0.0061423212651813735
871
- ≥4,13000,infovqa_val_anls,0.23197941094655744,0.0066388766376455225
872
- ≥4,13000,mme_total_score,705.0068027210884,
873
- ≥4,13000,mmmu_val_mmmu_acc,0.29444,
874
- ≥4,13000,mmstar_average,0.3172158612312008,
875
- ≥4,13000,ocrbench_ocrbench_accuracy,0.5,
876
- ≥4,13000,seedbench_seed_all,0.5257921067259589,
877
- ≥4,13000,textvqa_val_exact_match,0.50838,0.006803735244897213
878
- ≥4,14000,ai2d_exact_match,0.45628238341968913,0.008964689215887884
879
- ≥4,14000,average,0.4541657280018954,
880
- ≥4,14000,average_rank,3.3,
881
- ≥4,14000,chartqa_relaxed_overall,0.5988,0.0098047885010856
882
- ≥4,14000,docvqa_val_anls,0.6230752215069362,0.006110772532320183
883
- ≥4,14000,infovqa_val_anls,0.23950752488444424,0.00673701613611272
884
- ≥4,14000,mme_total_score,693.2602040816327,
885
- ≥4,14000,mmmu_val_mmmu_acc,0.29,
886
- ≥4,14000,mmstar_average,0.3462132371031542,
887
- ≥4,14000,ocrbench_ocrbench_accuracy,0.492,
888
- ≥4,14000,seedbench_seed_all,0.519733185102835,
889
- ≥4,14000,textvqa_val_exact_match,0.52188,0.0067822601638824
890
- ≥4,15000,ai2d_exact_match,0.4536917098445596,0.008960474382205331
891
- ≥4,15000,average,0.4546421832173102,
892
- ≥4,15000,average_rank,3.5,
893
- ≥4,15000,chartqa_relaxed_overall,0.6012,0.0097949885513097
894
- ≥4,15000,docvqa_val_anls,0.6265798815467575,0.006118388682866076
895
- ≥4,15000,infovqa_val_anls,0.24253641235942872,0.006778846024017067
896
- ≥4,15000,mme_total_score,745.8826530612245,
897
- ≥4,15000,mmmu_val_mmmu_acc,0.28111,
898
- ≥4,15000,mmstar_average,0.3514223789460134,
899
- ≥4,15000,ocrbench_ocrbench_accuracy,0.493,
900
- ≥4,15000,seedbench_seed_all,0.5226792662590328,
901
- ≥4,15000,textvqa_val_exact_match,0.51956,0.006792518600768668
902
- ≥4,16000,ai2d_exact_match,0.4582253886010363,0.008967689939886603
903
- ≥4,16000,average,0.46307812033280477,
904
- ≥4,16000,average_rank,3.1,
905
- ≥4,16000,chartqa_relaxed_overall,0.6092,0.009760545645634788
906
- ≥4,16000,docvqa_val_anls,0.6397697311161549,0.006077931892063438
907
- ≥4,16000,infovqa_val_anls,0.2566929717899322,0.007049147355082826
908
- ≥4,16000,mme_total_score,769.8112244897959,
909
- ≥4,16000,mmmu_val_mmmu_acc,0.29,
910
- ≥4,16000,mmstar_average,0.3500855084419833,
911
- ≥4,16000,ocrbench_ocrbench_accuracy,0.512,
912
- ≥4,16000,seedbench_seed_all,0.5250694830461368,
913
- ≥4,16000,textvqa_val_exact_match,0.5266599999999999,0.006785297114451678
914
- ≥4,17000,ai2d_exact_match,0.46243523316062174,0.008973720555405783
915
- ≥4,17000,average,0.4637285100748874,
916
- ≥4,17000,average_rank,3.2,
917
- ≥4,17000,chartqa_relaxed_overall,0.6072,0.00976941352263433
918
- ≥4,17000,docvqa_val_anls,0.6316407990464801,0.006115829668357635
919
- ≥4,17000,infovqa_val_anls,0.26095289130380417,0.007179006033610968
920
- ≥4,17000,mme_total_score,772.2568027210884,
921
- ≥4,17000,mmmu_val_mmmu_acc,0.29222,
922
- ≥4,17000,mmstar_average,0.3487846654954876,
923
- ≥4,17000,ocrbench_ocrbench_accuracy,0.516,
924
- ≥4,17000,seedbench_seed_all,0.5254030016675931,
925
- ≥4,17000,textvqa_val_exact_match,0.52892,0.006777692390690844
926
- ≥4,18000,ai2d_exact_match,0.46729274611398963,0.00897987952745343
927
- ≥4,18000,average,0.46301237822364466,
928
- ≥4,18000,average_rank,3.5,
929
- ≥4,18000,chartqa_relaxed_overall,0.6024,0.009789996609470577
930
- ≥4,18000,docvqa_val_anls,0.6353229754668962,0.006102794809473289
931
- ≥4,18000,infovqa_val_anls,0.2566414572268362,0.006998597263140097
932
- ≥4,18000,mme_total_score,770.295918367347,
933
- ≥4,18000,mmmu_val_mmmu_acc,0.27778,
934
- ≥4,18000,mmstar_average,0.3522173046936848,
935
- ≥4,18000,ocrbench_ocrbench_accuracy,0.518,
936
- ≥4,18000,seedbench_seed_all,0.5224569205113953,
937
- ≥4,18000,textvqa_val_exact_match,0.535,0.006782934589123506
938
- ≥4,19000,ai2d_exact_match,0.4647020725388601,0.008976701230834869
939
- ≥4,19000,average,0.4657296959805982,
940
- ≥4,19000,average_rank,3.3,
941
- ≥4,19000,chartqa_relaxed_overall,0.6088,0.009762332982341016
942
- ≥4,19000,docvqa_val_anls,0.6386155506856869,0.006091782897731878
943
- ≥4,19000,infovqa_val_anls,0.2477875071753752,0.006879861435025137
944
- ≥4,19000,mme_total_score,772.204081632653,
945
- ≥4,19000,mmmu_val_mmmu_acc,0.30333,
946
- ≥4,19000,mmstar_average,0.3470027726694857,
947
- ≥4,19000,ocrbench_ocrbench_accuracy,0.512,
948
- ≥4,19000,seedbench_seed_all,0.5288493607559756,
949
- ≥4,19000,textvqa_val_exact_match,0.54048,0.006763536279536092
950
- ≥4,20000,ai2d_exact_match,0.4634067357512953,0.008975020819363737
951
- ≥4,20000,average,0.46162598712482705,
952
- ≥4,20000,average_rank,3.4,
953
- ≥4,20000,chartqa_relaxed_overall,0.61,0.009756950303844571
954
- ≥4,20000,docvqa_val_anls,0.6435026807424298,0.006070985460919362
955
- ≥4,20000,infovqa_val_anls,0.2543282868714285,0.006962743278022537
956
- ≥4,20000,mme_total_score,765.8690476190477,
957
- ≥4,20000,mmmu_val_mmmu_acc,0.27222,
958
- ≥4,20000,mmstar_average,0.34236379610014667,
959
- ≥4,20000,ocrbench_ocrbench_accuracy,0.509,
960
- ≥4,20000,seedbench_seed_all,0.5262923846581434,
961
- ≥4,20000,textvqa_val_exact_match,0.53352,0.006776464123213716
962
- ≥5,1000,ai2d_exact_match,0.24902849740932642,0.007783374690341817
963
- ≥5,1000,average,0.23561247048158757,
964
- ≥5,1000,average_rank,4.2,
965
- ≥5,1000,chartqa_relaxed_overall,0.2548,0.008716718216771047
966
- ≥5,1000,docvqa_val_anls,0.24096701334945672,0.004990683419188375
967
- ≥5,1000,infovqa_val_anls,0.12232054164836681,0.0051959928578510384
968
- ≥5,1000,mme_total_score,620.9336734693877,
969
- ≥5,1000,mmmu_val_mmmu_acc,0.23778,
970
- ≥5,1000,mmstar_average,0.26414819971479786,
971
- ≥5,1000,ocrbench_ocrbench_accuracy,0.216,
972
- ≥5,1000,seedbench_seed_all,0.2623679822123402,
973
- ≥5,1000,textvqa_val_exact_match,0.27310000000000006,0.0061250290771750005
974
- ≥5,2000,ai2d_exact_match,0.2344559585492228,0.007625132817591135
975
- ≥5,2000,average,0.2752283006434932,
976
- ≥5,2000,average_rank,4.2,
977
- ≥5,2000,chartqa_relaxed_overall,0.3732,0.009675026948726469
978
- ≥5,2000,docvqa_val_anls,0.331054267713041,0.005645142408620243
979
- ≥5,2000,infovqa_val_anls,0.1253737215538702,0.00524700917894423
980
- ≥5,2000,mme_total_score,678.2414965986395,
981
- ≥5,2000,mmmu_val_mmmu_acc,0.24,
982
- ≥5,2000,mmstar_average,0.24144442112149672,
983
- ≥5,2000,ocrbench_ocrbench_accuracy,0.264,
984
- ≥5,2000,seedbench_seed_all,0.33140633685380766,
985
- ≥5,2000,textvqa_val_exact_match,0.33612,0.006470505591414144
986
- ≥5,3000,ai2d_exact_match,0.22409326424870465,0.007505002611196186
987
- ≥5,3000,average,0.29997958942235364,
988
- ≥5,3000,average_rank,4.3,
989
- ≥5,3000,chartqa_relaxed_overall,0.392,0.00976588700628918
990
- ≥5,3000,docvqa_val_anls,0.37299390513630937,0.005683849773109756
991
- ≥5,3000,infovqa_val_anls,0.13605101039483827,0.005410567699808442
992
- ≥5,3000,mme_total_score,659.7210884353742,
993
- ≥5,3000,mmmu_val_mmmu_acc,0.27,
994
- ≥5,3000,mmstar_average,0.2682811266889234,
995
- ≥5,3000,ocrbench_ocrbench_accuracy,0.287,
996
- ≥5,3000,seedbench_seed_all,0.3745969983324069,
997
- ≥5,3000,textvqa_val_exact_match,0.3748,0.006628980364742018
998
- ≥5,4000,ai2d_exact_match,0.22733160621761658,0.007543244231635894
999
- ≥5,4000,average,0.3084813519082869,
1000
- ≥5,4000,average_rank,4.7,
1001
- ≥5,4000,chartqa_relaxed_overall,0.43,0.00990349593288537
1002
- ≥5,4000,docvqa_val_anls,0.4066720118815712,0.006028824654560211
1003
- ≥5,4000,infovqa_val_anls,0.14319025154556023,0.005617800071290847
1004
- ≥5,4000,mme_total_score,656.1462585034013,
1005
- ≥5,4000,mmmu_val_mmmu_acc,0.25667,
1006
- ≥5,4000,mmstar_average,0.2585945343280555,
1007
- ≥5,4000,ocrbench_ocrbench_accuracy,0.294,
1008
- ≥5,4000,seedbench_seed_all,0.39277376320177876,
1009
- ≥5,4000,textvqa_val_exact_match,0.3671,0.006592830278584186
1010
- ≥5,5000,ai2d_exact_match,0.24028497409326424,0.007689893942245019
1011
- ≥5,5000,average,0.3230129052623469,
1012
- ≥5,5000,average_rank,4.9,
1013
- ≥5,5000,chartqa_relaxed_overall,0.442,0.009934479228979264
1014
- ≥5,5000,docvqa_val_anls,0.43465518326761016,0.006092084287625314
1015
- ≥5,5000,infovqa_val_anls,0.16044569408280707,0.005985099003597859
1016
- ≥5,5000,mme_total_score,700.9234693877552,
1017
- ≥5,5000,mmmu_val_mmmu_acc,0.26,
1018
- ≥5,5000,mmstar_average,0.27948727201527235,
1019
- ≥5,5000,ocrbench_ocrbench_accuracy,0.309,
1020
- ≥5,5000,seedbench_seed_all,0.39744302390216785,
1021
- ≥5,5000,textvqa_val_exact_match,0.3838,0.006651041968883851
1022
- ≥5,6000,ai2d_exact_match,0.21761658031088082,0.007426556596739526
1023
- ≥5,6000,average,0.3285664644731758,
1024
- ≥5,6000,average_rank,4.8,
1025
- ≥5,6000,chartqa_relaxed_overall,0.4708,0.009984929820955767
1026
- ≥5,6000,docvqa_val_anls,0.4274906773084525,0.005930539560380286
1027
- ≥5,6000,infovqa_val_anls,0.15122815225662642,0.005687399721363878
1028
- ≥5,6000,mme_total_score,692.2227891156463,
1029
- ≥5,6000,mmmu_val_mmmu_acc,0.27,
1030
- ≥5,6000,mmstar_average,0.27596736182231085,
1031
- ≥5,6000,ocrbench_ocrbench_accuracy,0.341,
1032
- ≥5,6000,seedbench_seed_all,0.4237354085603113,
1033
- ≥5,6000,textvqa_val_exact_match,0.37926,0.006628782590470618
1034
- ≥5,7000,ai2d_exact_match,0.22959844559585493,0.007569631399592313
1035
- ≥5,7000,average,0.3397133831241853,
1036
- ≥5,7000,average_rank,5.0,
1037
- ≥5,7000,chartqa_relaxed_overall,0.4864,0.009998299975543861
1038
- ≥5,7000,docvqa_val_anls,0.4538685197224749,0.00598758370400633
1039
- ≥5,7000,infovqa_val_anls,0.15500462855057698,0.005842239614739797
1040
- ≥5,7000,mme_total_score,662.3809523809523,
1041
- ≥5,7000,mmmu_val_mmmu_acc,0.26444,
1042
- ≥5,7000,mmstar_average,0.2946102327923966,
1043
- ≥5,7000,ocrbench_ocrbench_accuracy,0.339,
1044
- ≥5,7000,seedbench_seed_all,0.43351862145636466,
1045
- ≥5,7000,textvqa_val_exact_match,0.40098,0.00668858395709213
1046
- ≥5,8000,ai2d_exact_match,0.26878238341968913,0.007979127569354613
1047
- ≥5,8000,average,0.3468669425903158,
1048
- ≥5,8000,average_rank,4.7,
1049
- ≥5,8000,chartqa_relaxed_overall,0.4644,0.009976616117083942
1050
- ≥5,8000,docvqa_val_anls,0.43320064291973065,0.005825461000081097
1051
- ≥5,8000,infovqa_val_anls,0.1525871677997588,0.0057380999639673955
1052
- ≥5,8000,mme_total_score,714.7789115646258,
1053
- ≥5,8000,mmmu_val_mmmu_acc,0.27667,
1054
- ≥5,8000,mmstar_average,0.3189178311414238,
1055
- ≥5,8000,ocrbench_ocrbench_accuracy,0.358,
1056
- ≥5,8000,seedbench_seed_all,0.4440244580322401,
1057
- ≥5,8000,textvqa_val_exact_match,0.40522,0.006705157876473132
1058
- ≥5,9000,ai2d_exact_match,0.23834196891191708,0.007668527149232641
1059
- ≥5,9000,average,0.34742834361066494,
1060
- ≥5,9000,average_rank,4.9,
1061
- ≥5,9000,chartqa_relaxed_overall,0.4832,0.009996353076494045
1062
- ≥5,9000,docvqa_val_anls,0.44997891177952337,0.005999690608407377
1063
- ≥5,9000,infovqa_val_anls,0.15249014258349003,0.005725765633377559
1064
- ≥5,9000,mme_total_score,696.5544217687075,
1065
- ≥5,9000,mmmu_val_mmmu_acc,0.26444,
1066
- ≥5,9000,mmstar_average,0.3019547640515156,
1067
- ≥5,9000,ocrbench_ocrbench_accuracy,0.384,
1068
- ≥5,9000,seedbench_seed_all,0.44874930516953865,
1069
- ≥5,9000,textvqa_val_exact_match,0.4037,0.006699928343494548
1070
- ≥5,10000,ai2d_exact_match,0.2979274611398964,0.008231480357867917
1071
- ≥5,10000,average,0.3538147252476138,
1072
- ≥5,10000,average_rank,4.8,
1073
- ≥5,10000,chartqa_relaxed_overall,0.48,0.009993995796516643
1074
- ≥5,10000,docvqa_val_anls,0.45125781190343667,0.0059273100312449535
1075
- ≥5,10000,infovqa_val_anls,0.15739085013451903,0.005776029267754871
1076
- ≥5,10000,mme_total_score,718.7227891156463,
1077
- ≥5,10000,mmmu_val_mmmu_acc,0.27556,
1078
- ≥5,10000,mmstar_average,0.3004387942674594,
1079
- ≥5,10000,ocrbench_ocrbench_accuracy,0.357,
1080
- ≥5,10000,seedbench_seed_all,0.4556976097832129,
1081
- ≥5,10000,textvqa_val_exact_match,0.40906000000000003,0.006714715240436636
1082
- ≥5,11000,ai2d_exact_match,0.3167098445595855,0.008372690712254882
1083
- ≥5,11000,average,0.36396020347184427,
1084
- ≥5,11000,average_rank,5.0,
1085
- ≥5,11000,chartqa_relaxed_overall,0.4924,0.010000845102345324
1086
- ≥5,11000,docvqa_val_anls,0.4691277601070516,0.0060867637597330085
1087
- ≥5,11000,infovqa_val_anls,0.15562897334070494,0.005768608804593679
1088
- ≥5,11000,mme_total_score,680.7667066826731,
1089
- ≥5,11000,mmmu_val_mmmu_acc,0.27667,
1090
- ≥5,11000,mmstar_average,0.3111702671358657,
1091
- ≥5,11000,ocrbench_ocrbench_accuracy,0.388,
1092
- ≥5,11000,seedbench_seed_all,0.45497498610339077,
1093
- ≥5,11000,textvqa_val_exact_match,0.41096000000000005,0.006715250896200365
1094
- ≥5,12000,ai2d_exact_match,0.24838082901554404,0.007776597937116943
1095
- ≥5,12000,average,0.35400963042471534,
1096
- ≥5,12000,average_rank,4.9,
1097
- ≥5,12000,chartqa_relaxed_overall,0.4624,0.00997367964766694
1098
- ≥5,12000,docvqa_val_anls,0.46480289866811825,0.005910238300168798
1099
- ≥5,12000,infovqa_val_anls,0.15657154481637633,0.0057842205757870115
1100
- ≥5,12000,mme_total_score,742.4894957983194,
1101
- ≥5,12000,mmmu_val_mmmu_acc,0.28444,
1102
- ≥5,12000,mmstar_average,0.30237252416842486,
1103
- ≥5,12000,ocrbench_ocrbench_accuracy,0.391,
1104
- ≥5,12000,seedbench_seed_all,0.46197887715397445,
1105
- ≥5,12000,textvqa_val_exact_match,0.41414000000000006,0.0067237975855013775
1106
- ≥5,13000,ai2d_exact_match,0.27266839378238344,0.008015217564479081
1107
- ≥5,13000,average,0.3605408154099655,
1108
- ≥5,13000,average_rank,4.9,
1109
- ≥5,13000,chartqa_relaxed_overall,0.4796,0.00999367226769808
1110
- ≥5,13000,docvqa_val_anls,0.4888368998254502,0.006080092164054846
1111
- ≥5,13000,infovqa_val_anls,0.1685412928680358,0.006153102666352037
1112
- ≥5,13000,mme_total_score,715.9022609043617,
1113
- ≥5,13000,mmmu_val_mmmu_acc,0.27,
1114
- ≥5,13000,mmstar_average,0.30550310907874534,
1115
- ≥5,13000,ocrbench_ocrbench_accuracy,0.39,
1116
- ≥5,13000,seedbench_seed_all,0.46375764313507506,
1117
- ≥5,13000,textvqa_val_exact_match,0.40596000000000004,0.006708225975557757
1118
- ≥5,14000,ai2d_exact_match,0.27266839378238344,0.008015217564479094
1119
- ≥5,14000,average,0.35876061642606916,
1120
- ≥5,14000,average_rank,4.9,
1121
- ≥5,14000,chartqa_relaxed_overall,0.4832,0.009996353076494045
1122
- ≥5,14000,docvqa_val_anls,0.4686745608937551,0.005954780465596843
1123
- ≥5,14000,infovqa_val_anls,0.16026985404926572,0.00587737555538511
1124
- ≥5,14000,mme_total_score,694.7702080832332,
1125
- ≥5,14000,mmmu_val_mmmu_acc,0.27778,
1126
- ≥5,14000,mmstar_average,0.3065739842454048,
1127
- ≥5,14000,ocrbench_ocrbench_accuracy,0.388,
1128
- ≥5,14000,seedbench_seed_all,0.46575875486381324,
1129
- ≥5,14000,textvqa_val_exact_match,0.40592,0.006717590038338499
1130
- ≥5,15000,ai2d_exact_match,0.26295336787564766,0.007923526907377253
1131
- ≥5,15000,average,0.3594508046372947,
1132
- ≥5,15000,average_rank,4.9,
1133
- ≥5,15000,chartqa_relaxed_overall,0.4904,0.010000156861514821
1134
- ≥5,15000,docvqa_val_anls,0.47702085294845603,0.006014469495902542
1135
- ≥5,15000,infovqa_val_anls,0.1709556715444569,0.006117350998294382
1136
- ≥5,15000,mme_total_score,748.1163465386154,
1137
- ≥5,15000,mmmu_val_mmmu_acc,0.25667,
1138
- ≥5,15000,mmstar_average,0.2990729469212882,
1139
- ≥5,15000,ocrbench_ocrbench_accuracy,0.404,
1140
- ≥5,15000,seedbench_seed_all,0.46392440244580324,
1141
- ≥5,15000,textvqa_val_exact_match,0.4100599999999999,0.0067243737790625615
1142
- ≥5,16000,ai2d_exact_match,0.28950777202072536,0.00816284339533906
1143
- ≥5,16000,average,0.3652803192394071,
1144
- ≥5,16000,average_rank,4.9,
1145
- ≥5,16000,chartqa_relaxed_overall,0.5004,0.010001997399559365
1146
- ≥5,16000,docvqa_val_anls,0.4789319968433556,0.005936381904079473
1147
- ≥5,16000,infovqa_val_anls,0.16818261112655605,0.006062058685336811
1148
- ≥5,16000,mme_total_score,703.8838535414166,
1149
- ≥5,16000,mmmu_val_mmmu_acc,0.28111,
1150
- ≥5,16000,mmstar_average,0.30021933140749574,
1151
- ≥5,16000,ocrbench_ocrbench_accuracy,0.392,
1152
- ≥5,16000,seedbench_seed_all,0.4640911617565314,
1153
- ≥5,16000,textvqa_val_exact_match,0.41308,0.006723304491442948
1154
- ≥5,17000,ai2d_exact_match,0.28335492227979275,0.008110527983566212
1155
- ≥5,17000,average,0.36065417779712866,
1156
- ≥5,17000,average_rank,5.0,
1157
- ≥5,17000,chartqa_relaxed_overall,0.4688,0.009982508912777261
1158
- ≥5,17000,docvqa_val_anls,0.4676527518642357,0.00590362287731878
1159
- ≥5,17000,infovqa_val_anls,0.16818540516392913,0.00605571000794457
1160
- ≥5,17000,mme_total_score,754.0354141656662,
1161
- ≥5,17000,mmmu_val_mmmu_acc,0.26222,
1162
- ≥5,17000,mmstar_average,0.31626391497403816,
1163
- ≥5,17000,ocrbench_ocrbench_accuracy,0.404,
1164
- ≥5,17000,seedbench_seed_all,0.46309060589216233,
1165
- ≥5,17000,textvqa_val_exact_match,0.41231999999999996,0.006722044383678169
1166
- ≥5,18000,ai2d_exact_match,0.2911269430051813,0.00817630569100236
1167
- ≥5,18000,average,0.3642489832139911,
1168
- ≥5,18000,average_rank,4.9,
1169
- ≥5,18000,chartqa_relaxed_overall,0.488,0.009999119609104738
1170
- ≥5,18000,docvqa_val_anls,0.4852288069276555,0.006044640681137398
1171
- ≥5,18000,infovqa_val_anls,0.1659765406298008,0.006009331694189444
1172
- ≥5,18000,mme_total_score,748.4861944777911,
1173
- ≥5,18000,mmmu_val_mmmu_acc,0.28111,
1174
- ≥5,18000,mmstar_average,0.3014618713149217,
1175
- ≥5,18000,ocrbench_ocrbench_accuracy,0.389,
1176
- ≥5,18000,seedbench_seed_all,0.4660366870483602,
1177
- ≥5,18000,textvqa_val_exact_match,0.4103,0.0067180509406887
1178
- ≥5,19000,ai2d_exact_match,0.2817357512953368,0.008096452844781159
1179
- ≥5,19000,average,0.35871512802442374,
1180
- ≥5,19000,average_rank,4.7,
1181
- ≥5,19000,chartqa_relaxed_overall,0.452,0.009955804699716018
1182
- ≥5,19000,docvqa_val_anls,0.4693437417424619,0.005945802716190409
1183
- ≥5,19000,infovqa_val_anls,0.17352672765291935,0.006108049035774969
1184
- ≥5,19000,mme_total_score,757.4390756302521,
1185
- ≥5,19000,mmmu_val_mmmu_acc,0.29556,
1186
- ≥5,19000,mmstar_average,0.299605929305638,
1187
- ≥5,19000,ocrbench_ocrbench_accuracy,0.382,
1188
- ≥5,19000,seedbench_seed_all,0.4672040022234575,
1189
- ≥5,19000,textvqa_val_exact_match,0.40746,0.006711235192985202
1190
- ≥5,20000,ai2d_exact_match,0.28950777202072536,0.008162843395339051
1191
- ≥5,20000,average,0.3571101844602158,
1192
- ≥5,20000,average_rank,5.0,
1193
- ≥5,20000,chartqa_relaxed_overall,0.452,0.009955804699716018
1194
- ≥5,20000,docvqa_val_anls,0.4781541164812954,0.006040598891772297
1195
- ≥5,20000,infovqa_val_anls,0.16871824680773087,0.00599943702354704
1196
- ≥5,20000,mme_total_score,713.3514405762305,
1197
- ≥5,20000,mmmu_val_mmmu_acc,0.26667,
1198
- ≥5,20000,mmstar_average,0.30644375940695473,
1199
- ≥5,20000,ocrbench_ocrbench_accuracy,0.398,
1200
- ≥5,20000,seedbench_seed_all,0.4599777654252362,
1201
- ≥5,20000,textvqa_val_exact_match,0.39452000000000004,0.006680937127692554
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a47d8de2edf309fd39eb7e2ef5790d7f9c3ec4d5cc0f0c8680c12112f0d63e3
3
+ size 63287
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/content/assets/data/formatting_filters.csv CHANGED
@@ -1,1201 +1,3 @@
1
- run,step,metric,value,stderr
2
- Baseline,1000,ai2d_exact_match,0.2548575129533679,0.007843322436924496
3
- Baseline,1000,average,0.27120689295763617,
4
- Baseline,1000,average_rank,3.8,
5
- Baseline,1000,chartqa_relaxed_overall,0.3308,0.009411906161401973
6
- Baseline,1000,docvqa_val_anls,0.3528553494243383,0.005852289239342309
7
- Baseline,1000,infovqa_val_anls,0.17320578642581314,0.006297063452679795
8
- Baseline,1000,mme_total_score,977.4280712284914,
9
- Baseline,1000,mmmu_val_mmmu_acc,0.25222,
10
- Baseline,1000,mmstar_average,0.23215874078908072,
11
- Baseline,1000,ocrbench_ocrbench_accuracy,0.286,
12
- Baseline,1000,seedbench_seed_all,0.2563646470261256,
13
- Baseline,1000,textvqa_val_exact_match,0.3024,0.00628900296642181
14
- Baseline,2000,ai2d_exact_match,0.26295336787564766,0.007923526907377255
15
- Baseline,2000,average,0.3202068275596269,
16
- Baseline,2000,average_rank,3.7,
17
- Baseline,2000,chartqa_relaxed_overall,0.4688,0.009982508912777261
18
- Baseline,2000,docvqa_val_anls,0.4452261510942785,0.00614755494712251
19
- Baseline,2000,infovqa_val_anls,0.1820547866557169,0.006217861455795791
20
- Baseline,2000,mme_total_score,1049.3036214485794,
21
- Baseline,2000,mmmu_val_mmmu_acc,0.24556,
22
- Baseline,2000,mmstar_average,0.21305462434540698,
23
- Baseline,2000,ocrbench_ocrbench_accuracy,0.395,
24
- Baseline,2000,seedbench_seed_all,0.258532518065592,
25
- Baseline,2000,textvqa_val_exact_match,0.41068000000000005,0.006697862330024289
26
- Baseline,3000,ai2d_exact_match,0.25226683937823835,0.007816909588794397
27
- Baseline,3000,average,0.3507423834414229,
28
- Baseline,3000,average_rank,2.6,
29
- Baseline,3000,chartqa_relaxed_overall,0.5028,0.010001843767601082
30
- Baseline,3000,docvqa_val_anls,0.502653993831009,0.006267072346683124
31
- Baseline,3000,infovqa_val_anls,0.21728617578189535,0.006796941784959762
32
- Baseline,3000,mme_total_score,1170.2383953581434,
33
- Baseline,3000,mmmu_val_mmmu_acc,0.27556,
34
- Baseline,3000,mmstar_average,0.25432376938577683,
35
- Baseline,3000,ocrbench_ocrbench_accuracy,0.436,
36
- Baseline,3000,seedbench_seed_all,0.2792106725958866,
37
- Baseline,3000,textvqa_val_exact_match,0.43658,0.006766885462882726
38
- Baseline,4000,ai2d_exact_match,0.2645725388601036,0.007939149662089447
39
- Baseline,4000,average,0.36961781722974835,
40
- Baseline,4000,average_rank,2.8,
41
- Baseline,4000,chartqa_relaxed_overall,0.5312,0.009982508912777261
42
- Baseline,4000,docvqa_val_anls,0.5374434618615119,0.0062905728113059655
43
- Baseline,4000,infovqa_val_anls,0.2287924838861707,0.006994568698639919
44
- Baseline,4000,mme_total_score,1155.203781512605,
45
- Baseline,4000,mmmu_val_mmmu_acc,0.25556,
46
- Baseline,4000,mmstar_average,0.2575590188757354,
47
- Baseline,4000,ocrbench_ocrbench_accuracy,0.453,
48
- Baseline,4000,seedbench_seed_all,0.33913285158421347,
49
- Baseline,4000,textvqa_val_exact_match,0.4593,0.006791695475025738
50
- Baseline,5000,ai2d_exact_match,0.3125,0.008342439145556371
51
- Baseline,5000,average,0.3974627910380972,
52
- Baseline,5000,average_rank,3.1,
53
- Baseline,5000,chartqa_relaxed_overall,0.5488,0.00995424828018316
54
- Baseline,5000,docvqa_val_anls,0.552360266782429,0.006300308519952055
55
- Baseline,5000,infovqa_val_anls,0.23425555286643698,0.007002254622066442
56
- Baseline,5000,mme_total_score,1181.4653861544618,
57
- Baseline,5000,mmmu_val_mmmu_acc,0.26667,
58
- Baseline,5000,mmstar_average,0.29596648146165705,
59
- Baseline,5000,ocrbench_ocrbench_accuracy,0.462,
60
- Baseline,5000,seedbench_seed_all,0.43107281823235133,
61
- Baseline,5000,textvqa_val_exact_match,0.47354000000000007,0.0068172185364497985
62
- Baseline,6000,ai2d_exact_match,0.358160621761658,0.008629463221867162
63
- Baseline,6000,average,0.4161227404571003,
64
- Baseline,6000,average_rank,2.3,
65
- Baseline,6000,chartqa_relaxed_overall,0.5628,0.00992279440175477
66
- Baseline,6000,docvqa_val_anls,0.5747451497228876,0.00625495440870239
67
- Baseline,6000,infovqa_val_anls,0.22152017368968838,0.006604546680525351
68
- Baseline,6000,mme_total_score,1284.1648659463785,
69
- Baseline,6000,mmmu_val_mmmu_acc,0.27111,
70
- Baseline,6000,mmstar_average,0.2978489412854164,
71
- Baseline,6000,ocrbench_ocrbench_accuracy,0.495,
72
- Baseline,6000,seedbench_seed_all,0.4795997776542524,
73
- Baseline,6000,textvqa_val_exact_match,0.48432,0.006800535050670284
74
- Baseline,7000,ai2d_exact_match,0.3707901554404145,0.00869347755587734
75
- Baseline,7000,average,0.4291083177345374,
76
- Baseline,7000,average_rank,2.6,
77
- Baseline,7000,chartqa_relaxed_overall,0.5656,0.009915542506251351
78
- Baseline,7000,docvqa_val_anls,0.5940907049431567,0.006224236305767187
79
- Baseline,7000,infovqa_val_anls,0.2515675215816963,0.007105097396092786
80
- Baseline,7000,mme_total_score,1185.875650260104,
81
- Baseline,7000,mmmu_val_mmmu_acc,0.26556,
82
- Baseline,7000,mmstar_average,0.31372400960777047,
83
- Baseline,7000,ocrbench_ocrbench_accuracy,0.504,
84
- Baseline,7000,seedbench_seed_all,0.4964424680377988,
85
- Baseline,7000,textvqa_val_exact_match,0.5002,0.006794794025220267
86
- Baseline,8000,ai2d_exact_match,0.37759067357512954,0.008725299846043883
87
- Baseline,8000,average,0.43846759477995995,
88
- Baseline,8000,average_rank,2.1,
89
- Baseline,8000,chartqa_relaxed_overall,0.5832,0.009862556058385773
90
- Baseline,8000,docvqa_val_anls,0.6017336419437208,0.006231612198089698
91
- Baseline,8000,infovqa_val_anls,0.2449256624147254,0.006992518502948913
92
- Baseline,8000,mme_total_score,1199.2409963985594,
93
- Baseline,8000,mmmu_val_mmmu_acc,0.28111,
94
- Baseline,8000,mmstar_average,0.33512257186205047,
95
- Baseline,8000,ocrbench_ocrbench_accuracy,0.51,
96
- Baseline,8000,seedbench_seed_all,0.5024458032240133,
97
- Baseline,8000,textvqa_val_exact_match,0.51008,0.006796301690135059
98
- Baseline,9000,ai2d_exact_match,0.4067357512953368,0.008841214921078996
99
- Baseline,9000,average,0.4422510732201056,
100
- Baseline,9000,average_rank,2.1,
101
- Baseline,9000,chartqa_relaxed_overall,0.5912,0.009834211136815875
102
- Baseline,9000,docvqa_val_anls,0.6170968481662739,0.00617235763542544
103
- Baseline,9000,infovqa_val_anls,0.23537031288570615,0.00670318154156447
104
- Baseline,9000,mme_total_score,1231.5195078031213,
105
- Baseline,9000,mmmu_val_mmmu_acc,0.25889,
106
- Baseline,9000,mmstar_average,0.3216444898242951,
107
- Baseline,9000,ocrbench_ocrbench_accuracy,0.515,
108
- Baseline,9000,seedbench_seed_all,0.5120622568093385,
109
- Baseline,9000,textvqa_val_exact_match,0.52226,0.006792711289708482
110
- Baseline,10000,ai2d_exact_match,0.39993523316062174,0.008817096257082848
111
- Baseline,10000,average,0.4523875703250908,
112
- Baseline,10000,average_rank,2.4,
113
- Baseline,10000,chartqa_relaxed_overall,0.5996,0.00980154906867574
114
- Baseline,10000,docvqa_val_anls,0.6262613496433054,0.006147756371688175
115
- Baseline,10000,infovqa_val_anls,0.263290074230132,0.007186788766942786
116
- Baseline,10000,mme_total_score,1240.8218287314926,
117
- Baseline,10000,mmmu_val_mmmu_acc,0.28778,
118
- Baseline,10000,mmstar_average,0.32972717906018517,
119
- Baseline,10000,ocrbench_ocrbench_accuracy,0.517,
120
- Baseline,10000,seedbench_seed_all,0.5217342968315731,
121
- Baseline,10000,textvqa_val_exact_match,0.5261600000000001,0.006785774843600811
122
- Baseline,11000,ai2d_exact_match,0.422279792746114,0.008889771831066474
123
- Baseline,11000,average,0.4561398159525099,
124
- Baseline,11000,average_rank,2.1,
125
- Baseline,11000,chartqa_relaxed_overall,0.6104,0.009755142291143075
126
- Baseline,11000,docvqa_val_anls,0.6373130149166712,0.006128022584995044
127
- Baseline,11000,infovqa_val_anls,0.24419378339723755,0.006897644885887063
128
- Baseline,11000,mme_total_score,1322.9488795518205,
129
- Baseline,11000,mmmu_val_mmmu_acc,0.27778,
130
- Baseline,11000,mmstar_average,0.3298563439522548,
131
- Baseline,11000,ocrbench_ocrbench_accuracy,0.521,
132
- Baseline,11000,seedbench_seed_all,0.5237354085603113,
133
- Baseline,11000,textvqa_val_exact_match,0.5387,0.006770851562852138
134
- Baseline,12000,ai2d_exact_match,0.42001295336787564,0.008883255931688034
135
- Baseline,12000,average,0.4582751140055433,
136
- Baseline,12000,average_rank,2.4,
137
- Baseline,12000,chartqa_relaxed_overall,0.618,0.009719474639861454
138
- Baseline,12000,docvqa_val_anls,0.6393961983751871,0.0061228747388476674
139
- Baseline,12000,infovqa_val_anls,0.24798874058574302,0.006855374548993139
140
- Baseline,12000,mme_total_score,1225.6453581432572,
141
- Baseline,12000,mmmu_val_mmmu_acc,0.27889,
142
- Baseline,12000,mmstar_average,0.34010867846816534,
143
- Baseline,12000,ocrbench_ocrbench_accuracy,0.512,
144
- Baseline,12000,seedbench_seed_all,0.5350194552529183,
145
- Baseline,12000,textvqa_val_exact_match,0.5330600000000001,0.006777713092109446
146
- Baseline,13000,ai2d_exact_match,0.4375,0.008928571428571428
147
- Baseline,13000,average,0.4692868662590049,
148
- Baseline,13000,average_rank,1.6,
149
- Baseline,13000,chartqa_relaxed_overall,0.6148,0.00973479791861169
150
- Baseline,13000,docvqa_val_anls,0.6511374872549951,0.006086953065248391
151
- Baseline,13000,infovqa_val_anls,0.24465055100441893,0.006808432538374664
152
- Baseline,13000,mme_total_score,1281.7122849139657,
153
- Baseline,13000,mmmu_val_mmmu_acc,0.28222,
154
- Baseline,13000,mmstar_average,0.3453069542917521,
155
- Baseline,13000,ocrbench_ocrbench_accuracy,0.549,
156
- Baseline,13000,seedbench_seed_all,0.5442468037798777,
157
- Baseline,13000,textvqa_val_exact_match,0.55472,0.0067416788982325
158
- Baseline,14000,ai2d_exact_match,0.4572538860103627,0.00896620675297095
159
- Baseline,14000,average,0.47352486841689195,
160
- Baseline,14000,average_rank,1.7,
161
- Baseline,14000,chartqa_relaxed_overall,0.6172,0.009723347231923635
162
- Baseline,14000,docvqa_val_anls,0.6502269393708169,0.006057950730638126
163
- Baseline,14000,infovqa_val_anls,0.25805460837190913,0.007037735231659539
164
- Baseline,14000,mme_total_score,1309.1444577831132,
165
- Baseline,14000,mmmu_val_mmmu_acc,0.28111,
166
- Baseline,14000,mmstar_average,0.34575818188776586,
167
- Baseline,14000,ocrbench_ocrbench_accuracy,0.551,
168
- Baseline,14000,seedbench_seed_all,0.5483602001111729,
169
- Baseline,14000,textvqa_val_exact_match,0.55276,0.006751206724612103
170
- Baseline,15000,ai2d_exact_match,0.45045336787564766,0.008954861634252399
171
- Baseline,15000,average,0.47878665012878824,
172
- Baseline,15000,average_rank,1.6,
173
- Baseline,15000,chartqa_relaxed_overall,0.612,0.009747841205275417
174
- Baseline,15000,docvqa_val_anls,0.6621413031955148,0.006056838050222495
175
- Baseline,15000,infovqa_val_anls,0.2706898598157733,0.007200315730154543
176
- Baseline,15000,mme_total_score,1384.2171868747498,
177
- Baseline,15000,mmmu_val_mmmu_acc,0.30222,
178
- Baseline,15000,mmstar_average,0.35408135695920684,
179
- Baseline,15000,ocrbench_ocrbench_accuracy,0.558,
180
- Baseline,15000,seedbench_seed_all,0.5411339633129516,
181
- Baseline,15000,textvqa_val_exact_match,0.5583600000000001,0.0067279027203879065
182
- Baseline,16000,ai2d_exact_match,0.45077720207253885,0.008955440137395838
183
- Baseline,16000,average,0.47665128022935843,
184
- Baseline,16000,average_rank,1.6,
185
- Baseline,16000,chartqa_relaxed_overall,0.632,0.00964715642305132
186
- Baseline,16000,docvqa_val_anls,0.6709415729142987,0.005999818105621502
187
- Baseline,16000,infovqa_val_anls,0.26050032542402035,0.006997451875879188
188
- Baseline,16000,mme_total_score,1317.8491396558625,
189
- Baseline,16000,mmmu_val_mmmu_acc,0.27556,
190
- Baseline,16000,mmstar_average,0.33214333327093315,
191
- Baseline,16000,ocrbench_ocrbench_accuracy,0.56,
192
- Baseline,16000,seedbench_seed_all,0.5463590883824346,
193
- Baseline,16000,textvqa_val_exact_match,0.56158,0.006723854754867398
194
- Baseline,17000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
195
- Baseline,17000,average,0.4777141780162423,
196
- Baseline,17000,average_rank,1.9,
197
- Baseline,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
198
- Baseline,17000,docvqa_val_anls,0.6796338519136422,0.005948761388267941
199
- Baseline,17000,infovqa_val_anls,0.28070956072505215,0.007298333094144192
200
- Baseline,17000,mme_total_score,1381.9161664665867,
201
- Baseline,17000,mmmu_val_mmmu_acc,0.27667,
202
- Baseline,17000,mmstar_average,0.3370289492329521,
203
- Baseline,17000,ocrbench_ocrbench_accuracy,0.519,
204
- Baseline,17000,seedbench_seed_all,0.5510283490828238,
205
- Baseline,17000,textvqa_val_exact_match,0.56416,0.006724830373229479
206
- Baseline,18000,ai2d_exact_match,0.46567357512953367,0.008977921602780726
207
- Baseline,18000,average,0.4819834595278701,
208
- Baseline,18000,average_rank,1.7,
209
- Baseline,18000,chartqa_relaxed_overall,0.6376,0.009615793331418735
210
- Baseline,18000,docvqa_val_anls,0.6775884603912571,0.005972234236435759
211
- Baseline,18000,infovqa_val_anls,0.27154318420389256,0.007164903131667027
212
- Baseline,18000,mme_total_score,1336.922769107643,
213
- Baseline,18000,mmmu_val_mmmu_acc,0.28667,
214
- Baseline,18000,mmstar_average,0.34482796716566916,
215
- Baseline,18000,ocrbench_ocrbench_accuracy,0.533,
216
- Baseline,18000,seedbench_seed_all,0.5543079488604781,
217
- Baseline,18000,textvqa_val_exact_match,0.5666399999999999,0.006713392287599574
218
- Baseline,19000,ai2d_exact_match,0.4682642487046632,0.008981008686994101
219
- Baseline,19000,average,0.4899006713916878,
220
- Baseline,19000,average_rank,1.5,
221
- Baseline,19000,chartqa_relaxed_overall,0.6444,0.009575809858898698
222
- Baseline,19000,docvqa_val_anls,0.678226526479947,0.005970619221588814
223
- Baseline,19000,infovqa_val_anls,0.26993847247278,0.0071348470764911525
224
- Baseline,19000,mme_total_score,1406.6628651460583,
225
- Baseline,19000,mmmu_val_mmmu_acc,0.28333,
226
- Baseline,19000,mmstar_average,0.356220913822775,
227
- Baseline,19000,ocrbench_ocrbench_accuracy,0.577,
228
- Baseline,19000,seedbench_seed_all,0.554585881045025,
229
- Baseline,19000,textvqa_val_exact_match,0.57714,0.0066918487914812905
230
- Baseline,20000,ai2d_exact_match,0.47571243523316065,0.00898853090258662
231
- Baseline,20000,average,0.4873169067639118,
232
- Baseline,20000,average_rank,1.7,
233
- Baseline,20000,chartqa_relaxed_overall,0.6336,0.009638338810708618
234
- Baseline,20000,docvqa_val_anls,0.6895214454380043,0.005896462073053767
235
- Baseline,20000,infovqa_val_anls,0.2655657550458317,0.007033265532032538
236
- Baseline,20000,mme_total_score,1324.6738695478193,
237
- Baseline,20000,mmmu_val_mmmu_acc,0.30111,
238
- Baseline,20000,mmstar_average,0.33806766134497995,
239
- Baseline,20000,ocrbench_ocrbench_accuracy,0.555,
240
- Baseline,20000,seedbench_seed_all,0.5587548638132296,
241
- Baseline,20000,textvqa_val_exact_match,0.56852,0.006720151338087659
242
- ≥2,1000,ai2d_exact_match,0.2619818652849741,0.007914086941902845
243
- ≥2,1000,average,0.2852885776543714,
244
- ≥2,1000,average_rank,2.8,
245
- ≥2,1000,chartqa_relaxed_overall,0.36,0.009601920576192066
246
- ≥2,1000,docvqa_val_anls,0.3691495236959511,0.0059102400877721764
247
- ≥2,1000,infovqa_val_anls,0.18005913830944342,0.006300821228003093
248
- ≥2,1000,mme_total_score,1034.4992997198879,
249
- ≥2,1000,mmmu_val_mmmu_acc,0.25222,
250
- ≥2,1000,mmstar_average,0.20333316409480473,
251
- ≥2,1000,ocrbench_ocrbench_accuracy,0.331,
252
- ≥2,1000,seedbench_seed_all,0.264313507504169,
253
- ≥2,1000,textvqa_val_exact_match,0.34554,0.006483180392801138
254
- ≥2,2000,ai2d_exact_match,0.25971502590673573,0.007891865786132407
255
- ≥2,2000,average,0.3309474525195546,
256
- ≥2,2000,average_rank,2.3,
257
- ≥2,2000,chartqa_relaxed_overall,0.4664,0.009979391329160321
258
- ≥2,2000,docvqa_val_anls,0.44591152951098784,0.006197056264354256
259
- ≥2,2000,infovqa_val_anls,0.20775747304541303,0.006645281501282388
260
- ≥2,2000,mme_total_score,1083.1982793117247,
261
- ≥2,2000,mmmu_val_mmmu_acc,0.26222,
262
- ≥2,2000,mmstar_average,0.23515873070535015,
263
- ≥2,2000,ocrbench_ocrbench_accuracy,0.413,
264
- ≥2,2000,seedbench_seed_all,0.2757643135075042,
265
- ≥2,2000,textvqa_val_exact_match,0.4126,0.006707581257746032
266
- ≥2,3000,ai2d_exact_match,0.27299222797927464,0.00801819019286542
267
- ≥2,3000,average,0.35386512749374127,
268
- ≥2,3000,average_rank,1.8,
269
- ≥2,3000,chartqa_relaxed_overall,0.5124,0.009998924311892653
270
- ≥2,3000,docvqa_val_anls,0.48910828732243933,0.006274136020264289
271
- ≥2,3000,infovqa_val_anls,0.2070472808493129,0.0065577848697521875
272
- ≥2,3000,mme_total_score,1128.4556822729091,
273
- ≥2,3000,mmmu_val_mmmu_acc,0.25222,
274
- ≥2,3000,mmstar_average,0.25601322622316125,
275
- ≥2,3000,ocrbench_ocrbench_accuracy,0.447,
276
- ≥2,3000,seedbench_seed_all,0.30522512506948307,
277
- ≥2,3000,textvqa_val_exact_match,0.44278,0.006763750733490772
278
- ≥2,4000,ai2d_exact_match,0.3173575129533679,0.008377274276497445
279
- ≥2,4000,average,0.3859767914191833,
280
- ≥2,4000,average_rank,2.4,
281
- ≥2,4000,chartqa_relaxed_overall,0.5388,0.0099718403035556
282
- ≥2,4000,docvqa_val_anls,0.5360750144064242,0.006293888693576319
283
- ≥2,4000,infovqa_val_anls,0.20188347210673038,0.0064101781168258935
284
- ≥2,4000,mme_total_score,1110.1481592637056,
285
- ≥2,4000,mmmu_val_mmmu_acc,0.25222,
286
- ≥2,4000,mmstar_average,0.28905163247788923,
287
- ≥2,4000,ocrbench_ocrbench_accuracy,0.473,
288
- ≥2,4000,seedbench_seed_all,0.4102834908282379,
289
- ≥2,4000,textvqa_val_exact_match,0.4551200000000001,0.0067829756649846785
290
- ≥2,5000,ai2d_exact_match,0.32577720207253885,0.008435168191407938
291
- ≥2,5000,average,0.4029564015858402,
292
- ≥2,5000,average_rank,2.5,
293
- ≥2,5000,chartqa_relaxed_overall,0.5628,0.00992279440175477
294
- ≥2,5000,docvqa_val_anls,0.548770508666009,0.006315482288099859
295
- ≥2,5000,infovqa_val_anls,0.20783386531525747,0.006421967027729742
296
- ≥2,5000,mme_total_score,1206.0127050820329,
297
- ≥2,5000,mmmu_val_mmmu_acc,0.25667,
298
- ≥2,5000,mmstar_average,0.3210115801865161,
299
- ≥2,5000,ocrbench_ocrbench_accuracy,0.484,
300
- ≥2,5000,seedbench_seed_all,0.4440244580322401,
301
- ≥2,5000,textvqa_val_exact_match,0.47572,0.006783457774606987
302
- ≥2,6000,ai2d_exact_match,0.3542746113989637,0.00860846328571982
303
- ≥2,6000,average,0.4118759304334577,
304
- ≥2,6000,average_rank,3.3,
305
- ≥2,6000,chartqa_relaxed_overall,0.5644,0.00991868984106597
306
- ≥2,6000,docvqa_val_anls,0.5618652265799138,0.006261889040657647
307
- ≥2,6000,infovqa_val_anls,0.2101901707833487,0.006387610514125727
308
- ≥2,6000,mme_total_score,1135.471288515406,
309
- ≥2,6000,mmmu_val_mmmu_acc,0.26333,
310
- ≥2,6000,mmstar_average,0.3255666447386709,
311
- ≥2,6000,ocrbench_ocrbench_accuracy,0.482,
312
- ≥2,6000,seedbench_seed_all,0.4740967204002223,
313
- ≥2,6000,textvqa_val_exact_match,0.47116,0.00678908456375694
314
- ≥2,7000,ai2d_exact_match,0.37338082901554404,0.008705816961084268
315
- ≥2,7000,average,0.4291995483001856,
316
- ≥2,7000,average_rank,2.4,
317
- ≥2,7000,chartqa_relaxed_overall,0.5716,0.009898917689756362
318
- ≥2,7000,docvqa_val_anls,0.5846126379804475,0.006218823793449337
319
- ≥2,7000,infovqa_val_anls,0.2243908724169204,0.006651785538916188
320
- ≥2,7000,mme_total_score,1249.9180672268908,
321
- ≥2,7000,mmmu_val_mmmu_acc,0.27556,
322
- ≥2,7000,mmstar_average,0.32644844909642934,
323
- ≥2,7000,ocrbench_ocrbench_accuracy,0.506,
324
- ≥2,7000,seedbench_seed_all,0.4936631461923291,
325
- ≥2,7000,textvqa_val_exact_match,0.5071399999999999,0.00678246300696791
326
- ≥2,8000,ai2d_exact_match,0.3963730569948187,0.008803757198545703
327
- ≥2,8000,average,0.43448504857720643,
328
- ≥2,8000,average_rank,3.0,
329
- ≥2,8000,chartqa_relaxed_overall,0.5784,0.009878279615563902
330
- ≥2,8000,docvqa_val_anls,0.5935884981677085,0.006228109848938283
331
- ≥2,8000,infovqa_val_anls,0.22034669568379356,0.006538842004996925
332
- ≥2,8000,mme_total_score,1251.6327531012405,
333
- ≥2,8000,mmmu_val_mmmu_acc,0.27444,
334
- ≥2,8000,mmstar_average,0.3368503047476477,
335
- ≥2,8000,ocrbench_ocrbench_accuracy,0.516,
336
- ≥2,8000,seedbench_seed_all,0.4963868816008894,
337
- ≥2,8000,textvqa_val_exact_match,0.49798000000000003,0.006777844181917349
338
- ≥2,9000,ai2d_exact_match,0.4015544041450777,0.008822998789014784
339
- ≥2,9000,average,0.4409076865862069,
340
- ≥2,9000,average_rank,2.8,
341
- ≥2,9000,chartqa_relaxed_overall,0.5952,0.0098190299592035
342
- ≥2,9000,docvqa_val_anls,0.6142957639909281,0.006149142953850004
343
- ≥2,9000,infovqa_val_anls,0.225441641847203,0.006565814507342015
344
- ≥2,9000,mme_total_score,1170.923569427771,
345
- ≥2,9000,mmmu_val_mmmu_acc,0.28,
346
- ≥2,9000,mmstar_average,0.32763888124373686,
347
- ≥2,9000,ocrbench_ocrbench_accuracy,0.514,
348
- ≥2,9000,seedbench_seed_all,0.5012784880489161,
349
- ≥2,9000,textvqa_val_exact_match,0.50876,0.006788539558245703
350
- ≥2,10000,ai2d_exact_match,0.4018782383419689,0.008824167272304229
351
- ≥2,10000,average,0.44844067183729286,
352
- ≥2,10000,average_rank,2.7,
353
- ≥2,10000,chartqa_relaxed_overall,0.5956,0.009817474681589429
354
- ≥2,10000,docvqa_val_anls,0.6161881255627961,0.006150295182189919
355
- ≥2,10000,infovqa_val_anls,0.2273186020139702,0.006609762944776786
356
- ≥2,10000,mme_total_score,1244.6918767507002,
357
- ≥2,10000,mmmu_val_mmmu_acc,0.28667,
358
- ≥2,10000,mmstar_average,0.3405769394273513,
359
- ≥2,10000,ocrbench_ocrbench_accuracy,0.529,
360
- ≥2,10000,seedbench_seed_all,0.5174541411895498,
361
- ≥2,10000,textvqa_val_exact_match,0.52128,0.0067723707312184415
362
- ≥2,11000,ai2d_exact_match,0.41386010362694303,0.008864599272573477
363
- ≥2,11000,average,0.4508015001273205,
364
- ≥2,11000,average_rank,3.1,
365
- ≥2,11000,chartqa_relaxed_overall,0.5916,0.0098327233755248
366
- ≥2,11000,docvqa_val_anls,0.6132516406541649,0.006147223601932411
367
- ≥2,11000,infovqa_val_anls,0.23136501765139353,0.006670154065298524
368
- ≥2,11000,mme_total_score,1193.1198479391755,
369
- ≥2,11000,mmmu_val_mmmu_acc,0.28222,
370
- ≥2,11000,mmstar_average,0.34055130285985363,
371
- ≥2,11000,ocrbench_ocrbench_accuracy,0.544,
372
- ≥2,11000,seedbench_seed_all,0.5137854363535297,
373
- ≥2,11000,textvqa_val_exact_match,0.52658,0.006779520123033763
374
- ≥2,12000,ai2d_exact_match,0.42033678756476683,0.008884198538329101
375
- ≥2,12000,average,0.4593162089992856,
376
- ≥2,12000,average_rank,2.4,
377
- ≥2,12000,chartqa_relaxed_overall,0.612,0.009747841205275417
378
- ≥2,12000,docvqa_val_anls,0.6322256818549263,0.006037251396803284
379
- ≥2,12000,infovqa_val_anls,0.23499854511160906,0.006635085630122106
380
- ≥2,12000,mme_total_score,1282.3226290516207,
381
- ≥2,12000,mmmu_val_mmmu_acc,0.29444,
382
- ≥2,12000,mmstar_average,0.3455632878074604,
383
- ≥2,12000,ocrbench_ocrbench_accuracy,0.542,
384
- ≥2,12000,seedbench_seed_all,0.5148415786548082,
385
- ≥2,12000,textvqa_val_exact_match,0.5374399999999999,0.0067549667056943374
386
- ≥2,13000,ai2d_exact_match,0.4329663212435233,0.008917911748577596
387
- ≥2,13000,average,0.4594856750450977,
388
- ≥2,13000,average_rank,3.1,
389
- ≥2,13000,chartqa_relaxed_overall,0.6116,0.009749676839741497
390
- ≥2,13000,docvqa_val_anls,0.6480115225202001,0.006082136258345928
391
- ≥2,13000,infovqa_val_anls,0.2390399772273204,0.006801403608154099
392
- ≥2,13000,mme_total_score,1255.4888955582232,
393
- ≥2,13000,mmmu_val_mmmu_acc,0.26667,
394
- ≥2,13000,mmstar_average,0.3276926929918222,
395
- ≥2,13000,ocrbench_ocrbench_accuracy,0.551,
396
- ≥2,13000,seedbench_seed_all,0.5190105614230128,
397
- ≥2,13000,textvqa_val_exact_match,0.5393800000000001,0.006748937157104821
398
- ≥2,14000,ai2d_exact_match,0.43523316062176165,0.00892333645202351
399
- ≥2,14000,average,0.46380397688227554,
400
- ≥2,14000,average_rank,3.4,
401
- ≥2,14000,chartqa_relaxed_overall,0.6136,0.009740429476494075
402
- ≥2,14000,docvqa_val_anls,0.6474419557198757,0.006056802443739013
403
- ≥2,14000,infovqa_val_anls,0.24341248035748822,0.006789396426159645
404
- ≥2,14000,mme_total_score,1209.5489195678272,
405
- ≥2,14000,mmmu_val_mmmu_acc,0.27556,
406
- ≥2,14000,mmstar_average,0.35309886783724065,
407
- ≥2,14000,ocrbench_ocrbench_accuracy,0.545,
408
- ≥2,14000,seedbench_seed_all,0.5207893274041134,
409
- ≥2,14000,textvqa_val_exact_match,0.5400999999999999,0.006762835587905254
410
- ≥2,15000,ai2d_exact_match,0.43588082901554404,0.008924851504668983
411
- ≥2,15000,average,0.46327247775474995,
412
- ≥2,15000,average_rank,3.4,
413
- ≥2,15000,chartqa_relaxed_overall,0.614,0.009738559226822298
414
- ≥2,15000,docvqa_val_anls,0.638973421646662,0.005999307255506728
415
- ≥2,15000,infovqa_val_anls,0.23590457960067904,0.006699424952743598
416
- ≥2,15000,mme_total_score,1230.12775110044,
417
- ≥2,15000,mmmu_val_mmmu_acc,0.28667,
418
- ≥2,15000,mmstar_average,0.3545309625815601,
419
- ≥2,15000,ocrbench_ocrbench_accuracy,0.536,
420
- ≥2,15000,seedbench_seed_all,0.5225125069483046,
421
- ≥2,15000,textvqa_val_exact_match,0.54498,0.006749227387936104
422
- ≥2,16000,ai2d_exact_match,0.4413860103626943,0.008937105222785166
423
- ≥2,16000,average,0.4691799993543692,
424
- ≥2,16000,average_rank,3.1,
425
- ≥2,16000,chartqa_relaxed_overall,0.6168,0.009725273074549106
426
- ≥2,16000,docvqa_val_anls,0.6539654303329543,0.00605387835402321
427
- ≥2,16000,infovqa_val_anls,0.251011584102177,0.006888371171829252
428
- ≥2,16000,mme_total_score,1235.6986794717886,
429
- ≥2,16000,mmmu_val_mmmu_acc,0.28556,
430
- ≥2,16000,mmstar_average,0.35467603553935745,
431
- ≥2,16000,ocrbench_ocrbench_accuracy,0.545,
432
- ≥2,16000,seedbench_seed_all,0.5256809338521401,
433
- ≥2,16000,textvqa_val_exact_match,0.5485399999999999,0.0067546057338473825
434
- ≥2,17000,ai2d_exact_match,0.43976683937823835,0.008933617011753861
435
- ≥2,17000,average,0.47032074037035837,
436
- ≥2,17000,average_rank,3.1,
437
- ≥2,17000,chartqa_relaxed_overall,0.6184,0.009717527882093043
438
- ≥2,17000,docvqa_val_anls,0.655318828070759,0.005978737407680595
439
- ≥2,17000,infovqa_val_anls,0.24899610305034758,0.006825123869520012
440
- ≥2,17000,mme_total_score,1246.5548219287716,
441
- ≥2,17000,mmmu_val_mmmu_acc,0.29556,
442
- ≥2,17000,mmstar_average,0.3399003792152031,
443
- ≥2,17000,ocrbench_ocrbench_accuracy,0.553,
444
- ≥2,17000,seedbench_seed_all,0.5241245136186771,
445
- ≥2,17000,textvqa_val_exact_match,0.55782,0.0067278542139723035
446
- ≥2,18000,ai2d_exact_match,0.4413860103626943,0.008937105222785166
447
- ≥2,18000,average,0.4720458439616472,
448
- ≥2,18000,average_rank,3.0,
449
- ≥2,18000,chartqa_relaxed_overall,0.6256,0.009681288495793083
450
- ≥2,18000,docvqa_val_anls,0.6595541124701471,0.00598982698063352
451
- ≥2,18000,infovqa_val_anls,0.24628476636774824,0.006771852338911992
452
- ≥2,18000,mme_total_score,1246.580632252901,
453
- ≥2,18000,mmmu_val_mmmu_acc,0.29556,
454
- ≥2,18000,mmstar_average,0.3370877286888103,
455
- ≥2,18000,ocrbench_ocrbench_accuracy,0.557,
456
- ≥2,18000,seedbench_seed_all,0.5279599777654252,
457
- ≥2,18000,textvqa_val_exact_match,0.5579800000000001,0.006730967620262408
458
- ≥2,19000,ai2d_exact_match,0.44009067357512954,0.008934322367529354
459
- ≥2,19000,average,0.47484048232505544,
460
- ≥2,19000,average_rank,3.1,
461
- ≥2,19000,chartqa_relaxed_overall,0.6236,0.009691583292459796
462
- ≥2,19000,docvqa_val_anls,0.656845810830509,0.005998201285366962
463
- ≥2,19000,infovqa_val_anls,0.2483428639081206,0.006859079557818024
464
- ≥2,19000,mme_total_score,1255.002801120448,
465
- ≥2,19000,mmmu_val_mmmu_acc,0.30667,
466
- ≥2,19000,mmstar_average,0.3484268658746636,
467
- ≥2,19000,ocrbench_ocrbench_accuracy,0.557,
468
- ≥2,19000,seedbench_seed_all,0.5306281267370762,
469
- ≥2,19000,textvqa_val_exact_match,0.56196,0.006711810587335734
470
- ≥2,20000,ai2d_exact_match,0.44397668393782386,0.008942485993062323
471
- ≥2,20000,average,0.4719647885204447,
472
- ≥2,20000,average_rank,3.3,
473
- ≥2,20000,chartqa_relaxed_overall,0.6252,0.009683361554563506
474
- ≥2,20000,docvqa_val_anls,0.6531065052301426,0.005958657790556006
475
- ≥2,20000,infovqa_val_anls,0.2515640311557441,0.00684713602725156
476
- ≥2,20000,mme_total_score,1269.56512605042,
477
- ≥2,20000,mmmu_val_mmmu_acc,0.29222,
478
- ≥2,20000,mmstar_average,0.3405247257210479,
479
- ≥2,20000,ocrbench_ocrbench_accuracy,0.557,
480
- ≥2,20000,seedbench_seed_all,0.528071150639244,
481
- ≥2,20000,textvqa_val_exact_match,0.5560200000000001,0.006742124529303335
482
- ≥3,1000,ai2d_exact_match,0.25712435233160624,0.007866134203324925
483
- ≥3,1000,average,0.2908366935977347,
484
- ≥3,1000,average_rank,2.6,
485
- ≥3,1000,chartqa_relaxed_overall,0.3724,0.009670817229291067
486
- ≥3,1000,docvqa_val_anls,0.36190361730095816,0.005874681377878617
487
- ≥3,1000,infovqa_val_anls,0.1897409167650202,0.006570751118077319
488
- ≥3,1000,mme_total_score,938.3572428971589,
489
- ≥3,1000,mmmu_val_mmmu_acc,0.26333,
490
- ≥3,1000,mmstar_average,0.2361438073438948,
491
- ≥3,1000,ocrbench_ocrbench_accuracy,0.313,
492
- ≥3,1000,seedbench_seed_all,0.25758754863813227,
493
- ≥3,1000,textvqa_val_exact_match,0.36629999999999996,0.006582851113746775
494
- ≥3,2000,ai2d_exact_match,0.25647668393782386,0.007859644922870102
495
- ≥3,2000,average,0.327478691314146,
496
- ≥3,2000,average_rank,2.9,
497
- ≥3,2000,chartqa_relaxed_overall,0.4708,0.009984929820955767
498
- ≥3,2000,docvqa_val_anls,0.455859181323049,0.0061669106819143196
499
- ≥3,2000,infovqa_val_anls,0.20804914764579785,0.0066905821266465505
500
- ≥3,2000,mme_total_score,990.4248699479792,
501
- ≥3,2000,mmmu_val_mmmu_acc,0.27111,
502
- ≥3,2000,mmstar_average,0.21380673865938699,
503
- ≥3,2000,ocrbench_ocrbench_accuracy,0.405,
504
- ≥3,2000,seedbench_seed_all,0.26364647026125626,
505
- ≥3,2000,textvqa_val_exact_match,0.40256,0.0066960030295180025
506
- ≥3,3000,ai2d_exact_match,0.2697538860103627,0.007988222765138163
507
- ≥3,3000,average,0.34640625458292296,
508
- ≥3,3000,average_rank,3.1,
509
- ≥3,3000,chartqa_relaxed_overall,0.514,0.009998079047189691
510
- ≥3,3000,docvqa_val_anls,0.4749731938810012,0.00604931863100692
511
- ≥3,3000,infovqa_val_anls,0.19785201580687228,0.00636819106561235
512
- ≥3,3000,mme_total_score,1022.0748299319728,
513
- ≥3,3000,mmmu_val_mmmu_acc,0.26556,
514
- ≥3,3000,mmstar_average,0.2234035546364529,
515
- ≥3,3000,ocrbench_ocrbench_accuracy,0.435,
516
- ≥3,3000,seedbench_seed_all,0.29655364091161757,
517
- ≥3,3000,textvqa_val_exact_match,0.44056000000000006,0.006770653264576898
518
- ≥3,4000,ai2d_exact_match,0.31476683937823835,0.008358827401711809
519
- ≥3,4000,average,0.3840989485719881,
520
- ≥3,4000,average_rank,2.5,
521
- ≥3,4000,chartqa_relaxed_overall,0.5244,0.009990083919101193
522
- ≥3,4000,docvqa_val_anls,0.5398623644141017,0.006209437344747972
523
- ≥3,4000,infovqa_val_anls,0.21841657659961455,0.006654701266433889
524
- ≥3,4000,mme_total_score,1008.1938775510204,
525
- ≥3,4000,mmmu_val_mmmu_acc,0.27778,
526
- ≥3,4000,mmstar_average,0.25611290572758977,
527
- ≥3,4000,ocrbench_ocrbench_accuracy,0.462,
528
- ≥3,4000,seedbench_seed_all,0.39733185102834906,
529
- ≥3,4000,textvqa_val_exact_match,0.46621999999999997,0.006799457981763631
530
- ≥3,5000,ai2d_exact_match,0.3442357512953368,0.008551327504046387
531
- ≥3,5000,average,0.4034839586685592,
532
- ≥3,5000,average_rank,2.4,
533
- ≥3,5000,chartqa_relaxed_overall,0.5544,0.009942625323290008
534
- ≥3,5000,docvqa_val_anls,0.5567727758893183,0.006173642024037381
535
- ≥3,5000,infovqa_val_anls,0.21638639427926507,0.006559084868006158
536
- ≥3,5000,mme_total_score,1074.1284513805522,
537
- ≥3,5000,mmmu_val_mmmu_acc,0.26778,
538
- ≥3,5000,mmstar_average,0.3009278216170371,
539
- ≥3,5000,ocrbench_ocrbench_accuracy,0.482,
540
- ≥3,5000,seedbench_seed_all,0.4471928849360756,
541
- ≥3,5000,textvqa_val_exact_match,0.46165999999999996,0.006793381991893107
542
- ≥3,6000,ai2d_exact_match,0.36819948186528495,0.008680870162409787
543
- ≥3,6000,average,0.41987173897944946,
544
- ≥3,6000,average_rank,2.2,
545
- ≥3,6000,chartqa_relaxed_overall,0.5636,0.009920755241100424
546
- ≥3,6000,docvqa_val_anls,0.5766507662420887,0.006104661016322198
547
- ≥3,6000,infovqa_val_anls,0.2209691160904877,0.0066290878786102805
548
- ≥3,6000,mme_total_score,1088.6353541416568,
549
- ≥3,6000,mmmu_val_mmmu_acc,0.29778,
550
- ≥3,6000,mmstar_average,0.2960442855054549,
551
- ≥3,6000,ocrbench_ocrbench_accuracy,0.496,
552
- ≥3,6000,seedbench_seed_all,0.48360200111172874,
553
- ≥3,6000,textvqa_val_exact_match,0.476,0.006791614329821814
554
- ≥3,7000,ai2d_exact_match,0.3905440414507772,0.008780876258359173
555
- ≥3,7000,average,0.4305333557001585,
556
- ≥3,7000,average_rank,2.4,
557
- ≥3,7000,chartqa_relaxed_overall,0.5744,0.009890651444389179
558
- ≥3,7000,docvqa_val_anls,0.5943945047786826,0.006168637154272831
559
- ≥3,7000,infovqa_val_anls,0.23015651757384684,0.006652654324068369
560
- ≥3,7000,mme_total_score,1024.3486394557824,
561
- ≥3,7000,mmmu_val_mmmu_acc,0.29,
562
- ≥3,7000,mmstar_average,0.3086297067032336,
563
- ≥3,7000,ocrbench_ocrbench_accuracy,0.496,
564
- ≥3,7000,seedbench_seed_all,0.49577543079488606,
565
- ≥3,7000,textvqa_val_exact_match,0.4949,0.006791673090238732
566
- ≥3,8000,ai2d_exact_match,0.39863989637305697,0.008812301996070583
567
- ≥3,8000,average,0.43894563539556736,
568
- ≥3,8000,average_rank,2.4,
569
- ≥3,8000,chartqa_relaxed_overall,0.5812,0.009869224115088964
570
- ≥3,8000,docvqa_val_anls,0.597896936397571,0.006178924858305047
571
- ≥3,8000,infovqa_val_anls,0.23624667779429379,0.006701812126185011
572
- ≥3,8000,mme_total_score,1087.3003201280512,
573
- ≥3,8000,mmmu_val_mmmu_acc,0.30444,
574
- ≥3,8000,mmstar_average,0.3179238728089695,
575
- ≥3,8000,ocrbench_ocrbench_accuracy,0.52,
576
- ≥3,8000,seedbench_seed_all,0.5060033351862145,
577
- ≥3,8000,textvqa_val_exact_match,0.48816000000000004,0.006805617250862191
578
- ≥3,9000,ai2d_exact_match,0.4073834196891192,0.008843420154535594
579
- ≥3,9000,average,0.4380819691649286,
580
- ≥3,9000,average_rank,2.8,
581
- ≥3,9000,chartqa_relaxed_overall,0.5892,0.009841548985529353
582
- ≥3,9000,docvqa_val_anls,0.5926801961513722,0.00607014347283834
583
- ≥3,9000,infovqa_val_anls,0.22884227739619317,0.006587321958723987
584
- ≥3,9000,mme_total_score,960.1394557823129,
585
- ≥3,9000,mmmu_val_mmmu_acc,0.29222,
586
- ≥3,9000,mmstar_average,0.3023124740503409,
587
- ≥3,9000,ocrbench_ocrbench_accuracy,0.516,
588
- ≥3,9000,seedbench_seed_all,0.5108393551973318,
589
- ≥3,9000,textvqa_val_exact_match,0.50326,0.006787480273097782
590
- ≥3,10000,ai2d_exact_match,0.42487046632124353,0.008896983637113786
591
- ≥3,10000,average,0.45376975700130806,
592
- ≥3,10000,average_rank,2.5,
593
- ≥3,10000,chartqa_relaxed_overall,0.592,0.009831228876620145
594
- ≥3,10000,docvqa_val_anls,0.6288940533515488,0.006078026262812974
595
- ≥3,10000,infovqa_val_anls,0.2639557991160976,0.007015193539901653
596
- ≥3,10000,mme_total_score,1135.5116046418568,
597
- ≥3,10000,mmmu_val_mmmu_acc,0.29556,
598
- ≥3,10000,mmstar_average,0.3171165325775241,
599
- ≥3,10000,ocrbench_ocrbench_accuracy,0.53,
600
- ≥3,10000,seedbench_seed_all,0.5157309616453586,
601
- ≥3,10000,textvqa_val_exact_match,0.5158,0.0067831610812991135
602
- ≥3,11000,ai2d_exact_match,0.4271373056994819,0.008903088856242218
603
- ≥3,11000,average,0.4507656942256156,
604
- ≥3,11000,average_rank,3.1,
605
- ≥3,11000,chartqa_relaxed_overall,0.6008,0.00979663889573671
606
- ≥3,11000,docvqa_val_anls,0.6266233612884972,0.006097228164879785
607
- ≥3,11000,infovqa_val_anls,0.23605295775343718,0.006674753327687541
608
- ≥3,11000,mme_total_score,1115.0593237294918,
609
- ≥3,11000,mmmu_val_mmmu_acc,0.27889,
610
- ≥3,11000,mmstar_average,0.3244509807099135,
611
- ≥3,11000,ocrbench_ocrbench_accuracy,0.524,
612
- ≥3,11000,seedbench_seed_all,0.5219566425792107,
613
- ≥3,11000,textvqa_val_exact_match,0.5169799999999999,0.006776837095888084
614
- ≥3,12000,ai2d_exact_match,0.42843264248704666,0.008906491762178372
615
- ≥3,12000,average,0.4596080978908205,
616
- ≥3,12000,average_rank,2.6,
617
- ≥3,12000,chartqa_relaxed_overall,0.6048,0.009779828322460816
618
- ≥3,12000,docvqa_val_anls,0.6391083009950597,0.006038971765674556
619
- ≥3,12000,infovqa_val_anls,0.24141834493583503,0.006794485284013245
620
- ≥3,12000,mme_total_score,1183.3176270508202,
621
- ≥3,12000,mmmu_val_mmmu_acc,0.28444,
622
- ≥3,12000,mmstar_average,0.3293224419601992,
623
- ≥3,12000,ocrbench_ocrbench_accuracy,0.555,
624
- ≥3,12000,seedbench_seed_all,0.528071150639244,
625
- ≥3,12000,textvqa_val_exact_match,0.5258799999999999,0.006773951756875811
626
- ≥3,13000,ai2d_exact_match,0.43458549222797926,0.008921805911548515
627
- ≥3,13000,average,0.4623863039639755,
628
- ≥3,13000,average_rank,2.7,
629
- ≥3,13000,chartqa_relaxed_overall,0.6108,0.00975332737879659
630
- ≥3,13000,docvqa_val_anls,0.6376374898768016,0.006015671277879292
631
- ≥3,13000,infovqa_val_anls,0.24710671614089955,0.006756961641692092
632
- ≥3,13000,mme_total_score,1261.84493797519,
633
- ≥3,13000,mmmu_val_mmmu_acc,0.28889,
634
- ≥3,13000,mmstar_average,0.3264133242561134,
635
- ≥3,13000,ocrbench_ocrbench_accuracy,0.553,
636
- ≥3,13000,seedbench_seed_all,0.5306837131739855,
637
- ≥3,13000,textvqa_val_exact_match,0.5323599999999999,0.0067627001192260856
638
- ≥3,14000,ai2d_exact_match,0.4381476683937824,0.008930032335354969
639
- ≥3,14000,average,0.4678786302971554,
640
- ≥3,14000,average_rank,2.8,
641
- ≥3,14000,chartqa_relaxed_overall,0.6104,0.009755142291143075
642
- ≥3,14000,docvqa_val_anls,0.6523739582747238,0.006065891171788989
643
- ≥3,14000,infovqa_val_anls,0.2541881734588241,0.006851623469491799
644
- ≥3,14000,mme_total_score,1188.5243097238895,
645
- ≥3,14000,mmmu_val_mmmu_acc,0.30333,
646
- ≥3,14000,mmstar_average,0.3360144984503474,
647
- ≥3,14000,ocrbench_ocrbench_accuracy,0.544,
648
- ≥3,14000,seedbench_seed_all,0.5320733740967204,
649
- ≥3,14000,textvqa_val_exact_match,0.54038,0.006754155375986593
650
- ≥3,15000,ai2d_exact_match,0.4420336787564767,0.008938473522297184
651
- ≥3,15000,average,0.4717225541426424,
652
- ≥3,15000,average_rank,2.6,
653
- ≥3,15000,chartqa_relaxed_overall,0.6204,0.009707689307588963
654
- ≥3,15000,docvqa_val_anls,0.6657062061222615,0.005987913582977679
655
- ≥3,15000,infovqa_val_anls,0.2547770182395889,0.00697535381427897
656
- ≥3,15000,mme_total_score,1150.081532613045,
657
- ≥3,15000,mmmu_val_mmmu_acc,0.29889,
658
- ≥3,15000,mmstar_average,0.32974187627218104,
659
- ≥3,15000,ocrbench_ocrbench_accuracy,0.556,
660
- ≥3,15000,seedbench_seed_all,0.533574207893274,
661
- ≥3,15000,textvqa_val_exact_match,0.54438,0.006740769296908389
662
- ≥3,16000,ai2d_exact_match,0.44397668393782386,0.008942485993062323
663
- ≥3,16000,average,0.4725329505079693,
664
- ≥3,16000,average_rank,2.7,
665
- ≥3,16000,chartqa_relaxed_overall,0.6136,0.009740429476494075
666
- ≥3,16000,docvqa_val_anls,0.6627356411508976,0.00599828184206493
667
- ≥3,16000,infovqa_val_anls,0.25144929243788827,0.006859545868541458
668
- ≥3,16000,mme_total_score,1189.4136654661866,
669
- ≥3,16000,mmmu_val_mmmu_acc,0.30556,
670
- ≥3,16000,mmstar_average,0.32828609880164517,
671
- ≥3,16000,ocrbench_ocrbench_accuracy,0.565,
672
- ≥3,16000,seedbench_seed_all,0.5359088382434686,
673
- ≥3,16000,textvqa_val_exact_match,0.54628,0.006755557699551266
674
- ≥3,17000,ai2d_exact_match,0.4423575129533679,0.008939151893135124
675
- ≥3,17000,average,0.47219284094380815,
676
- ≥3,17000,average_rank,2.9,
677
- ≥3,17000,chartqa_relaxed_overall,0.6196,0.009711645711462604
678
- ≥3,17000,docvqa_val_anls,0.6671354152323413,0.005979986643812461
679
- ≥3,17000,infovqa_val_anls,0.26085018558007095,0.006930202483417548
680
- ≥3,17000,mme_total_score,1181.9268707482993,
681
- ≥3,17000,mmmu_val_mmmu_acc,0.29667,
682
- ≥3,17000,mmstar_average,0.3246494808541184,
683
- ≥3,17000,ocrbench_ocrbench_accuracy,0.556,
684
- ≥3,17000,seedbench_seed_all,0.5353529738743746,
685
- ≥3,17000,textvqa_val_exact_match,0.5471199999999999,0.006741055517194408
686
- ≥3,18000,ai2d_exact_match,0.44624352331606215,0.0089469921763539
687
- ≥3,18000,average,0.47727537354972976,
688
- ≥3,18000,average_rank,2.8,
689
- ≥3,18000,chartqa_relaxed_overall,0.6212,0.009703704898413913
690
- ≥3,18000,docvqa_val_anls,0.6676971859833172,0.005968624246725931
691
- ≥3,18000,infovqa_val_anls,0.2614701461784385,0.006943538426265278
692
- ≥3,18000,mme_total_score,1133.047819127651,
693
- ≥3,18000,mmmu_val_mmmu_acc,0.30444,
694
- ≥3,18000,mmstar_average,0.3242292852357318,
695
- ≥3,18000,ocrbench_ocrbench_accuracy,0.582,
696
- ≥3,18000,seedbench_seed_all,0.5367982212340189,
697
- ≥3,18000,textvqa_val_exact_match,0.5513999999999999,0.006735687188133017
698
- ≥3,19000,ai2d_exact_match,0.4520725388601036,0.008957715852675527
699
- ≥3,19000,average,0.4762675915069992,
700
- ≥3,19000,average_rank,3.0,
701
- ≥3,19000,chartqa_relaxed_overall,0.6216,0.009701702181065136
702
- ≥3,19000,docvqa_val_anls,0.6679273632688325,0.00596194457686321
703
- ≥3,19000,infovqa_val_anls,0.25211534311880446,0.006837669178934141
704
- ≥3,19000,mme_total_score,1168.6077430972389,
705
- ≥3,19000,mmmu_val_mmmu_acc,0.30111,
706
- ≥3,19000,mmstar_average,0.334229548576509,
707
- ≥3,19000,ocrbench_ocrbench_accuracy,0.566,
708
- ≥3,19000,seedbench_seed_all,0.5363535297387437,
709
- ≥3,19000,textvqa_val_exact_match,0.555,0.006737661257130932
710
- ≥3,20000,ai2d_exact_match,0.4566062176165803,0.008965198879336198
711
- ≥3,20000,average,0.4782761612786655,
712
- ≥3,20000,average_rank,2.7,
713
- ≥3,20000,chartqa_relaxed_overall,0.6268,0.009675026948726469
714
- ≥3,20000,docvqa_val_anls,0.6699567897644018,0.005975453790424837
715
- ≥3,20000,infovqa_val_anls,0.2594904076423186,0.006910668664574003
716
- ≥3,20000,mme_total_score,1194.4682873149259,
717
- ≥3,20000,mmmu_val_mmmu_acc,0.30667,
718
- ≥3,20000,mmstar_average,0.3291890626103143,
719
- ≥3,20000,ocrbench_ocrbench_accuracy,0.571,
720
- ≥3,20000,seedbench_seed_all,0.5353529738743746,
721
- ≥3,20000,textvqa_val_exact_match,0.54942,0.0067426571472292
722
- ≥4,1000,ai2d_exact_match,0.266839378238342,0.007960790788435024
723
- ≥4,1000,average,0.28718938224797474,
724
- ≥4,1000,average_rank,2.8,
725
- ≥4,1000,chartqa_relaxed_overall,0.3824,0.009721414421746647
726
- ≥4,1000,docvqa_val_anls,0.3742280929549393,0.005897617626003216
727
- ≥4,1000,infovqa_val_anls,0.18767733564942402,0.006495529242061099
728
- ≥4,1000,mme_total_score,970.0657262905162,
729
- ≥4,1000,mmmu_val_mmmu_acc,0.24667,
730
- ≥4,1000,mmstar_average,0.20409674845299178,
731
- ≥4,1000,ocrbench_ocrbench_accuracy,0.324,
732
- ≥4,1000,seedbench_seed_all,0.2471928849360756,
733
- ≥4,1000,textvqa_val_exact_match,0.3516,0.006519815150594346
734
- ≥4,2000,ai2d_exact_match,0.2700777202072539,0.007991243694641088
735
- ≥4,2000,average,0.32538295993176786,
736
- ≥4,2000,average_rank,2.8,
737
- ≥4,2000,chartqa_relaxed_overall,0.476,0.009990471651004463
738
- ≥4,2000,docvqa_val_anls,0.45055679456484166,0.006087636141467791
739
- ≥4,2000,infovqa_val_anls,0.21184608413063888,0.006740983882332282
740
- ≥4,2000,mme_total_score,1065.059423769508,
741
- ≥4,2000,mmmu_val_mmmu_acc,0.25444,
742
- ≥4,2000,mmstar_average,0.20479630173942967,
743
- ≥4,2000,ocrbench_ocrbench_accuracy,0.404,
744
- ≥4,2000,seedbench_seed_all,0.2535297387437465,
745
- ≥4,2000,textvqa_val_exact_match,0.4032,0.00669032914742019
746
- ≥4,3000,ai2d_exact_match,0.26813471502590674,0.007973037037795191
747
- ≥4,3000,average,0.3429973351943505,
748
- ≥4,3000,average_rank,3.6,
749
- ≥4,3000,chartqa_relaxed_overall,0.5052,0.010001459677380663
750
- ≥4,3000,docvqa_val_anls,0.4883627712637139,0.006123671768321872
751
- ≥4,3000,infovqa_val_anls,0.2020989926298624,0.006492359244043468
752
- ≥4,3000,mme_total_score,1028.0742296918768,
753
- ≥4,3000,mmmu_val_mmmu_acc,0.24444,
754
- ≥4,3000,mmstar_average,0.23755500197641968,
755
- ≥4,3000,ocrbench_ocrbench_accuracy,0.417,
756
- ≥4,3000,seedbench_seed_all,0.2961645358532518,
757
- ≥4,3000,textvqa_val_exact_match,0.42802000000000007,0.006729073636571477
758
- ≥4,4000,ai2d_exact_match,0.297279792746114,0.008226320033454882
759
- ≥4,4000,average,0.37640705986204226,
760
- ≥4,4000,average_rank,3.0,
761
- ≥4,4000,chartqa_relaxed_overall,0.5328,0.009980456292330589
762
- ≥4,4000,docvqa_val_anls,0.5114700599486628,0.006120071866795458
763
- ≥4,4000,infovqa_val_anls,0.20557836945629954,0.006329851460183733
764
- ≥4,4000,mme_total_score,1074.640656262505,
765
- ≥4,4000,mmmu_val_mmmu_acc,0.25889,
766
- ≥4,4000,mmstar_average,0.24011275407256244,
767
- ≥4,4000,ocrbench_ocrbench_accuracy,0.489,
768
- ≥4,4000,seedbench_seed_all,0.40261256253474154,
769
- ≥4,4000,textvqa_val_exact_match,0.44992,0.006773387223162055
770
- ≥4,5000,ai2d_exact_match,0.32998704663212436,0.008462949140760363
771
- ≥4,5000,average,0.3995227518308942,
772
- ≥4,5000,average_rank,2.8,
773
- ≥4,5000,chartqa_relaxed_overall,0.55,0.009951864943131942
774
- ≥4,5000,docvqa_val_anls,0.5627332434349699,0.006167596088104117
775
- ≥4,5000,infovqa_val_anls,0.20676909019266723,0.0063195922615256655
776
- ≥4,5000,mme_total_score,1081.3841536614646,
777
- ≥4,5000,mmmu_val_mmmu_acc,0.26667,
778
- ≥4,5000,mmstar_average,0.26742033896981504,
779
- ≥4,5000,ocrbench_ocrbench_accuracy,0.49,
780
- ≥4,5000,seedbench_seed_all,0.4530850472484714,
781
- ≥4,5000,textvqa_val_exact_match,0.46903999999999996,0.006785801728684695
782
- ≥4,6000,ai2d_exact_match,0.35654145077720206,0.008620788425978479
783
- ≥4,6000,average,0.41458714913417777,
784
- ≥4,6000,average_rank,2.8,
785
- ≥4,6000,chartqa_relaxed_overall,0.5632,0.009921778100334079
786
- ≥4,6000,docvqa_val_anls,0.5818014224607982,0.006182490179642956
787
- ≥4,6000,infovqa_val_anls,0.2145391217079547,0.006472934595237677
788
- ≥4,6000,mme_total_score,1132.2886154461785,
789
- ≥4,6000,mmmu_val_mmmu_acc,0.26667,
790
- ≥4,6000,mmstar_average,0.28714914548287923,
791
- ≥4,6000,ocrbench_ocrbench_accuracy,0.499,
792
- ≥4,6000,seedbench_seed_all,0.47376320177876596,
793
- ≥4,6000,textvqa_val_exact_match,0.48862,0.006787319991169747
794
- ≥4,7000,ai2d_exact_match,0.38471502590673573,0.008756678690415541
795
- ≥4,7000,average,0.42592935170009355,
796
- ≥4,7000,average_rank,3.1,
797
- ≥4,7000,chartqa_relaxed_overall,0.5804,0.009871844677005952
798
- ≥4,7000,docvqa_val_anls,0.5710623718792285,0.006078423874650784
799
- ≥4,7000,infovqa_val_anls,0.22007869704137703,0.006475129444868969
800
- ≥4,7000,mme_total_score,1041.2597038815525,
801
- ≥4,7000,mmmu_val_mmmu_acc,0.28444,
802
- ≥4,7000,mmstar_average,0.3026487819798931,
803
- ≥4,7000,ocrbench_ocrbench_accuracy,0.502,
804
- ≥4,7000,seedbench_seed_all,0.4947192884936076,
805
- ≥4,7000,textvqa_val_exact_match,0.4933,0.006785560460724908
806
- ≥4,8000,ai2d_exact_match,0.3915155440414508,0.008784780895708938
807
- ≥4,8000,average,0.43659006376695136,
808
- ≥4,8000,average_rank,3.0,
809
- ≥4,8000,chartqa_relaxed_overall,0.5736,0.009893046292521752
810
- ≥4,8000,docvqa_val_anls,0.6079864136742988,0.006139878520335163
811
- ≥4,8000,infovqa_val_anls,0.23243402779245617,0.006686893363455147
812
- ≥4,8000,mme_total_score,1108.9173669467787,
813
- ≥4,8000,mmmu_val_mmmu_acc,0.28,
814
- ≥4,8000,mmstar_average,0.3276025817239844,
815
- ≥4,8000,ocrbench_ocrbench_accuracy,0.508,
816
- ≥4,8000,seedbench_seed_all,0.5016120066703724,
817
- ≥4,8000,textvqa_val_exact_match,0.50656,0.006805281452749051
818
- ≥4,9000,ai2d_exact_match,0.39248704663212436,0.008788649010397578
819
- ≥4,9000,average,0.4379212821083599,
820
- ≥4,9000,average_rank,2.9,
821
- ≥4,9000,chartqa_relaxed_overall,0.5844,0.009858475126140203
822
- ≥4,9000,docvqa_val_anls,0.6225000882770518,0.00610983265425905
823
- ≥4,9000,infovqa_val_anls,0.2357319670089269,0.006735352134813103
824
- ≥4,9000,mme_total_score,1054.3165266106444,
825
- ≥4,9000,mmmu_val_mmmu_acc,0.28556,
826
- ≥4,9000,mmstar_average,0.30919474945291153,
827
- ≥4,9000,ocrbench_ocrbench_accuracy,0.496,
828
- ≥4,9000,seedbench_seed_all,0.5078376876042245,
829
- ≥4,9000,textvqa_val_exact_match,0.50758,0.0067866133191798106
830
- ≥4,10000,ai2d_exact_match,0.4177461139896373,0.008876547725654098
831
- ≥4,10000,average,0.4482945169324334,
832
- ≥4,10000,average_rank,3.0,
833
- ≥4,10000,chartqa_relaxed_overall,0.5872,0.009848718845878486
834
- ≥4,10000,docvqa_val_anls,0.6178172719068701,0.006018237392964321
835
- ≥4,10000,infovqa_val_anls,0.24180220451279583,0.006673139519957623
836
- ≥4,10000,mme_total_score,1143.5380152060825,
837
- ≥4,10000,mmmu_val_mmmu_acc,0.29667,
838
- ≥4,10000,mmstar_average,0.31635030378359796,
839
- ≥4,10000,ocrbench_ocrbench_accuracy,0.524,
840
- ≥4,10000,seedbench_seed_all,0.5165647581989995,
841
- ≥4,10000,textvqa_val_exact_match,0.5165,0.006796704277648658
842
- ≥4,11000,ai2d_exact_match,0.41515544041450775,0.00886864516657515
843
- ≥4,11000,average,0.45134109009976725,
844
- ≥4,11000,average_rank,2.5,
845
- ≥4,11000,chartqa_relaxed_overall,0.5956,0.009817474681589429
846
- ≥4,11000,docvqa_val_anls,0.629269001239484,0.00608373788497042
847
- ≥4,11000,infovqa_val_anls,0.24324006994727237,0.006777064540159464
848
- ≥4,11000,mme_total_score,1228.8085234093637,
849
- ≥4,11000,mmmu_val_mmmu_acc,0.28333,
850
- ≥4,11000,mmstar_average,0.3288790569397762,
851
- ≥4,11000,ocrbench_ocrbench_accuracy,0.522,
852
- ≥4,11000,seedbench_seed_all,0.525236242356865,
853
- ≥4,11000,textvqa_val_exact_match,0.5193599999999999,0.0067761804436039675
854
- ≥4,12000,ai2d_exact_match,0.4183937823834197,0.008878484004260249
855
- ≥4,12000,average,0.45687238598965646,
856
- ≥4,12000,average_rank,3.3,
857
- ≥4,12000,chartqa_relaxed_overall,0.5988,0.0098047885010856
858
- ≥4,12000,docvqa_val_anls,0.6281800356608191,0.005956403319187123
859
- ≥4,12000,infovqa_val_anls,0.242249391011484,0.006664412716854741
860
- ≥4,12000,mme_total_score,1051.548619447779,
861
- ≥4,12000,mmmu_val_mmmu_acc,0.28,
862
- ≥4,12000,mmstar_average,0.32638661949265274,
863
- ≥4,12000,ocrbench_ocrbench_accuracy,0.553,
864
- ≥4,12000,seedbench_seed_all,0.5309616453585325,
865
- ≥4,12000,textvqa_val_exact_match,0.53388,0.006762808309810877
866
- ≥4,13000,ai2d_exact_match,0.4323186528497409,0.008916326937351901
867
- ≥4,13000,average,0.46134498058034357,
868
- ≥4,13000,average_rank,3.1,
869
- ≥4,13000,chartqa_relaxed_overall,0.5948,0.009820578470976232
870
- ≥4,13000,docvqa_val_anls,0.6459204882256453,0.006047391420582867
871
- ≥4,13000,infovqa_val_anls,0.24395762124162781,0.006787945348887751
872
- ≥4,13000,mme_total_score,1195.637755102041,
873
- ≥4,13000,mmmu_val_mmmu_acc,0.29556,
874
- ≥4,13000,mmstar_average,0.329867095702076,
875
- ≥4,13000,ocrbench_ocrbench_accuracy,0.542,
876
- ≥4,13000,seedbench_seed_all,0.5337409672040022,
877
- ≥4,13000,textvqa_val_exact_match,0.53394,0.006767804364428913
878
- ≥4,14000,ai2d_exact_match,0.4319948186528497,0.008915528710615492
879
- ≥4,14000,average,0.4668148142530245,
880
- ≥4,14000,average_rank,2.7,
881
- ≥4,14000,chartqa_relaxed_overall,0.6076,0.009767653701044555
882
- ≥4,14000,docvqa_val_anls,0.6561789267585798,0.005953346874132679
883
- ≥4,14000,infovqa_val_anls,0.24945371957223306,0.006769327490532885
884
- ≥4,14000,mme_total_score,1259.298019207683,
885
- ≥4,14000,mmmu_val_mmmu_acc,0.30111,
886
- ≥4,14000,mmstar_average,0.32172026573936097,
887
- ≥4,14000,ocrbench_ocrbench_accuracy,0.55,
888
- ≥4,14000,seedbench_seed_all,0.5360755975541968,
889
- ≥4,14000,textvqa_val_exact_match,0.5472000000000001,0.006748951153204005
890
- ≥4,15000,ai2d_exact_match,0.44624352331606215,0.008946992176353898
891
- ≥4,15000,average,0.46662671868754135,
892
- ≥4,15000,average_rank,2.9,
893
- ≥4,15000,chartqa_relaxed_overall,0.6044,0.009781540134915584
894
- ≥4,15000,docvqa_val_anls,0.6622581274446402,0.005962189435141322
895
- ≥4,15000,infovqa_val_anls,0.2534140745372918,0.006885986461871116
896
- ≥4,15000,mme_total_score,1200.2537014805923,
897
- ≥4,15000,mmmu_val_mmmu_acc,0.29,
898
- ≥4,15000,mmstar_average,0.3198168607331238,
899
- ≥4,15000,ocrbench_ocrbench_accuracy,0.538,
900
- ≥4,15000,seedbench_seed_all,0.5381878821567537,
901
- ≥4,15000,textvqa_val_exact_match,0.54732,0.006746470669416614
902
- ≥4,16000,ai2d_exact_match,0.43911917098445596,0.008932194723472647
903
- ≥4,16000,average,0.46812785270927354,
904
- ≥4,16000,average_rank,3.0,
905
- ≥4,16000,chartqa_relaxed_overall,0.6108,0.00975332737879659
906
- ≥4,16000,docvqa_val_anls,0.6699643513666329,0.005944732124585459
907
- ≥4,16000,infovqa_val_anls,0.2589072217280723,0.006864729360775582
908
- ≥4,16000,mme_total_score,1239.2577030812326,
909
- ≥4,16000,mmmu_val_mmmu_acc,0.28444,
910
- ≥4,16000,mmstar_average,0.3155913699930164,
911
- ≥4,16000,ocrbench_ocrbench_accuracy,0.547,
912
- ≥4,16000,seedbench_seed_all,0.535408560311284,
913
- ≥4,16000,textvqa_val_exact_match,0.55192,0.006727935474062503
914
- ≥4,17000,ai2d_exact_match,0.44591968911917096,0.00894635996642554
915
- ≥4,17000,average,0.4711902865454063,
916
- ≥4,17000,average_rank,2.9,
917
- ≥4,17000,chartqa_relaxed_overall,0.6092,0.009760545645634788
918
- ≥4,17000,docvqa_val_anls,0.6630256300679175,0.005926991608870499
919
- ≥4,17000,infovqa_val_anls,0.2604941623528308,0.0069459226352746855
920
- ≥4,17000,mme_total_score,1231.9475790316128,
921
- ≥4,17000,mmmu_val_mmmu_acc,0.28667,
922
- ≥4,17000,mmstar_average,0.3281863880858027,
923
- ≥4,17000,ocrbench_ocrbench_accuracy,0.559,
924
- ≥4,17000,seedbench_seed_all,0.5380767092829349,
925
- ≥4,17000,textvqa_val_exact_match,0.55014,0.00673464677421427
926
- ≥4,18000,ai2d_exact_match,0.44527202072538863,0.008945084019331404
927
- ≥4,18000,average,0.4730863890198541,
928
- ≥4,18000,average_rank,3.1,
929
- ≥4,18000,chartqa_relaxed_overall,0.6148,0.00973479791861169
930
- ≥4,18000,docvqa_val_anls,0.6724670614264582,0.0059283840951577715
931
- ≥4,18000,infovqa_val_anls,0.2591524677671406,0.006860568910244235
932
- ≥4,18000,mme_total_score,1230.187074829932,
933
- ≥4,18000,mmmu_val_mmmu_acc,0.28222,
934
- ≥4,18000,mmstar_average,0.3313130996754855,
935
- ≥4,18000,ocrbench_ocrbench_accuracy,0.559,
936
- ≥4,18000,seedbench_seed_all,0.5391328515842134,
937
- ≥4,18000,textvqa_val_exact_match,0.55442,0.0067378017419973775
938
- ≥4,19000,ai2d_exact_match,0.4475388601036269,0.008949482610884277
939
- ≥4,19000,average,0.4748981492546839,
940
- ≥4,19000,average_rank,3.0,
941
- ≥4,19000,chartqa_relaxed_overall,0.614,0.009738559226822298
942
- ≥4,19000,docvqa_val_anls,0.6780110114952748,0.005954038851856335
943
- ≥4,19000,infovqa_val_anls,0.2592553130284412,0.0068947091925615645
944
- ≥4,19000,mme_total_score,1280.6934773909566,
945
- ≥4,19000,mmmu_val_mmmu_acc,0.29778,
946
- ≥4,19000,mmstar_average,0.33015385627459537,
947
- ≥4,19000,ocrbench_ocrbench_accuracy,0.55,
948
- ≥4,19000,seedbench_seed_all,0.5397443023902168,
949
- ≥4,19000,textvqa_val_exact_match,0.5576000000000001,0.00671993150976252
950
- ≥4,20000,ai2d_exact_match,0.45077720207253885,0.008955440137395838
951
- ≥4,20000,average,0.47750231781976243,
952
- ≥4,20000,average_rank,2.7,
953
- ≥4,20000,chartqa_relaxed_overall,0.6204,0.009707689307588963
954
- ≥4,20000,docvqa_val_anls,0.673153386104693,0.005945073379634221
955
- ≥4,20000,infovqa_val_anls,0.2604945747241511,0.006917780880359967
956
- ≥4,20000,mme_total_score,1348.6498599439776,
957
- ≥4,20000,mmmu_val_mmmu_acc,0.29222,
958
- ≥4,20000,mmstar_average,0.32618642565880246,
959
- ≥4,20000,ocrbench_ocrbench_accuracy,0.569,
960
- ≥4,20000,seedbench_seed_all,0.5406892718176765,
961
- ≥4,20000,textvqa_val_exact_match,0.5646,0.006722023885782034
962
- ≥5,1000,ai2d_exact_match,0.27396373056994816,0.008027076080717028
963
- ≥5,1000,average,0.26438200891802877,
964
- ≥5,1000,average_rank,3.0,
965
- ≥5,1000,chartqa_relaxed_overall,0.2832,0.00901285729603301
966
- ≥5,1000,docvqa_val_anls,0.32055326545515606,0.0056245129740867565
967
- ≥5,1000,infovqa_val_anls,0.15327397474830004,0.005916826112508726
968
- ≥5,1000,mme_total_score,1087.6624649859943,
969
- ≥5,1000,mmmu_val_mmmu_acc,0.29778,
970
- ≥5,1000,mmstar_average,0.26060215117868224,
971
- ≥5,1000,ocrbench_ocrbench_accuracy,0.259,
972
- ≥5,1000,seedbench_seed_all,0.2649249583101723,
973
- ≥5,1000,textvqa_val_exact_match,0.26614,0.006037548383085275
974
- ≥5,2000,ai2d_exact_match,0.26392487046632124,0.007932917099101329
975
- ≥5,2000,average,0.2929576826335877,
976
- ≥5,2000,average_rank,3.3,
977
- ≥5,2000,chartqa_relaxed_overall,0.3824,0.009721414421746647
978
- ≥5,2000,docvqa_val_anls,0.3929824030686217,0.005977850940256623
979
- ≥5,2000,infovqa_val_anls,0.15895135963621443,0.005878593482981634
980
- ≥5,2000,mme_total_score,1073.4139655862346,
981
- ≥5,2000,mmmu_val_mmmu_acc,0.27333,
982
- ≥5,2000,mmstar_average,0.25335477956948643,
983
- ≥5,2000,ocrbench_ocrbench_accuracy,0.301,
984
- ≥5,2000,seedbench_seed_all,0.26831573096164535,
985
- ≥5,2000,textvqa_val_exact_match,0.34236,0.006479253215027554
986
- ≥5,3000,ai2d_exact_match,0.2600388601036269,0.007895056974601723
987
- ≥5,3000,average,0.3126381365493242,
988
- ≥5,3000,average_rank,3.9,
989
- ≥5,3000,chartqa_relaxed_overall,0.4324,0.009910165515884228
990
- ≥5,3000,docvqa_val_anls,0.4366357263318607,0.00610598785442012
991
- ≥5,3000,infovqa_val_anls,0.17846201123654198,0.006273305639193489
992
- ≥5,3000,mme_total_score,1164.5565226090434,
993
- ≥5,3000,mmmu_val_mmmu_acc,0.28778,
994
- ≥5,3000,mmstar_average,0.25130117268378377,
995
- ≥5,3000,ocrbench_ocrbench_accuracy,0.344,
996
- ≥5,3000,seedbench_seed_all,0.2858254585881045,
997
- ≥5,3000,textvqa_val_exact_match,0.3373,0.006457064405451384
998
- ≥5,4000,ai2d_exact_match,0.25647668393782386,0.007859644922870104
999
- ≥5,4000,average,0.3300809923443584,
1000
- ≥5,4000,average_rank,4.3,
1001
- ≥5,4000,chartqa_relaxed_overall,0.4428,0.009936335154498413
1002
- ≥5,4000,docvqa_val_anls,0.4736486989184438,0.006240863735639683
1003
- ≥5,4000,infovqa_val_anls,0.19267658764675277,0.006512420811238904
1004
- ≥5,4000,mme_total_score,1218.2668067226891,
1005
- ≥5,4000,mmmu_val_mmmu_acc,0.26889,
1006
- ≥5,4000,mmstar_average,0.22297093502644408,
1007
- ≥5,4000,ocrbench_ocrbench_accuracy,0.379,
1008
- ≥5,4000,seedbench_seed_all,0.322846025569761,
1009
- ≥5,4000,textvqa_val_exact_match,0.41142,0.006712445761838313
1010
- ≥5,5000,ai2d_exact_match,0.25161917098445596,0.007810248924722509
1011
- ≥5,5000,average,0.3420574749713038,
1012
- ≥5,5000,average_rank,4.2,
1013
- ≥5,5000,chartqa_relaxed_overall,0.4488,0.009949423119365426
1014
- ≥5,5000,docvqa_val_anls,0.4973120888104521,0.00627054301371889
1015
- ≥5,5000,infovqa_val_anls,0.20687122924296383,0.006767419172429617
1016
- ≥5,5000,mme_total_score,1285.299119647859,
1017
- ≥5,5000,mmmu_val_mmmu_acc,0.26778,
1018
- ≥5,5000,mmstar_average,0.24681232878335083,
1019
- ≥5,5000,ocrbench_ocrbench_accuracy,0.392,
1020
- ≥5,5000,seedbench_seed_all,0.3604224569205114,
1021
- ≥5,5000,textvqa_val_exact_match,0.4069,0.00670861230775927
1022
- ≥5,6000,ai2d_exact_match,0.2704015544041451,0.00799425923314582
1023
- ≥5,6000,average,0.35916516291601697,
1024
- ≥5,6000,average_rank,4.4,
1025
- ≥5,6000,chartqa_relaxed_overall,0.4844,0.009997131241172205
1026
- ≥5,6000,docvqa_val_anls,0.5108154498847224,0.0062636540505031655
1027
- ≥5,6000,infovqa_val_anls,0.20262763630072025,0.0066138397079363274
1028
- ≥5,6000,mme_total_score,1273.862545018007,
1029
- ≥5,6000,mmmu_val_mmmu_acc,0.27444,
1030
- ≥5,6000,mmstar_average,0.2588150329919745,
1031
- ≥5,6000,ocrbench_ocrbench_accuracy,0.403,
1032
- ≥5,6000,seedbench_seed_all,0.4082267926625903,
1033
- ≥5,6000,textvqa_val_exact_match,0.41976,0.006731520716318925
1034
- ≥5,7000,ai2d_exact_match,0.31994818652849744,0.008395421656067303
1035
- ≥5,7000,average,0.3723337802797541,
1036
- ≥5,7000,average_rank,4.5,
1037
- ≥5,7000,chartqa_relaxed_overall,0.476,0.009990471651004463
1038
- ≥5,7000,docvqa_val_anls,0.5291779466505276,0.006267960743408816
1039
- ≥5,7000,infovqa_val_anls,0.20957812087727798,0.006721757004150909
1040
- ≥5,7000,mme_total_score,1327.2439975990396,
1041
- ≥5,7000,mmmu_val_mmmu_acc,0.27222,
1042
- ≥5,7000,mmstar_average,0.29354698358099446,
1043
- ≥5,7000,ocrbench_ocrbench_accuracy,0.403,
1044
- ≥5,7000,seedbench_seed_all,0.42301278488048916,
1045
- ≥5,7000,textvqa_val_exact_match,0.42452,0.006734688198055274
1046
- ≥5,8000,ai2d_exact_match,0.30958549222797926,0.008321027166750249
1047
- ≥5,8000,average,0.37926040717793597,
1048
- ≥5,8000,average_rank,4.5,
1049
- ≥5,8000,chartqa_relaxed_overall,0.5136,0.009998299975543861
1050
- ≥5,8000,docvqa_val_anls,0.5386485557171258,0.006250093887872433
1051
- ≥5,8000,infovqa_val_anls,0.21347817313272946,0.006767638253739939
1052
- ≥5,8000,mme_total_score,1351.172769107643,
1053
- ≥5,8000,mmmu_val_mmmu_acc,0.27667,
1054
- ≥5,8000,mmstar_average,0.27077818615838667,
1055
- ≥5,8000,ocrbench_ocrbench_accuracy,0.406,
1056
- ≥5,8000,seedbench_seed_all,0.4538632573652029,
1057
- ≥5,8000,textvqa_val_exact_match,0.43072,0.00674498000523754
1058
- ≥5,9000,ai2d_exact_match,0.32642487046632124,0.00843949241376102
1059
- ≥5,9000,average,0.3915431470529602,
1060
- ≥5,9000,average_rank,4.4,
1061
- ≥5,9000,chartqa_relaxed_overall,0.5196,0.009994312908659929
1062
- ≥5,9000,docvqa_val_anls,0.5447526718541965,0.006277223186340111
1063
- ≥5,9000,infovqa_val_anls,0.22534586447558344,0.006943394394173722
1064
- ≥5,9000,mme_total_score,1380.0509203681472,
1065
- ≥5,9000,mmmu_val_mmmu_acc,0.28222,
1066
- ≥5,9000,mmstar_average,0.2981132324115024,
1067
- ≥5,9000,ocrbench_ocrbench_accuracy,0.42,
1068
- ≥5,9000,seedbench_seed_all,0.45703168426903834,
1069
- ≥5,9000,textvqa_val_exact_match,0.4504,0.0067806462400486975
1070
- ≥5,10000,ai2d_exact_match,0.3121761658031088,0.008340079044408505
1071
- ≥5,10000,average,0.3945344056050298,
1072
- ≥5,10000,average_rank,4.4,
1073
- ≥5,10000,chartqa_relaxed_overall,0.524,0.009990471651004463
1074
- ≥5,10000,docvqa_val_anls,0.5476477162524015,0.006282119242898783
1075
- ≥5,10000,infovqa_val_anls,0.2268357982996008,0.007080273138697436
1076
- ≥5,10000,mme_total_score,1385.6108443377352,
1077
- ≥5,10000,mmmu_val_mmmu_acc,0.29222,
1078
- ≥5,10000,mmstar_average,0.29882846925636025,
1079
- ≥5,10000,ocrbench_ocrbench_accuracy,0.43,
1080
- ≥5,10000,seedbench_seed_all,0.4627015008337966,
1081
- ≥5,10000,textvqa_val_exact_match,0.4564,0.006792248149691337
1082
- ≥5,11000,ai2d_exact_match,0.3403497409326425,0.008528080007639036
1083
- ≥5,11000,average,0.40311924614292627,
1084
- ≥5,11000,average_rank,4.2,
1085
- ≥5,11000,chartqa_relaxed_overall,0.5404,0.009969297405349211
1086
- ≥5,11000,docvqa_val_anls,0.5698821874786791,0.006251823346664307
1087
- ≥5,11000,infovqa_val_anls,0.22660700332356035,0.006919487246988994
1088
- ≥5,11000,mme_total_score,1358.4087635054022,
1089
- ≥5,11000,mmmu_val_mmmu_acc,0.28778,
1090
- ≥5,11000,mmstar_average,0.28965012568597354,
1091
- ≥5,11000,ocrbench_ocrbench_accuracy,0.436,
1092
- ≥5,11000,seedbench_seed_all,0.4714841578654808,
1093
- ≥5,11000,textvqa_val_exact_match,0.46592,0.006784225516827446
1094
- ≥5,12000,ai2d_exact_match,0.342940414507772,0.008543648986216495
1095
- ≥5,12000,average,0.4128131018529697,
1096
- ≥5,12000,average_rank,4.3,
1097
- ≥5,12000,chartqa_relaxed_overall,0.5548,0.009941746291659784
1098
- ≥5,12000,docvqa_val_anls,0.578981486161722,0.00625708617478689
1099
- ≥5,12000,infovqa_val_anls,0.2380032381589791,0.007080943870134072
1100
- ≥5,12000,mme_total_score,1390.3039215686274,
1101
- ≥5,12000,mmmu_val_mmmu_acc,0.28222,
1102
- ≥5,12000,mmstar_average,0.3060607822951693,
1103
- ≥5,12000,ocrbench_ocrbench_accuracy,0.472,
1104
- ≥5,12000,seedbench_seed_all,0.46559199555308506,
1105
- ≥5,12000,textvqa_val_exact_match,0.47472,0.006773519058221244
1106
- ≥5,13000,ai2d_exact_match,0.33678756476683935,0.008506208807020252
1107
- ≥5,13000,average,0.41416266738683244,
1108
- ≥5,13000,average_rank,4.5,
1109
- ≥5,13000,chartqa_relaxed_overall,0.5564,0.009938164963872337
1110
- ≥5,13000,docvqa_val_anls,0.5882749499950303,0.0062089530468064
1111
- ≥5,13000,infovqa_val_anls,0.2250291831460855,0.007008754051627638
1112
- ≥5,13000,mme_total_score,1463.7286914765905,
1113
- ≥5,13000,mmmu_val_mmmu_acc,0.28222,
1114
- ≥5,13000,mmstar_average,0.32070873992428756,
1115
- ≥5,13000,ocrbench_ocrbench_accuracy,0.475,
1116
- ≥5,13000,seedbench_seed_all,0.4624235686492496,
1117
- ≥5,13000,textvqa_val_exact_match,0.48062,0.006792356759039414
1118
- ≥5,14000,ai2d_exact_match,0.35103626943005184,0.008590489143063932
1119
- ≥5,14000,average,0.4197541703337554,
1120
- ≥5,14000,average_rank,4.4,
1121
- ≥5,14000,chartqa_relaxed_overall,0.5644,0.00991868984106597
1122
- ≥5,14000,docvqa_val_anls,0.5968397354218249,0.006216108072191749
1123
- ≥5,14000,infovqa_val_anls,0.23493831065135024,0.00713715521281919
1124
- ≥5,14000,mme_total_score,1381.4046618647458,
1125
- ≥5,14000,mmmu_val_mmmu_acc,0.28778,
1126
- ≥5,14000,mmstar_average,0.3178569306745569,
1127
- ≥5,14000,ocrbench_ocrbench_accuracy,0.465,
1128
- ≥5,14000,seedbench_seed_all,0.46931628682601445,
1129
- ≥5,14000,textvqa_val_exact_match,0.49062,0.0067877549928948315
1130
- ≥5,15000,ai2d_exact_match,0.3448834196891192,0.008555140353607656
1131
- ≥5,15000,average,0.4156222682362929,
1132
- ≥5,15000,average_rank,4.5,
1133
- ≥5,15000,chartqa_relaxed_overall,0.5544,0.009942625323290008
1134
- ≥5,15000,docvqa_val_anls,0.5981327465682499,0.0062119027314077434
1135
- ≥5,15000,infovqa_val_anls,0.2430496253387209,0.007241165402150032
1136
- ≥5,15000,mme_total_score,1405.2406962785115,
1137
- ≥5,15000,mmmu_val_mmmu_acc,0.27667,
1138
- ≥5,15000,mmstar_average,0.30769549523760537,
1139
- ≥5,15000,ocrbench_ocrbench_accuracy,0.462,
1140
- ≥5,15000,seedbench_seed_all,0.4724291272929405,
1141
- ≥5,15000,textvqa_val_exact_match,0.48134,0.006785688616050607
1142
- ≥5,16000,ai2d_exact_match,0.3555699481865285,0.008615532040064747
1143
- ≥5,16000,average,0.41928937760980056,
1144
- ≥5,16000,average_rank,4.6,
1145
- ≥5,16000,chartqa_relaxed_overall,0.556,0.00993907007952043
1146
- ≥5,16000,docvqa_val_anls,0.5950015990375694,0.006217949166028718
1147
- ≥5,16000,infovqa_val_anls,0.2429016453664355,0.007192121794741783
1148
- ≥5,16000,mme_total_score,1444.7096838735495,
1149
- ≥5,16000,mmmu_val_mmmu_acc,0.27222,
1150
- ≥5,16000,mmstar_average,0.29597997743741594,
1151
- ≥5,16000,ocrbench_ocrbench_accuracy,0.484,
1152
- ≥5,16000,seedbench_seed_all,0.4802112284602557,
1153
- ≥5,16000,textvqa_val_exact_match,0.49172000000000005,0.006790781344017229
1154
- ≥5,17000,ai2d_exact_match,0.35783678756476683,0.008627736835305362
1155
- ≥5,17000,average,0.4243671877798907,
1156
- ≥5,17000,average_rank,4.2,
1157
- ≥5,17000,chartqa_relaxed_overall,0.566,0.00991448025705367
1158
- ≥5,17000,docvqa_val_anls,0.6011648636453683,0.006202633675401635
1159
- ≥5,17000,infovqa_val_anls,0.24233190899997978,0.007185211142139982
1160
- ≥5,17000,mme_total_score,1383.0262104841936,
1161
- ≥5,17000,mmmu_val_mmmu_acc,0.29778,
1162
- ≥5,17000,mmstar_average,0.30487588800790116,
1163
- ≥5,17000,ocrbench_ocrbench_accuracy,0.48,
1164
- ≥5,17000,seedbench_seed_all,0.48343524180100056,
1165
- ≥5,17000,textvqa_val_exact_match,0.48588000000000003,0.006793096079908642
1166
- ≥5,18000,ai2d_exact_match,0.3484455958549223,0.008575797499263314
1167
- ≥5,18000,average,0.4229679292209723,
1168
- ≥5,18000,average_rank,4.4,
1169
- ≥5,18000,chartqa_relaxed_overall,0.5564,0.009938164963872337
1170
- ≥5,18000,docvqa_val_anls,0.6015112951191799,0.006202182626672507
1171
- ≥5,18000,infovqa_val_anls,0.2406225801562843,0.007159684093951319
1172
- ≥5,18000,mme_total_score,1388.7428971588636,
1173
- ≥5,18000,mmmu_val_mmmu_acc,0.29444,
1174
- ≥5,18000,mmstar_average,0.3048242431646457,
1175
- ≥5,18000,ocrbench_ocrbench_accuracy,0.489,
1176
- ≥5,18000,seedbench_seed_all,0.48176764869371874,
1177
- ≥5,18000,textvqa_val_exact_match,0.4897,0.006784304485905058
1178
- ≥5,19000,ai2d_exact_match,0.3552461139896373,0.00861377131101951
1179
- ≥5,19000,average,0.4271521214095191,
1180
- ≥5,19000,average_rank,4.4,
1181
- ≥5,19000,chartqa_relaxed_overall,0.564,0.009919725822025206
1182
- ≥5,19000,docvqa_val_anls,0.6030864459750552,0.006186369284106836
1183
- ≥5,19000,infovqa_val_anls,0.24933668460761893,0.007278561320407618
1184
- ≥5,19000,mme_total_score,1420.4112645058024,
1185
- ≥5,19000,mmmu_val_mmmu_acc,0.28889,
1186
- ≥5,19000,mmstar_average,0.3146239893029105,
1187
- ≥5,19000,ocrbench_ocrbench_accuracy,0.495,
1188
- ≥5,19000,seedbench_seed_all,0.48254585881045026,
1189
- ≥5,19000,textvqa_val_exact_match,0.49163999999999997,0.006786164784802775
1190
- ≥5,20000,ai2d_exact_match,0.3630181347150259,0.008654846701304475
1191
- ≥5,20000,average,0.4295614849660391,
1192
- ≥5,20000,average_rank,4.6,
1193
- ≥5,20000,chartqa_relaxed_overall,0.566,0.00991448025705367
1194
- ≥5,20000,docvqa_val_anls,0.6104819342838989,0.006177273769345363
1195
- ≥5,20000,infovqa_val_anls,0.24655527159214874,0.007266841528312276
1196
- ≥5,20000,mme_total_score,1413.0101040416166,
1197
- ≥5,20000,mmmu_val_mmmu_acc,0.28444,
1198
- ≥5,20000,mmstar_average,0.32507494461467334,
1199
- ≥5,20000,ocrbench_ocrbench_accuracy,0.499,
1200
- ≥5,20000,seedbench_seed_all,0.4775430794886048,
1201
- ≥5,20000,textvqa_val_exact_match,0.4939399999999999,0.006784796384004054
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5218781e5f018891311410d684785a3c661ca3cd25d2ac62bf45e6bb7d69e78
3
+ size 63268
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/content/assets/data/internal_deduplication.csv CHANGED
@@ -1,729 +1,3 @@
1
- run,step,metric,value,stderr
2
- Baseline,300,ai2d_exact_match,0.2551813471502591,0.007846598309236504
3
- Baseline,300,average,0.1836384379377178,
4
- Baseline,300,average_rank,1.4444444444444444,
5
- Baseline,300,chartqa_relaxed_overall,0.1328,0.006788526912302523
6
- Baseline,300,docvqa_val_anls,0.1503143424142802,0.004151727384820528
7
- Baseline,300,infovqa_val_anls,0.11374396685909084,0.005163280990095591
8
- Baseline,300,mme_total_score,691.1952781112445,
9
- Baseline,300,mmmu_val_mmmu_acc,0.26556,
10
- Baseline,300,mmstar_average,0.2859278470781123,
11
- Baseline,300,ocrbench_ocrbench_accuracy,0.149,
12
- Baseline,300,textvqa_val_exact_match,0.11657999999999999,0.004405144921606561
13
- Baseline,1500,ai2d_exact_match,0.27525906735751293,0.008038849490577982
14
- Baseline,1500,average,0.318819844462715,
15
- Baseline,1500,average_rank,1.2222222222222223,
16
- Baseline,1500,chartqa_relaxed_overall,0.374,0.009679208378267924
17
- Baseline,1500,docvqa_val_anls,0.437411196849637,0.0061765544267728045
18
- Baseline,1500,infovqa_val_anls,0.21582289145457856,0.006873661480889723
19
- Baseline,1500,mme_total_score,1066.704581832733,
20
- Baseline,1500,mmmu_val_mmmu_acc,0.24,
21
- Baseline,1500,mmstar_average,0.23474560003999134,
22
- Baseline,1500,ocrbench_ocrbench_accuracy,0.411,
23
- Baseline,1500,textvqa_val_exact_match,0.36232000000000003,0.006579840604488538
24
- Baseline,2700,ai2d_exact_match,0.27849740932642486,0.008067913113285858
25
- Baseline,2700,average,0.36471172748595665,
26
- Baseline,2700,average_rank,1.4444444444444444,
27
- Baseline,2700,chartqa_relaxed_overall,0.4624,0.00997367964766694
28
- Baseline,2700,docvqa_val_anls,0.4953558755845657,0.006275075768152338
29
- Baseline,2700,infovqa_val_anls,0.20975551937756792,0.006468441430093479
30
- Baseline,2700,mme_total_score,1172.469887955182,
31
- Baseline,2700,mmmu_val_mmmu_acc,0.27111,
32
- Baseline,2700,mmstar_average,0.2503150155990948,
33
- Baseline,2700,ocrbench_ocrbench_accuracy,0.486,
34
- Baseline,2700,textvqa_val_exact_match,0.46426000000000006,0.006792330795207658
35
- Baseline,3900,ai2d_exact_match,0.35038860103626945,0.008586842325753156
36
- Baseline,3900,average,0.398537125609502,
37
- Baseline,3900,average_rank,1.4444444444444444,
38
- Baseline,3900,chartqa_relaxed_overall,0.4948,0.010001459677380663
39
- Baseline,3900,docvqa_val_anls,0.5407649774017467,0.00626354456311192
40
- Baseline,3900,infovqa_val_anls,0.22943878312324553,0.006664668392753554
41
- Baseline,3900,mme_total_score,1168.9393757503,
42
- Baseline,3900,mmmu_val_mmmu_acc,0.27,
43
- Baseline,3900,mmstar_average,0.3015046433147543,
44
- Baseline,3900,ocrbench_ocrbench_accuracy,0.517,
45
- Baseline,3900,textvqa_val_exact_match,0.4844,0.006794038548018284
46
- Baseline,5100,ai2d_exact_match,0.3898963730569948,0.008778252852376944
47
- Baseline,5100,average,0.42767475240113806,
48
- Baseline,5100,average_rank,1.2222222222222223,
49
- Baseline,5100,chartqa_relaxed_overall,0.5264,0.009988048880946633
50
- Baseline,5100,docvqa_val_anls,0.5781350651939515,0.006244324391533268
51
- Baseline,5100,infovqa_val_anls,0.2546269175216946,0.007112814176935012
52
- Baseline,5100,mme_total_score,1185.1023409363747,
53
- Baseline,5100,mmmu_val_mmmu_acc,0.29222,
54
- Baseline,5100,mmstar_average,0.33637966343646347,
55
- Baseline,5100,ocrbench_ocrbench_accuracy,0.533,
56
- Baseline,5100,textvqa_val_exact_match,0.51074,0.0068004249599511925
57
- Baseline,6300,ai2d_exact_match,0.41515544041450775,0.00886864516657515
58
- Baseline,6300,average,0.43890688312888254,
59
- Baseline,6300,average_rank,1.4444444444444444,
60
- Baseline,6300,chartqa_relaxed_overall,0.5388,0.0099718403035556
61
- Baseline,6300,docvqa_val_anls,0.6024512173813115,0.006190216536053702
62
- Baseline,6300,infovqa_val_anls,0.2548412895443468,0.007030638027408485
63
- Baseline,6300,mme_total_score,1187.329431772709,
64
- Baseline,6300,mmmu_val_mmmu_acc,0.30667,
65
- Baseline,6300,mmstar_average,0.3500771176908943,
66
- Baseline,6300,ocrbench_ocrbench_accuracy,0.516,
67
- Baseline,6300,textvqa_val_exact_match,0.52726,0.006770298802059908
68
- Baseline,7500,ai2d_exact_match,0.42972797927461137,0.008909832364541428
69
- Baseline,7500,average,0.44878537461255386,
70
- Baseline,7500,average_rank,1.3333333333333333,
71
- Baseline,7500,chartqa_relaxed_overall,0.5728,0.009895414680177737
72
- Baseline,7500,docvqa_val_anls,0.6164034078362094,0.006122657396260068
73
- Baseline,7500,infovqa_val_anls,0.25244937386016403,0.006941949044716374
74
- Baseline,7500,mme_total_score,1282.560024009604,
75
- Baseline,7500,mmmu_val_mmmu_acc,0.29667,
76
- Baseline,7500,mmstar_average,0.3339722359294459,
77
- Baseline,7500,ocrbench_ocrbench_accuracy,0.558,
78
- Baseline,7500,textvqa_val_exact_match,0.5302600000000001,0.0067524799649562395
79
- Baseline,8700,ai2d_exact_match,0.44527202072538863,0.008945084019331404
80
- Baseline,8700,average,0.4558942646480554,
81
- Baseline,8700,average_rank,1.5555555555555556,
82
- Baseline,8700,chartqa_relaxed_overall,0.5852,0.009855721084488851
83
- Baseline,8700,docvqa_val_anls,0.6221835109907441,0.006147036255020746
84
- Baseline,8700,infovqa_val_anls,0.25900127209441604,0.006885435292484948
85
- Baseline,8700,mme_total_score,1182.047919167667,
86
- Baseline,8700,mmmu_val_mmmu_acc,0.30333,
87
- Baseline,8700,mmstar_average,0.3299073133738943,
88
- Baseline,8700,ocrbench_ocrbench_accuracy,0.559,
89
- Baseline,8700,textvqa_val_exact_match,0.54326,0.0067297527736521565
90
- Baseline,9900,ai2d_exact_match,0.4520725388601036,0.008957715852675529
91
- Baseline,9900,average,0.4655685311713072,
92
- Baseline,9900,average_rank,1.5555555555555556,
93
- Baseline,9900,chartqa_relaxed_overall,0.5888,0.009842996384797287
94
- Baseline,9900,docvqa_val_anls,0.6443822232919176,0.006072644236356477
95
- Baseline,9900,infovqa_val_anls,0.2707219279967856,0.007060292176646616
96
- Baseline,9900,mme_total_score,1293.4631852741097,
97
- Baseline,9900,mmmu_val_mmmu_acc,0.30444,
98
- Baseline,9900,mmstar_average,0.34327155922165065,
99
- Baseline,9900,ocrbench_ocrbench_accuracy,0.557,
100
- Baseline,9900,textvqa_val_exact_match,0.56386,0.006703146016110842
101
- Baseline,11100,ai2d_exact_match,0.4494818652849741,0.008953103134587198
102
- Baseline,11100,average,0.471077301321738,
103
- Baseline,11100,average_rank,1.6666666666666667,
104
- Baseline,11100,chartqa_relaxed_overall,0.5948,0.009820578470976232
105
- Baseline,11100,docvqa_val_anls,0.657973309294109,0.006015458191652746
106
- Baseline,11100,infovqa_val_anls,0.29696232573726855,0.007574623301736419
107
- Baseline,11100,mme_total_score,1338.3029211684673,
108
- Baseline,11100,mmmu_val_mmmu_acc,0.29667,
109
- Baseline,11100,mmstar_average,0.3394909102575524,
110
- Baseline,11100,ocrbench_ocrbench_accuracy,0.565,
111
- Baseline,11100,textvqa_val_exact_match,0.56824,0.006679879088496093
112
- Baseline,12300,ai2d_exact_match,0.4676165803108808,0.008980259712600086
113
- Baseline,12300,average,0.47342294699365395,
114
- Baseline,12300,average_rank,1.5555555555555556,
115
- Baseline,12300,chartqa_relaxed_overall,0.598,0.009808000752013664
116
- Baseline,12300,docvqa_val_anls,0.6588847758219586,0.00602421968017162
117
- Baseline,12300,infovqa_val_anls,0.2830975650419957,0.007216197962807829
118
- Baseline,12300,mme_total_score,1269.7461984793918,
119
- Baseline,12300,mmmu_val_mmmu_acc,0.28333,
120
- Baseline,12300,mmstar_average,0.3693946547743964,
121
- Baseline,12300,ocrbench_ocrbench_accuracy,0.559,
122
- Baseline,12300,textvqa_val_exact_match,0.5680599999999999,0.006686980665598219
123
- Baseline,13500,ai2d_exact_match,0.47085492227979275,0.008983852707691612
124
- Baseline,13500,average,0.48226394524672617,
125
- Baseline,13500,average_rank,1.5555555555555556,
126
- Baseline,13500,chartqa_relaxed_overall,0.618,0.009719474639861454
127
- Baseline,13500,docvqa_val_anls,0.6663692127257962,0.005978102603390597
128
- Baseline,13500,infovqa_val_anls,0.32051341945189793,0.007779116582967409
129
- Baseline,13500,mme_total_score,1202.768607442977,
130
- Baseline,13500,mmmu_val_mmmu_acc,0.28,
131
- Baseline,13500,mmstar_average,0.35477400751632243,
132
- Baseline,13500,ocrbench_ocrbench_accuracy,0.569,
133
- Baseline,13500,textvqa_val_exact_match,0.5785999999999999,0.006676145758177908
134
- Baseline,14700,ai2d_exact_match,0.46567357512953367,0.008977921602780724
135
- Baseline,14700,average,0.48621829332317545,
136
- Baseline,14700,average_rank,1.5555555555555556,
137
- Baseline,14700,chartqa_relaxed_overall,0.6296,0.0096601689190934
138
- Baseline,14700,docvqa_val_anls,0.6810941724065047,0.005910647813959628
139
- Baseline,14700,infovqa_val_anls,0.3016034504434661,0.007417514325399065
140
- Baseline,14700,mme_total_score,1281.9612845138056,
141
- Baseline,14700,mmmu_val_mmmu_acc,0.29778,
142
- Baseline,14700,mmstar_average,0.365895148605899,
143
- Baseline,14700,ocrbench_ocrbench_accuracy,0.562,
144
- Baseline,14700,textvqa_val_exact_match,0.5861,0.006642001297519238
145
- Baseline,15900,ai2d_exact_match,0.48186528497409326,0.008993233105757854
146
- Baseline,15900,average,0.48999290982002447,
147
- Baseline,15900,average_rank,1.5,
148
- Baseline,15900,chartqa_relaxed_overall,0.64,0.009601920576192066
149
- Baseline,15900,docvqa_val_anls,0.6858324657211811,0.00589619582327283
150
- Baseline,15900,infovqa_val_anls,0.2913749730393032,0.007302812648430173
151
- Baseline,15900,mme_total_score,1296.9955982392958,
152
- Baseline,15900,mmmu_val_mmmu_acc,0.29111,
153
- Baseline,15900,mmstar_average,0.35848055482561814,
154
- Baseline,15900,ocrbench_ocrbench_accuracy,0.581,
155
- Baseline,15900,textvqa_val_exact_match,0.59028,0.006635865524726405
156
- Baseline,17100,ai2d_exact_match,0.4740932642487047,0.008987066275159845
157
- Baseline,17100,average,0.4931189092163302,
158
- Baseline,17100,average_rank,1.7777777777777777,
159
- Baseline,17100,chartqa_relaxed_overall,0.644,0.009578219924326623
160
- Baseline,17100,docvqa_val_anls,0.6847803896363295,0.005919128355709122
161
- Baseline,17100,infovqa_val_anls,0.3018247984331409,0.007408081810180743
162
- Baseline,17100,mme_total_score,1262.8012204881952,
163
- Baseline,17100,mmmu_val_mmmu_acc,0.28444,
164
- Baseline,17100,mmstar_average,0.36583282141246676,
165
- Baseline,17100,ocrbench_ocrbench_accuracy,0.588,
166
- Baseline,17100,textvqa_val_exact_match,0.6019800000000001,0.0065905009567234045
167
- Baseline,18300,ai2d_exact_match,0.4876943005181347,0.008996428218289523
168
- Baseline,18300,average,0.5004883767088391,
169
- Baseline,18300,average_rank,1.5,
170
- Baseline,18300,chartqa_relaxed_overall,0.652,0.00952862623294433
171
- Baseline,18300,docvqa_val_anls,0.6975218894019752,0.005845051202995877
172
- Baseline,18300,infovqa_val_anls,0.3185079040699619,0.007608667971660477
173
- Baseline,18300,mme_total_score,1310.265706282513,
174
- Baseline,18300,mmmu_val_mmmu_acc,0.29556,
175
- Baseline,18300,mmstar_average,0.36108291968064027,
176
- Baseline,18300,ocrbench_ocrbench_accuracy,0.588,
177
- Baseline,18300,textvqa_val_exact_match,0.60354,0.006611280926348344
178
- Baseline,19500,ai2d_exact_match,0.47765544041450775,0.00899016344465196
179
- Baseline,19500,average,0.5040547762672563,
180
- Baseline,19500,average_rank,1.4444444444444444,
181
- Baseline,19500,chartqa_relaxed_overall,0.6552,0.009507962165354631
182
- Baseline,19500,docvqa_val_anls,0.7041825239698998,0.005808767160221614
183
- Baseline,19500,infovqa_val_anls,0.3209241432627218,0.007605560217474187
184
- Baseline,19500,mme_total_score,1295.3964585834333,
185
- Baseline,19500,mmmu_val_mmmu_acc,0.30333,
186
- Baseline,19500,mmstar_average,0.35936610249092044,
187
- Baseline,19500,ocrbench_ocrbench_accuracy,0.604,
188
- Baseline,19500,textvqa_val_exact_match,0.60778,0.006595164407254131
189
- Baseline,20700,ai2d_exact_match,0.49190414507772023,0.008997974381217105
190
- Baseline,20700,average,0.5348651598748863,
191
- Baseline,20700,average_rank,1.25,
192
- Baseline,20700,chartqa_relaxed_overall,0.6472,0.009558734841217527
193
- Baseline,20700,docvqa_val_anls,0.70377508713271,0.005815829966103309
194
- Baseline,20700,infovqa_val_anls,0.31228879567103124,0.0074592773891107925
195
- Baseline,20700,mme_total_score,1267.3561424569828,
196
- Baseline,20700,mmstar_average,0.36086809124274183,
197
- Baseline,20700,ocrbench_ocrbench_accuracy,0.605,
198
- Baseline,20700,textvqa_val_exact_match,0.62302,0.006536647571369781
199
- Baseline,21900,ai2d_exact_match,0.49125647668393785,0.008997778057794698
200
- Baseline,21900,average,0.5035549318138456,
201
- Baseline,21900,average_rank,1.4444444444444444,
202
- Baseline,21900,chartqa_relaxed_overall,0.6556,0.009505345687488459
203
- Baseline,21900,docvqa_val_anls,0.7044656227681543,0.005797355786446792
204
- Baseline,21900,infovqa_val_anls,0.3214548388700204,0.007656455061893302
205
- Baseline,21900,mme_total_score,1270.262104841937,
206
- Baseline,21900,mmmu_val_mmmu_acc,0.28111,
207
- Baseline,21900,mmstar_average,0.36167251618865237,
208
- Baseline,21900,ocrbench_ocrbench_accuracy,0.597,
209
- Baseline,21900,textvqa_val_exact_match,0.61588,0.006563701818052925
210
- Baseline,23100,ai2d_exact_match,0.49319948186528495,0.008998321712163856
211
- Baseline,23100,average,0.5385543058304301,
212
- Baseline,23100,average_rank,1.5,
213
- Baseline,23100,chartqa_relaxed_overall,0.6592,0.009481461028833927
214
- Baseline,23100,docvqa_val_anls,0.7121972356483652,0.005769225218375019
215
- Baseline,23100,infovqa_val_anls,0.31967136620122777,0.007611618366213475
216
- Baseline,23100,mme_total_score,1318.2786114445778,
217
- Baseline,23100,mmstar_average,0.3630320570981325,
218
- Baseline,23100,ocrbench_ocrbench_accuracy,0.602,
219
- Baseline,23100,textvqa_val_exact_match,0.62058,0.006524799408523169
220
- Baseline,24300,ai2d_exact_match,0.49255181347150256,0.008998155599035915
221
- Baseline,24300,average,0.5094308504545716,
222
- Baseline,24300,average_rank,1.5555555555555556,
223
- Baseline,24300,chartqa_relaxed_overall,0.6704,0.009403239035659185
224
- Baseline,24300,docvqa_val_anls,0.7177853964151442,0.005720014481294498
225
- Baseline,24300,infovqa_val_anls,0.31972012794378407,0.007606738233281323
226
- Baseline,24300,mme_total_score,1306.592336934774,
227
- Baseline,24300,mmmu_val_mmmu_acc,0.29778,
228
- Baseline,24300,mmstar_average,0.37076946580614156,
229
- Baseline,24300,ocrbench_ocrbench_accuracy,0.59,
230
- Baseline,24300,textvqa_val_exact_match,0.6164400000000001,0.006543401905866729
231
- Baseline,25500,ai2d_exact_match,0.501619170984456,0.008999106932714636
232
- Baseline,25500,average,0.5486249165918439,
233
- Baseline,25500,average_rank,1.625,
234
- Baseline,25500,chartqa_relaxed_overall,0.6752,0.00936787525721462
235
- Baseline,25500,docvqa_val_anls,0.7137288248520355,0.0057597420625403505
236
- Baseline,25500,infovqa_val_anls,0.34135511904919924,0.0077802284678825705
237
- Baseline,25500,mme_total_score,1323.6883753501402,
238
- Baseline,25500,mmstar_average,0.369071301257217,
239
- Baseline,25500,ocrbench_ocrbench_accuracy,0.619,
240
- Baseline,25500,textvqa_val_exact_match,0.6204,0.00653548089294892
241
- Baseline,26700,ai2d_exact_match,0.4990284974093264,0.008999137132137064
242
- Baseline,26700,average,0.5171016246428288,
243
- Baseline,26700,average_rank,1.4444444444444444,
244
- Baseline,26700,chartqa_relaxed_overall,0.6712,0.009397422445513864
245
- Baseline,26700,docvqa_val_anls,0.7233130041233962,0.005709000608468465
246
- Baseline,26700,infovqa_val_anls,0.34093933218960265,0.007871398735359877
247
- Baseline,26700,mme_total_score,1290.1798719487797,
248
- Baseline,26700,mmmu_val_mmmu_acc,0.29889,
249
- Baseline,26700,mmstar_average,0.3681821634203056,
250
- Baseline,26700,ocrbench_ocrbench_accuracy,0.602,
251
- Baseline,26700,textvqa_val_exact_match,0.63326,0.006491932186699375
252
- Baseline,27900,ai2d_exact_match,0.49773316062176165,0.008999061633391479
253
- Baseline,27900,average,0.5456332793229398,
254
- Baseline,27900,average_rank,1.625,
255
- Baseline,27900,chartqa_relaxed_overall,0.6756,0.009364877808842454
256
- Baseline,27900,docvqa_val_anls,0.7132690678246167,0.00575358310740901
257
- Baseline,27900,infovqa_val_anls,0.3362338249924974,0.007684149470716349
258
- Baseline,27900,mme_total_score,1267.1172468987595,
259
- Baseline,27900,mmstar_average,0.3725169018217032,
260
- Baseline,27900,ocrbench_ocrbench_accuracy,0.599,
261
- Baseline,27900,textvqa_val_exact_match,0.62508,0.006518059200340837
262
- Baseline,29100,ai2d_exact_match,0.5019430051813472,0.008999086170553228
263
- Baseline,29100,average,0.5238317316407767,
264
- Baseline,29100,average_rank,1.0,
265
- Baseline,29100,chartqa_relaxed_overall,0.6828,0.009309582768982347
266
- Baseline,29100,docvqa_val_anls,0.7233823673869951,0.005705166797815572
267
- Baseline,29100,infovqa_val_anls,0.34214735285161113,0.007759163899965965
268
- Baseline,29100,mme_total_score,1321.8040216086433,
269
- Baseline,29100,mmmu_val_mmmu_acc,0.31222,
270
- Baseline,29100,mmstar_average,0.3709411277062599,
271
- Baseline,29100,ocrbench_ocrbench_accuracy,0.622,
272
- Baseline,29100,textvqa_val_exact_match,0.6352199999999999,0.00647159073314463
273
- Baseline,30300,ai2d_exact_match,0.5055051813471503,0.008998608627616667
274
- Baseline,30300,average,0.5497034826600226,
275
- Baseline,30300,average_rank,1.375,
276
- Baseline,30300,chartqa_relaxed_overall,0.6784,0.009343676884347384
277
- Baseline,30300,docvqa_val_anls,0.7227075209990185,0.005720573311731873
278
- Baseline,30300,infovqa_val_anls,0.33249900926543363,0.007751325884024483
279
- Baseline,30300,mme_total_score,1290.3790516206482,
280
- Baseline,30300,mmstar_average,0.36331266700855536,
281
- Baseline,30300,ocrbench_ocrbench_accuracy,0.612,
282
- Baseline,30300,textvqa_val_exact_match,0.6335,0.006488911402865572
283
- Baseline,31500,ai2d_exact_match,0.4993523316062176,0.008999146569435543
284
- Baseline,31500,average,0.5220721222554265,
285
- Baseline,31500,average_rank,1.5555555555555556,
286
- Baseline,31500,chartqa_relaxed_overall,0.6872,0.009274528060677767
287
- Baseline,31500,docvqa_val_anls,0.732681296661989,0.005643494305560718
288
- Baseline,31500,infovqa_val_anls,0.34453436089995576,0.007841367492503165
289
- Baseline,31500,mme_total_score,1304.8996598639455,
290
- Baseline,31500,mmmu_val_mmmu_acc,0.29444,
291
- Baseline,31500,mmstar_average,0.37192898887525,
292
- Baseline,31500,ocrbench_ocrbench_accuracy,0.61,
293
- Baseline,31500,textvqa_val_exact_match,0.63644,0.006473052244580776
294
- Baseline,32700,ai2d_exact_match,0.49870466321243523,0.00899912391990207
295
- Baseline,32700,average,0.5546837276191249,
296
- Baseline,32700,average_rank,1.5,
297
- Baseline,32700,chartqa_relaxed_overall,0.68,0.009331389496316869
298
- Baseline,32700,docvqa_val_anls,0.7278962076951819,0.005686137433507678
299
- Baseline,32700,infovqa_val_anls,0.3359004823603636,0.007743137801806592
300
- Baseline,32700,mme_total_score,1329.2223889555821,
301
- Baseline,32700,mmstar_average,0.3761847400658931,
302
- Baseline,32700,ocrbench_ocrbench_accuracy,0.626,
303
- Baseline,32700,textvqa_val_exact_match,0.6381000000000001,0.006469625121275727
304
- Baseline,33900,ai2d_exact_match,0.5019430051813472,0.00899908617055323
305
- Baseline,33900,average,0.5185104134885045,
306
- Baseline,33900,average_rank,1.5555555555555556,
307
- Baseline,33900,chartqa_relaxed_overall,0.6784,0.009343676884347384
308
- Baseline,33900,docvqa_val_anls,0.7328401883203162,0.005641229328683336
309
- Baseline,33900,infovqa_val_anls,0.33727943427582574,0.0077500601420040695
310
- Baseline,33900,mme_total_score,1330.3196278511405,
311
- Baseline,33900,mmmu_val_mmmu_acc,0.28,
312
- Baseline,33900,mmstar_average,0.3640006801305467,
313
- Baseline,33900,ocrbench_ocrbench_accuracy,0.617,
314
- Baseline,33900,textvqa_val_exact_match,0.63662,0.006467562214018388
315
- Baseline,35100,ai2d_exact_match,0.5029145077720207,0.008999001233939133
316
- Baseline,35100,average,0.5522905800868071,
317
- Baseline,35100,average_rank,1.625,
318
- Baseline,35100,chartqa_relaxed_overall,0.68,0.009331389496316869
319
- Baseline,35100,docvqa_val_anls,0.7269648828481717,0.005683622810231662
320
- Baseline,35100,infovqa_val_anls,0.33846207838337145,0.00774681529996113
321
- Baseline,35100,mme_total_score,1299.1129451780712,
322
- Baseline,35100,mmstar_average,0.36183259160408615,
323
- Baseline,35100,ocrbench_ocrbench_accuracy,0.616,
324
- Baseline,35100,textvqa_val_exact_match,0.63986,0.0064564830453322595
325
- Baseline,36300,ai2d_exact_match,0.501619170984456,0.008999106932714636
326
- Baseline,36300,average,0.5203510175588769,
327
- Baseline,36300,average_rank,1.4444444444444444,
328
- Baseline,36300,chartqa_relaxed_overall,0.6808,0.009325198535746702
329
- Baseline,36300,docvqa_val_anls,0.7270212281583848,0.0056833541878296414
330
- Baseline,36300,infovqa_val_anls,0.3340392024865933,0.007611756166885497
331
- Baseline,36300,mme_total_score,1280.1442577030812,
332
- Baseline,36300,mmmu_val_mmmu_acc,0.30111,
333
- Baseline,36300,mmstar_average,0.36247853884158143,
334
- Baseline,36300,ocrbench_ocrbench_accuracy,0.615,
335
- Baseline,36300,textvqa_val_exact_match,0.64074,0.0064493076522863105
336
- Baseline,37500,ai2d_exact_match,0.5074481865284974,0.008998155599035891
337
- Baseline,37500,average,0.5599086924183005,
338
- Baseline,37500,average_rank,1.25,
339
- Baseline,37500,chartqa_relaxed_overall,0.69,0.009251715392027472
340
- Baseline,37500,docvqa_val_anls,0.7338638293909314,0.005628628195159443
341
- Baseline,37500,infovqa_val_anls,0.35075945776545553,0.007880392253956911
342
- Baseline,37500,mme_total_score,1308.0833333333333,
343
- Baseline,37500,mmstar_average,0.37624937324321944,
344
- Baseline,37500,ocrbench_ocrbench_accuracy,0.622,
345
- Baseline,37500,textvqa_val_exact_match,0.63904,0.006478670412520058
346
- Baseline,38700,ai2d_exact_match,0.5,0.008999154119267315
347
- Baseline,38700,average,0.5225140432328732,
348
- Baseline,38700,average_rank,1.5555555555555556,
349
- Baseline,38700,chartqa_relaxed_overall,0.6832,0.009306435832216308
350
- Baseline,38700,docvqa_val_anls,0.73088808708227,0.00563114482117092
351
- Baseline,38700,infovqa_val_anls,0.3478216232204623,0.00789714223139076
352
- Baseline,38700,mme_total_score,1277.5526210484195,
353
- Baseline,38700,mmmu_val_mmmu_acc,0.28667,
354
- Baseline,38700,mmstar_average,0.3681926355602532,
355
- Baseline,38700,ocrbench_ocrbench_accuracy,0.624,
356
- Baseline,38700,textvqa_val_exact_match,0.6393399999999999,0.00647079957419683
357
- Baseline,39900,ai2d_exact_match,0.5058290155440415,0.008998542562369288
358
- Baseline,39900,average,0.5567573845010034,
359
- Baseline,39900,average_rank,1.375,
360
- Baseline,39900,chartqa_relaxed_overall,0.6788,0.00934061683451043
361
- Baseline,39900,docvqa_val_anls,0.7307115103048833,0.005666517404544185
362
- Baseline,39900,infovqa_val_anls,0.3519024541637205,0.007911172051974351
363
- Baseline,39900,mme_total_score,1294.3033213285314,
364
- Baseline,39900,mmstar_average,0.36969871149437833,
365
- Baseline,39900,ocrbench_ocrbench_accuracy,0.619,
366
- Baseline,39900,textvqa_val_exact_match,0.6413599999999999,0.006448549204074314
367
- Internal Deduplication,300,ai2d_exact_match,0.2503238341968912,0.007796858242572104
368
- Internal Deduplication,300,average,0.19412722789194248,
369
- Internal Deduplication,300,average_rank,1.5555555555555556,
370
- Internal Deduplication,300,chartqa_relaxed_overall,0.1412,0.0069659481604092775
371
- Internal Deduplication,300,docvqa_val_anls,0.15637861297756628,0.004267695603476823
372
- Internal Deduplication,300,infovqa_val_anls,0.1042887841127396,0.005046536381262501
373
- Internal Deduplication,300,mme_total_score,598.6149459783913,
374
- Internal Deduplication,300,mmmu_val_mmmu_acc,0.26556,
375
- Internal Deduplication,300,mmstar_average,0.2694265918483427,
376
- Internal Deduplication,300,ocrbench_ocrbench_accuracy,0.167,
377
- Internal Deduplication,300,textvqa_val_exact_match,0.19884000000000002,0.005492264002465154
378
- Internal Deduplication,1500,ai2d_exact_match,0.27299222797927464,0.008018190192865413
379
- Internal Deduplication,1500,average,0.31955460499150806,
380
- Internal Deduplication,1500,average_rank,1.7777777777777777,
381
- Internal Deduplication,1500,chartqa_relaxed_overall,0.3708,0.00966231277258432
382
- Internal Deduplication,1500,docvqa_val_anls,0.42768709568231533,0.006154040400291129
383
- Internal Deduplication,1500,infovqa_val_anls,0.2099303690224102,0.00676857279363082
384
- Internal Deduplication,1500,mme_total_score,992.9132653061225,
385
- Internal Deduplication,1500,mmmu_val_mmmu_acc,0.26889,
386
- Internal Deduplication,1500,mmstar_average,0.21057714724806412,
387
- Internal Deduplication,1500,ocrbench_ocrbench_accuracy,0.404,
388
- Internal Deduplication,1500,textvqa_val_exact_match,0.39155999999999996,0.006665511164780805
389
- Internal Deduplication,2700,ai2d_exact_match,0.295660621761658,0.008213332656949247
390
- Internal Deduplication,2700,average,0.36762151428382045,
391
- Internal Deduplication,2700,average_rank,1.5555555555555556,
392
- Internal Deduplication,2700,chartqa_relaxed_overall,0.4752,0.009989689762981844
393
- Internal Deduplication,2700,docvqa_val_anls,0.5094800317043119,0.006254649346492251
394
- Internal Deduplication,2700,infovqa_val_anls,0.20719401979989327,0.006520807933324386
395
- Internal Deduplication,2700,mme_total_score,1071.3925570228091,
396
- Internal Deduplication,2700,mmmu_val_mmmu_acc,0.27,
397
- Internal Deduplication,2700,mmstar_average,0.2397774410047003,
398
- Internal Deduplication,2700,ocrbench_ocrbench_accuracy,0.494,
399
- Internal Deduplication,2700,textvqa_val_exact_match,0.44965999999999995,0.006770608917152268
400
- Internal Deduplication,3900,ai2d_exact_match,0.35751295336787564,0.008626006165018857
401
- Internal Deduplication,3900,average,0.40092708598125315,
402
- Internal Deduplication,3900,average_rank,1.5555555555555556,
403
- Internal Deduplication,3900,chartqa_relaxed_overall,0.5108,0.009999667061284322
404
- Internal Deduplication,3900,docvqa_val_anls,0.5404721998847206,0.0062378368939630035
405
- Internal Deduplication,3900,infovqa_val_anls,0.22349780573998537,0.006643570027298634
406
- Internal Deduplication,3900,mme_total_score,1134.516706682673,
407
- Internal Deduplication,3900,mmmu_val_mmmu_acc,0.29111,
408
- Internal Deduplication,3900,mmstar_average,0.27976372885744333,
409
- Internal Deduplication,3900,ocrbench_ocrbench_accuracy,0.51,
410
- Internal Deduplication,3900,textvqa_val_exact_match,0.49426000000000003,0.006797576913163843
411
- Internal Deduplication,5100,ai2d_exact_match,0.38827720207253885,0.008771623130477878
412
- Internal Deduplication,5100,average,0.4219485735226934,
413
- Internal Deduplication,5100,average_rank,1.7777777777777777,
414
- Internal Deduplication,5100,chartqa_relaxed_overall,0.5236,0.009990852959439592
415
- Internal Deduplication,5100,docvqa_val_anls,0.5747949496010799,0.006245322873999332
416
- Internal Deduplication,5100,infovqa_val_anls,0.2283558074433608,0.006643505571541433
417
- Internal Deduplication,5100,mme_total_score,1120.3775510204082,
418
- Internal Deduplication,5100,mmmu_val_mmmu_acc,0.27444,
419
- Internal Deduplication,5100,mmstar_average,0.32262062906456745,
420
- Internal Deduplication,5100,ocrbench_ocrbench_accuracy,0.546,
421
- Internal Deduplication,5100,textvqa_val_exact_match,0.5175,0.006791610648074506
422
- Internal Deduplication,6300,ai2d_exact_match,0.3947538860103627,0.008797532848529212
423
- Internal Deduplication,6300,average,0.4392913905300591,
424
- Internal Deduplication,6300,average_rank,1.5555555555555556,
425
- Internal Deduplication,6300,chartqa_relaxed_overall,0.554,0.009943497838271193
426
- Internal Deduplication,6300,docvqa_val_anls,0.6054354573141266,0.006148692369883667
427
- Internal Deduplication,6300,infovqa_val_anls,0.2479668172159887,0.006849066135124891
428
- Internal Deduplication,6300,mme_total_score,1120.747699079632,
429
- Internal Deduplication,6300,mmmu_val_mmmu_acc,0.28222,
430
- Internal Deduplication,6300,mmstar_average,0.33081496369999497,
431
- Internal Deduplication,6300,ocrbench_ocrbench_accuracy,0.562,
432
- Internal Deduplication,6300,textvqa_val_exact_match,0.53714,0.00675218797787041
433
- Internal Deduplication,7500,ai2d_exact_match,0.4368523316062176,0.008927095061184939
434
- Internal Deduplication,7500,average,0.4484625925841701,
435
- Internal Deduplication,7500,average_rank,1.6666666666666667,
436
- Internal Deduplication,7500,chartqa_relaxed_overall,0.5716,0.009898917689756362
437
- Internal Deduplication,7500,docvqa_val_anls,0.6158904129878224,0.006156668221029065
438
- Internal Deduplication,7500,infovqa_val_anls,0.2491041330885082,0.006950914810318631
439
- Internal Deduplication,7500,mme_total_score,1182.0997398959585,
440
- Internal Deduplication,7500,mmmu_val_mmmu_acc,0.30222,
441
- Internal Deduplication,7500,mmstar_average,0.3126938629908125,
442
- Internal Deduplication,7500,ocrbench_ocrbench_accuracy,0.554,
443
- Internal Deduplication,7500,textvqa_val_exact_match,0.5453399999999999,0.006743052026354684
444
- Internal Deduplication,8700,ai2d_exact_match,0.43555699481865284,0.008924095913829722
445
- Internal Deduplication,8700,average,0.4610890710492869,
446
- Internal Deduplication,8700,average_rank,1.4444444444444444,
447
- Internal Deduplication,8700,chartqa_relaxed_overall,0.5856,0.009854334029231191
448
- Internal Deduplication,8700,docvqa_val_anls,0.6337792662388687,0.006121292484093459
449
- Internal Deduplication,8700,infovqa_val_anls,0.3014589775424448,0.007723778532370607
450
- Internal Deduplication,8700,mme_total_score,1146.702080832333,
451
- Internal Deduplication,8700,mmmu_val_mmmu_acc,0.28111,
452
- Internal Deduplication,8700,mmstar_average,0.34138732979432873,
453
- Internal Deduplication,8700,ocrbench_ocrbench_accuracy,0.554,
454
- Internal Deduplication,8700,textvqa_val_exact_match,0.5558200000000001,0.006722310868494742
455
- Internal Deduplication,9900,ai2d_exact_match,0.4530440414507772,0.008959382447335284
456
- Internal Deduplication,9900,average,0.4640919637505932,
457
- Internal Deduplication,9900,average_rank,1.4444444444444444,
458
- Internal Deduplication,9900,chartqa_relaxed_overall,0.596,0.009815912634917984
459
- Internal Deduplication,9900,docvqa_val_anls,0.6449581300442709,0.006031449307242489
460
- Internal Deduplication,9900,infovqa_val_anls,0.2651241729320676,0.007027677036596941
461
- Internal Deduplication,9900,mme_total_score,1198.2277911164465,
462
- Internal Deduplication,9900,mmmu_val_mmmu_acc,0.28,
463
- Internal Deduplication,9900,mmstar_average,0.33564936557763,
464
- Internal Deduplication,9900,ocrbench_ocrbench_accuracy,0.571,
465
- Internal Deduplication,9900,textvqa_val_exact_match,0.5669599999999999,0.0067004067615447065
466
- Internal Deduplication,11100,ai2d_exact_match,0.4566062176165803,0.008965198879336196
467
- Internal Deduplication,11100,average,0.4745786301209996,
468
- Internal Deduplication,11100,average_rank,1.3333333333333333,
469
- Internal Deduplication,11100,chartqa_relaxed_overall,0.608,0.00976588700628918
470
- Internal Deduplication,11100,docvqa_val_anls,0.6596743239996393,0.005996833864420919
471
- Internal Deduplication,11100,infovqa_val_anls,0.30142039609988674,0.0075421730872732295
472
- Internal Deduplication,11100,mme_total_score,1136.5589235694279,
473
- Internal Deduplication,11100,mmmu_val_mmmu_acc,0.29,
474
- Internal Deduplication,11100,mmstar_average,0.32532810325189065,
475
- Internal Deduplication,11100,ocrbench_ocrbench_accuracy,0.586,
476
- Internal Deduplication,11100,textvqa_val_exact_match,0.5696,0.00669753233570974
477
- Internal Deduplication,12300,ai2d_exact_match,0.47085492227979275,0.0089838527076916
478
- Internal Deduplication,12300,average,0.47675266119609205,
479
- Internal Deduplication,12300,average_rank,1.4444444444444444,
480
- Internal Deduplication,12300,chartqa_relaxed_overall,0.6024,0.009789996609470577
481
- Internal Deduplication,12300,docvqa_val_anls,0.6541921314490913,0.0059901948837693935
482
- Internal Deduplication,12300,infovqa_val_anls,0.26890492643687214,0.0068929334847927185
483
- Internal Deduplication,12300,mme_total_score,1180.1697679071628,
484
- Internal Deduplication,12300,mmmu_val_mmmu_acc,0.30111,
485
- Internal Deduplication,12300,mmstar_average,0.3420593094029801,
486
- Internal Deduplication,12300,ocrbench_ocrbench_accuracy,0.588,
487
- Internal Deduplication,12300,textvqa_val_exact_match,0.5865000000000001,0.006650353031162167
488
- Internal Deduplication,13500,ai2d_exact_match,0.4689119170984456,0.008981742470016596
489
- Internal Deduplication,13500,average,0.477194042186954,
490
- Internal Deduplication,13500,average_rank,1.4444444444444444,
491
- Internal Deduplication,13500,chartqa_relaxed_overall,0.6076,0.009767653701044555
492
- Internal Deduplication,13500,docvqa_val_anls,0.6669529256090054,0.005964340335624923
493
- Internal Deduplication,13500,infovqa_val_anls,0.28048200541677026,0.00715533754622952
494
- Internal Deduplication,13500,mme_total_score,1205.548119247699,
495
- Internal Deduplication,13500,mmmu_val_mmmu_acc,0.28556,
496
- Internal Deduplication,13500,mmstar_average,0.3358454893714108,
497
- Internal Deduplication,13500,ocrbench_ocrbench_accuracy,0.589,
498
- Internal Deduplication,13500,textvqa_val_exact_match,0.5832,0.006654352566675162
499
- Internal Deduplication,14700,ai2d_exact_match,0.47733160621761656,0.008989900821900263
500
- Internal Deduplication,14700,average,0.4884023663438535,
501
- Internal Deduplication,14700,average_rank,1.4444444444444444,
502
- Internal Deduplication,14700,chartqa_relaxed_overall,0.6304,0.009655859891905061
503
- Internal Deduplication,14700,docvqa_val_anls,0.6801802838124448,0.005922660123416213
504
- Internal Deduplication,14700,infovqa_val_anls,0.306442807638199,0.007585813874676366
505
- Internal Deduplication,14700,mme_total_score,1141.5065026010404,
506
- Internal Deduplication,14700,mmmu_val_mmmu_acc,0.28556,
507
- Internal Deduplication,14700,mmstar_average,0.3313042330825678,
508
- Internal Deduplication,14700,ocrbench_ocrbench_accuracy,0.601,
509
- Internal Deduplication,14700,textvqa_val_exact_match,0.595,0.006618682753560443
510
- Internal Deduplication,15900,ai2d_exact_match,0.48737046632124353,0.0089962828388782
511
- Internal Deduplication,15900,average,0.5203517701538484,
512
- Internal Deduplication,15900,average_rank,1.5,
513
- Internal Deduplication,15900,chartqa_relaxed_overall,0.6268,0.009675026948726469
514
- Internal Deduplication,15900,docvqa_val_anls,0.6832159326200654,0.005900840845629961
515
- Internal Deduplication,15900,infovqa_val_anls,0.3152545751330662,0.007651477632904633
516
- Internal Deduplication,15900,mme_total_score,1225.4948979591836,
517
- Internal Deduplication,15900,mmstar_average,0.32764141700256333,
518
- Internal Deduplication,15900,ocrbench_ocrbench_accuracy,0.603,
519
- Internal Deduplication,15900,textvqa_val_exact_match,0.5991799999999999,0.006605224547149299
520
- Internal Deduplication,17100,ai2d_exact_match,0.47636010362694303,0.008989090232793597
521
- Internal Deduplication,17100,average,0.4961663419392575,
522
- Internal Deduplication,17100,average_rank,1.2222222222222223,
523
- Internal Deduplication,17100,chartqa_relaxed_overall,0.6464,0.009563650001989001
524
- Internal Deduplication,17100,docvqa_val_anls,0.6927261914773173,0.005861047908265113
525
- Internal Deduplication,17100,infovqa_val_anls,0.3154358494585615,0.00763456160506387
526
- Internal Deduplication,17100,mme_total_score,1286.2750100040016,
527
- Internal Deduplication,17100,mmmu_val_mmmu_acc,0.29889,
528
- Internal Deduplication,17100,mmstar_average,0.34921859095123836,
529
- Internal Deduplication,17100,ocrbench_ocrbench_accuracy,0.587,
530
- Internal Deduplication,17100,textvqa_val_exact_match,0.6033,0.006602767700613255
531
- Internal Deduplication,18300,ai2d_exact_match,0.4786269430051813,0.008990928596702264
532
- Internal Deduplication,18300,average,0.5266473503807093,
533
- Internal Deduplication,18300,average_rank,1.5,
534
- Internal Deduplication,18300,chartqa_relaxed_overall,0.6552,0.009507962165354631
535
- Internal Deduplication,18300,docvqa_val_anls,0.6989798369115747,0.00583327960847754
536
- Internal Deduplication,18300,infovqa_val_anls,0.31662733272229215,0.00758318378302427
537
- Internal Deduplication,18300,mme_total_score,1217.9891956782712,
538
- Internal Deduplication,18300,mmstar_average,0.3360973400259174,
539
- Internal Deduplication,18300,ocrbench_ocrbench_accuracy,0.595,
540
- Internal Deduplication,18300,textvqa_val_exact_match,0.6060000000000001,0.006592108249887561
541
- Internal Deduplication,19500,ai2d_exact_match,0.4896373056994819,0.008997221155546277
542
- Internal Deduplication,19500,average,0.5003413312777834,
543
- Internal Deduplication,19500,average_rank,1.5555555555555556,
544
- Internal Deduplication,19500,chartqa_relaxed_overall,0.6508,0.009536252935404934
545
- Internal Deduplication,19500,docvqa_val_anls,0.7013552478733074,0.005824977752328648
546
- Internal Deduplication,19500,infovqa_val_anls,0.32620790060169225,0.007764453086996403
547
- Internal Deduplication,19500,mme_total_score,1299.4400760304122,
548
- Internal Deduplication,19500,mmmu_val_mmmu_acc,0.29556,
549
- Internal Deduplication,19500,mmstar_average,0.3368301960477849,
550
- Internal Deduplication,19500,ocrbench_ocrbench_accuracy,0.593,
551
- Internal Deduplication,19500,textvqa_val_exact_match,0.60934,0.006559905437723197
552
- Internal Deduplication,20700,ai2d_exact_match,0.4889896373056995,0.008996971954224612
553
- Internal Deduplication,20700,average,0.5296276786578733,
554
- Internal Deduplication,20700,average_rank,1.75,
555
- Internal Deduplication,20700,chartqa_relaxed_overall,0.6444,0.009575809858898698
556
- Internal Deduplication,20700,docvqa_val_anls,0.6989112987356239,0.00585808944665685
557
- Internal Deduplication,20700,infovqa_val_anls,0.3158264619814475,0.007568423570507376
558
- Internal Deduplication,20700,mme_total_score,1174.7768107242898,
559
- Internal Deduplication,20700,mmstar_average,0.33400635258234235,
560
- Internal Deduplication,20700,ocrbench_ocrbench_accuracy,0.614,
561
- Internal Deduplication,20700,textvqa_val_exact_match,0.6112599999999999,0.0065589363778955695
562
- Internal Deduplication,21900,ai2d_exact_match,0.4957901554404145,0.008998835133354702
563
- Internal Deduplication,21900,average,0.5035083877228906,
564
- Internal Deduplication,21900,average_rank,1.5555555555555556,
565
- Internal Deduplication,21900,chartqa_relaxed_overall,0.64,0.009601920576192066
566
- Internal Deduplication,21900,docvqa_val_anls,0.7037412472922321,0.005813532329025727
567
- Internal Deduplication,21900,infovqa_val_anls,0.3194560697014221,0.007649647661031666
568
- Internal Deduplication,21900,mme_total_score,1199.6734693877552,
569
- Internal Deduplication,21900,mmmu_val_mmmu_acc,0.30889,
570
- Internal Deduplication,21900,mmstar_average,0.33692962934905674,
571
- Internal Deduplication,21900,ocrbench_ocrbench_accuracy,0.603,
572
- Internal Deduplication,21900,textvqa_val_exact_match,0.6202599999999999,0.006539392877923941
573
- Internal Deduplication,23100,ai2d_exact_match,0.4944948186528497,0.008998608627616672
574
- Internal Deduplication,23100,average,0.5413853458503779,
575
- Internal Deduplication,23100,average_rank,1.5,
576
- Internal Deduplication,23100,chartqa_relaxed_overall,0.646,0.009566096595876119
577
- Internal Deduplication,23100,docvqa_val_anls,0.7101587999220607,0.005806193919644477
578
- Internal Deduplication,23100,infovqa_val_anls,0.336754873549068,0.007886540099947482
579
- Internal Deduplication,23100,mme_total_score,1316.6187474989997,
580
- Internal Deduplication,23100,mmstar_average,0.3476289288286667,
581
- Internal Deduplication,23100,ocrbench_ocrbench_accuracy,0.627,
582
- Internal Deduplication,23100,textvqa_val_exact_match,0.62766,0.006520482207447814
583
- Internal Deduplication,24300,ai2d_exact_match,0.4899611398963731,0.008997340090107673
584
- Internal Deduplication,24300,average,0.5100750686661266,
585
- Internal Deduplication,24300,average_rank,1.4444444444444444,
586
- Internal Deduplication,24300,chartqa_relaxed_overall,0.6516,0.009531175862679805
587
- Internal Deduplication,24300,docvqa_val_anls,0.7179021844889384,0.005742973360829408
588
- Internal Deduplication,24300,infovqa_val_anls,0.3358758923979091,0.007878017215252312
589
- Internal Deduplication,24300,mme_total_score,1409.844237695078,
590
- Internal Deduplication,24300,mmmu_val_mmmu_acc,0.28556,
591
- Internal Deduplication,24300,mmstar_average,0.3347613325457924,
592
- Internal Deduplication,24300,ocrbench_ocrbench_accuracy,0.634,
593
- Internal Deduplication,24300,textvqa_val_exact_match,0.63094,0.006498229657201687
594
- Internal Deduplication,25500,ai2d_exact_match,0.48607512953367876,0.008995663534025174
595
- Internal Deduplication,25500,average,0.5472398215745332,
596
- Internal Deduplication,25500,average_rank,1.375,
597
- Internal Deduplication,25500,chartqa_relaxed_overall,0.6536,0.0095183536193109
598
- Internal Deduplication,25500,docvqa_val_anls,0.7180940785000507,0.005735169057784404
599
- Internal Deduplication,25500,infovqa_val_anls,0.35632636677863483,0.008180298439903802
600
- Internal Deduplication,25500,mme_total_score,1376.716986794718,
601
- Internal Deduplication,25500,mmstar_average,0.3529231762093682,
602
- Internal Deduplication,25500,ocrbench_ocrbench_accuracy,0.633,
603
- Internal Deduplication,25500,textvqa_val_exact_match,0.63066,0.006504156647155582
604
- Internal Deduplication,26700,ai2d_exact_match,0.49255181347150256,0.008998155599035912
605
- Internal Deduplication,26700,average,0.516487110189266,
606
- Internal Deduplication,26700,average_rank,1.5555555555555556,
607
- Internal Deduplication,26700,chartqa_relaxed_overall,0.6644,0.009445885130487209
608
- Internal Deduplication,26700,docvqa_val_anls,0.7168133343849862,0.005756579734549226
609
- Internal Deduplication,26700,infovqa_val_anls,0.34371436472133005,0.008017561696940439
610
- Internal Deduplication,26700,mme_total_score,1409.4487795118048,
611
- Internal Deduplication,26700,mmmu_val_mmmu_acc,0.30222,
612
- Internal Deduplication,26700,mmstar_average,0.35023736893630925,
613
- Internal Deduplication,26700,ocrbench_ocrbench_accuracy,0.63,
614
- Internal Deduplication,26700,textvqa_val_exact_match,0.6319600000000001,0.006495302107669356
615
- Internal Deduplication,27900,ai2d_exact_match,0.4954663212435233,0.008998784170060767
616
- Internal Deduplication,27900,average,0.5488694312151498,
617
- Internal Deduplication,27900,average_rank,1.375,
618
- Internal Deduplication,27900,chartqa_relaxed_overall,0.6736,0.009379787213112317
619
- Internal Deduplication,27900,docvqa_val_anls,0.7224633461958828,0.005716176978314635
620
- Internal Deduplication,27900,infovqa_val_anls,0.35413809221269893,0.00811649922857756
621
- Internal Deduplication,27900,mme_total_score,1365.8970588235293,
622
- Internal Deduplication,27900,mmstar_average,0.33847825885394267,
623
- Internal Deduplication,27900,ocrbench_ocrbench_accuracy,0.623,
624
- Internal Deduplication,27900,textvqa_val_exact_match,0.6349400000000001,0.006474057612069333
625
- Internal Deduplication,29100,ai2d_exact_match,0.4957901554404145,0.008998835133354704
626
- Internal Deduplication,29100,average,0.5113797484193323,
627
- Internal Deduplication,29100,average_rank,2.0,
628
- Internal Deduplication,29100,chartqa_relaxed_overall,0.6604,0.009473364442136777
629
- Internal Deduplication,29100,docvqa_val_anls,0.716657704725735,0.005756925555640175
630
- Internal Deduplication,29100,infovqa_val_anls,0.3372271343716428,0.007828634509891694
631
- Internal Deduplication,29100,mme_total_score,1300.1049419767908,
632
- Internal Deduplication,29100,mmmu_val_mmmu_acc,0.29556,
633
- Internal Deduplication,29100,mmstar_average,0.33882299281686595,
634
- Internal Deduplication,29100,ocrbench_ocrbench_accuracy,0.613,
635
- Internal Deduplication,29100,textvqa_val_exact_match,0.6335799999999999,0.006486361946288509
636
- Internal Deduplication,30300,ai2d_exact_match,0.49676165803108807,0.008998965371572352
637
- Internal Deduplication,30300,average,0.5468368131516261,
638
- Internal Deduplication,30300,average_rank,1.625,
639
- Internal Deduplication,30300,chartqa_relaxed_overall,0.6608,0.009470650520873179
640
- Internal Deduplication,30300,docvqa_val_anls,0.7208981382284003,0.005745692168242118
641
- Internal Deduplication,30300,infovqa_val_anls,0.33146012551516996,0.007795838114372819
642
- Internal Deduplication,30300,mme_total_score,1330.1678671468587,
643
- Internal Deduplication,30300,mmstar_average,0.35709777028672485,
644
- Internal Deduplication,30300,ocrbench_ocrbench_accuracy,0.622,
645
- Internal Deduplication,30300,textvqa_val_exact_match,0.6388400000000001,0.006462092742178937
646
- Internal Deduplication,31500,ai2d_exact_match,0.4996761658031088,0.008999152231809677
647
- Internal Deduplication,31500,average,0.5161255997108974,
648
- Internal Deduplication,31500,average_rank,1.4444444444444444,
649
- Internal Deduplication,31500,chartqa_relaxed_overall,0.6624,0.009459719367730022
650
- Internal Deduplication,31500,docvqa_val_anls,0.7248827916963386,0.005715267948257416
651
- Internal Deduplication,31500,infovqa_val_anls,0.3462785194206036,0.007940616340604684
652
- Internal Deduplication,31500,mme_total_score,1388.7246898759504,
653
- Internal Deduplication,31500,mmmu_val_mmmu_acc,0.28556,
654
- Internal Deduplication,31500,mmstar_average,0.34634732076712815,
655
- Internal Deduplication,31500,ocrbench_ocrbench_accuracy,0.622,
656
- Internal Deduplication,31500,textvqa_val_exact_match,0.64186,0.006449237676913657
657
- Internal Deduplication,32700,ai2d_exact_match,0.4957901554404145,0.008998835133354704
658
- Internal Deduplication,32700,average,0.5500475012134611,
659
- Internal Deduplication,32700,average_rank,1.5,
660
- Internal Deduplication,32700,chartqa_relaxed_overall,0.6688,0.009414779829167153
661
- Internal Deduplication,32700,docvqa_val_anls,0.7263156273407247,0.00570514646941267
662
- Internal Deduplication,32700,infovqa_val_anls,0.3489756877198793,0.00798640336179305
663
- Internal Deduplication,32700,mme_total_score,1362.764905962385,
664
- Internal Deduplication,32700,mmstar_average,0.3385910379932094,
665
- Internal Deduplication,32700,ocrbench_ocrbench_accuracy,0.63,
666
- Internal Deduplication,32700,textvqa_val_exact_match,0.64186,0.006452586710386076
667
- Internal Deduplication,33900,ai2d_exact_match,0.4957901554404145,0.008998835133354704
668
- Internal Deduplication,33900,average,0.5160312203077811,
669
- Internal Deduplication,33900,average_rank,1.4444444444444444,
670
- Internal Deduplication,33900,chartqa_relaxed_overall,0.674,0.009376820884924869
671
- Internal Deduplication,33900,docvqa_val_anls,0.7257174511919398,0.005702388110070895
672
- Internal Deduplication,33900,infovqa_val_anls,0.3422539948680319,0.007936425119162906
673
- Internal Deduplication,33900,mme_total_score,1389.4628851540615,
674
- Internal Deduplication,33900,mmmu_val_mmmu_acc,0.28444,
675
- Internal Deduplication,33900,mmstar_average,0.34272816096186326,
676
- Internal Deduplication,33900,ocrbench_ocrbench_accuracy,0.619,
677
- Internal Deduplication,33900,textvqa_val_exact_match,0.64432,0.0064359794815068575
678
- Internal Deduplication,35100,ai2d_exact_match,0.49838082901554404,0.008999106932714645
679
- Internal Deduplication,35100,average,0.5533101842015907,
680
- Internal Deduplication,35100,average_rank,1.375,
681
- Internal Deduplication,35100,chartqa_relaxed_overall,0.6736,0.009379787213112317
682
- Internal Deduplication,35100,docvqa_val_anls,0.7278181728761878,0.005688301164010059
683
- Internal Deduplication,35100,infovqa_val_anls,0.351201318391893,0.008119188634171728
684
- Internal Deduplication,35100,mme_total_score,1411.3839535814327,
685
- Internal Deduplication,35100,mmstar_average,0.34205096912751043,
686
- Internal Deduplication,35100,ocrbench_ocrbench_accuracy,0.634,
687
- Internal Deduplication,35100,textvqa_val_exact_match,0.64612,0.006431209933771596
688
- Internal Deduplication,36300,ai2d_exact_match,0.49805699481865284,0.00899908617055324
689
- Internal Deduplication,36300,average,0.5195231205481649,
690
- Internal Deduplication,36300,average_rank,1.5555555555555556,
691
- Internal Deduplication,36300,chartqa_relaxed_overall,0.672,0.009391574983583366
692
- Internal Deduplication,36300,docvqa_val_anls,0.730916270863908,0.005660120362847363
693
- Internal Deduplication,36300,infovqa_val_anls,0.3412406587672079,0.007911958522422949
694
- Internal Deduplication,36300,mme_total_score,1367.637254901961,
695
- Internal Deduplication,36300,mmmu_val_mmmu_acc,0.29444,
696
- Internal Deduplication,36300,mmstar_average,0.34529103993555027,
697
- Internal Deduplication,36300,ocrbench_ocrbench_accuracy,0.634,
698
- Internal Deduplication,36300,textvqa_val_exact_match,0.6402399999999999,0.006461617365628822
699
- Internal Deduplication,37500,ai2d_exact_match,0.5019430051813472,0.008999086170553233
700
- Internal Deduplication,37500,average,0.5495836143474903,
701
- Internal Deduplication,37500,average_rank,1.75,
702
- Internal Deduplication,37500,chartqa_relaxed_overall,0.6756,0.009364877808842454
703
- Internal Deduplication,37500,docvqa_val_anls,0.7255309514873474,0.005687086085909167
704
- Internal Deduplication,37500,infovqa_val_anls,0.3366534174444908,0.007850461211973954
705
- Internal Deduplication,37500,mme_total_score,1364.8713485394157,
706
- Internal Deduplication,37500,mmstar_average,0.3467179263192468,
707
- Internal Deduplication,37500,ocrbench_ocrbench_accuracy,0.618,
708
- Internal Deduplication,37500,textvqa_val_exact_match,0.64264,0.0064540760066348676
709
- Internal Deduplication,38700,ai2d_exact_match,0.49708549222797926,0.008999001233939138
710
- Internal Deduplication,38700,average,0.5196671356527304,
711
- Internal Deduplication,38700,average_rank,1.4444444444444444,
712
- Internal Deduplication,38700,chartqa_relaxed_overall,0.6744,0.009373846787815587
713
- Internal Deduplication,38700,docvqa_val_anls,0.732080533728902,0.0056514543481841085
714
- Internal Deduplication,38700,infovqa_val_anls,0.34326469229313616,0.0079487702679686
715
- Internal Deduplication,38700,mme_total_score,1366.760604241697,
716
- Internal Deduplication,38700,mmmu_val_mmmu_acc,0.28778,
717
- Internal Deduplication,38700,mmstar_average,0.34458636697182526,
718
- Internal Deduplication,38700,ocrbench_ocrbench_accuracy,0.632,
719
- Internal Deduplication,38700,textvqa_val_exact_match,0.6461399999999999,0.00642093963319658
720
- Internal Deduplication,39900,ai2d_exact_match,0.4957901554404145,0.008998835133354702
721
- Internal Deduplication,39900,average,0.5516529838475074,
722
- Internal Deduplication,39900,average_rank,1.625,
723
- Internal Deduplication,39900,chartqa_relaxed_overall,0.6696,0.009409024811273465
724
- Internal Deduplication,39900,docvqa_val_anls,0.723701988394961,0.005721818793341698
725
- Internal Deduplication,39900,infovqa_val_anls,0.3483904533235705,0.007951328084102772
726
- Internal Deduplication,39900,mme_total_score,1403.717386954782,
727
- Internal Deduplication,39900,mmstar_average,0.34950828977360593,
728
- Internal Deduplication,39900,ocrbench_ocrbench_accuracy,0.629,
729
- Internal Deduplication,39900,textvqa_val_exact_match,0.64558,0.006428340177019748
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b6bf0d84fe1bc67436c70f9a8d5919627e9c2bc9c3f931f4af80c01be22649
3
+ size 47060
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/content/assets/data/relevance_filters.csv CHANGED
@@ -1,1201 +1,3 @@
1
- run,step,metric,value,stderr
2
- Baseline,1000,ai2d_exact_match,0.2548575129533679,0.007843322436924496
3
- Baseline,1000,average,0.27120689295763617,
4
- Baseline,1000,average_rank,3.1,
5
- Baseline,1000,chartqa_relaxed_overall,0.3308,0.009411906161401973
6
- Baseline,1000,docvqa_val_anls,0.3528553494243383,0.005852289239342309
7
- Baseline,1000,infovqa_val_anls,0.17320578642581314,0.006297063452679795
8
- Baseline,1000,mme_total_score,977.4280712284914,
9
- Baseline,1000,mmmu_val_mmmu_acc,0.25222,
10
- Baseline,1000,mmstar_average,0.23215874078908072,
11
- Baseline,1000,ocrbench_ocrbench_accuracy,0.286,
12
- Baseline,1000,seedbench_seed_all,0.2563646470261256,
13
- Baseline,1000,textvqa_val_exact_match,0.3024,0.00628900296642181
14
- Baseline,2000,ai2d_exact_match,0.26295336787564766,0.007923526907377255
15
- Baseline,2000,average,0.3202068275596269,
16
- Baseline,2000,average_rank,2.9,
17
- Baseline,2000,chartqa_relaxed_overall,0.4688,0.009982508912777261
18
- Baseline,2000,docvqa_val_anls,0.4452261510942785,0.00614755494712251
19
- Baseline,2000,infovqa_val_anls,0.1820547866557169,0.006217861455795791
20
- Baseline,2000,mme_total_score,1049.3036214485794,
21
- Baseline,2000,mmmu_val_mmmu_acc,0.24556,
22
- Baseline,2000,mmstar_average,0.21305462434540698,
23
- Baseline,2000,ocrbench_ocrbench_accuracy,0.395,
24
- Baseline,2000,seedbench_seed_all,0.258532518065592,
25
- Baseline,2000,textvqa_val_exact_match,0.41068000000000005,0.006697862330024289
26
- Baseline,3000,ai2d_exact_match,0.25226683937823835,0.007816909588794397
27
- Baseline,3000,average,0.3507423834414229,
28
- Baseline,3000,average_rank,2.7,
29
- Baseline,3000,chartqa_relaxed_overall,0.5028,0.010001843767601082
30
- Baseline,3000,docvqa_val_anls,0.502653993831009,0.006267072346683124
31
- Baseline,3000,infovqa_val_anls,0.21728617578189535,0.006796941784959762
32
- Baseline,3000,mme_total_score,1170.2383953581434,
33
- Baseline,3000,mmmu_val_mmmu_acc,0.27556,
34
- Baseline,3000,mmstar_average,0.25432376938577683,
35
- Baseline,3000,ocrbench_ocrbench_accuracy,0.436,
36
- Baseline,3000,seedbench_seed_all,0.2792106725958866,
37
- Baseline,3000,textvqa_val_exact_match,0.43658,0.006766885462882726
38
- Baseline,4000,ai2d_exact_match,0.2645725388601036,0.007939149662089447
39
- Baseline,4000,average,0.36961781722974835,
40
- Baseline,4000,average_rank,3.7,
41
- Baseline,4000,chartqa_relaxed_overall,0.5312,0.009982508912777261
42
- Baseline,4000,docvqa_val_anls,0.5374434618615119,0.0062905728113059655
43
- Baseline,4000,infovqa_val_anls,0.2287924838861707,0.006994568698639919
44
- Baseline,4000,mme_total_score,1155.203781512605,
45
- Baseline,4000,mmmu_val_mmmu_acc,0.25556,
46
- Baseline,4000,mmstar_average,0.2575590188757354,
47
- Baseline,4000,ocrbench_ocrbench_accuracy,0.453,
48
- Baseline,4000,seedbench_seed_all,0.33913285158421347,
49
- Baseline,4000,textvqa_val_exact_match,0.4593,0.006791695475025738
50
- Baseline,5000,ai2d_exact_match,0.3125,0.008342439145556371
51
- Baseline,5000,average,0.3974627910380972,
52
- Baseline,5000,average_rank,3.3,
53
- Baseline,5000,chartqa_relaxed_overall,0.5488,0.00995424828018316
54
- Baseline,5000,docvqa_val_anls,0.552360266782429,0.006300308519952055
55
- Baseline,5000,infovqa_val_anls,0.23425555286643698,0.007002254622066442
56
- Baseline,5000,mme_total_score,1181.4653861544618,
57
- Baseline,5000,mmmu_val_mmmu_acc,0.26667,
58
- Baseline,5000,mmstar_average,0.29596648146165705,
59
- Baseline,5000,ocrbench_ocrbench_accuracy,0.462,
60
- Baseline,5000,seedbench_seed_all,0.43107281823235133,
61
- Baseline,5000,textvqa_val_exact_match,0.47354000000000007,0.0068172185364497985
62
- Baseline,6000,ai2d_exact_match,0.358160621761658,0.008629463221867162
63
- Baseline,6000,average,0.4161227404571003,
64
- Baseline,6000,average_rank,2.6,
65
- Baseline,6000,chartqa_relaxed_overall,0.5628,0.00992279440175477
66
- Baseline,6000,docvqa_val_anls,0.5747451497228876,0.00625495440870239
67
- Baseline,6000,infovqa_val_anls,0.22152017368968838,0.006604546680525351
68
- Baseline,6000,mme_total_score,1284.1648659463785,
69
- Baseline,6000,mmmu_val_mmmu_acc,0.27111,
70
- Baseline,6000,mmstar_average,0.2978489412854164,
71
- Baseline,6000,ocrbench_ocrbench_accuracy,0.495,
72
- Baseline,6000,seedbench_seed_all,0.4795997776542524,
73
- Baseline,6000,textvqa_val_exact_match,0.48432,0.006800535050670284
74
- Baseline,7000,ai2d_exact_match,0.3707901554404145,0.00869347755587734
75
- Baseline,7000,average,0.4291083177345374,
76
- Baseline,7000,average_rank,2.9,
77
- Baseline,7000,chartqa_relaxed_overall,0.5656,0.009915542506251351
78
- Baseline,7000,docvqa_val_anls,0.5940907049431567,0.006224236305767187
79
- Baseline,7000,infovqa_val_anls,0.2515675215816963,0.007105097396092786
80
- Baseline,7000,mme_total_score,1185.875650260104,
81
- Baseline,7000,mmmu_val_mmmu_acc,0.26556,
82
- Baseline,7000,mmstar_average,0.31372400960777047,
83
- Baseline,7000,ocrbench_ocrbench_accuracy,0.504,
84
- Baseline,7000,seedbench_seed_all,0.4964424680377988,
85
- Baseline,7000,textvqa_val_exact_match,0.5002,0.006794794025220267
86
- Baseline,8000,ai2d_exact_match,0.37759067357512954,0.008725299846043883
87
- Baseline,8000,average,0.43846759477995995,
88
- Baseline,8000,average_rank,3.2,
89
- Baseline,8000,chartqa_relaxed_overall,0.5832,0.009862556058385773
90
- Baseline,8000,docvqa_val_anls,0.6017336419437208,0.006231612198089698
91
- Baseline,8000,infovqa_val_anls,0.2449256624147254,0.006992518502948913
92
- Baseline,8000,mme_total_score,1199.2409963985594,
93
- Baseline,8000,mmmu_val_mmmu_acc,0.28111,
94
- Baseline,8000,mmstar_average,0.33512257186205047,
95
- Baseline,8000,ocrbench_ocrbench_accuracy,0.51,
96
- Baseline,8000,seedbench_seed_all,0.5024458032240133,
97
- Baseline,8000,textvqa_val_exact_match,0.51008,0.006796301690135059
98
- Baseline,9000,ai2d_exact_match,0.4067357512953368,0.008841214921078996
99
- Baseline,9000,average,0.4422510732201056,
100
- Baseline,9000,average_rank,3.2,
101
- Baseline,9000,chartqa_relaxed_overall,0.5912,0.009834211136815875
102
- Baseline,9000,docvqa_val_anls,0.6170968481662739,0.00617235763542544
103
- Baseline,9000,infovqa_val_anls,0.23537031288570615,0.00670318154156447
104
- Baseline,9000,mme_total_score,1231.5195078031213,
105
- Baseline,9000,mmmu_val_mmmu_acc,0.25889,
106
- Baseline,9000,mmstar_average,0.3216444898242951,
107
- Baseline,9000,ocrbench_ocrbench_accuracy,0.515,
108
- Baseline,9000,seedbench_seed_all,0.5120622568093385,
109
- Baseline,9000,textvqa_val_exact_match,0.52226,0.006792711289708482
110
- Baseline,10000,ai2d_exact_match,0.39993523316062174,0.008817096257082848
111
- Baseline,10000,average,0.4523875703250908,
112
- Baseline,10000,average_rank,2.9,
113
- Baseline,10000,chartqa_relaxed_overall,0.5996,0.00980154906867574
114
- Baseline,10000,docvqa_val_anls,0.6262613496433054,0.006147756371688175
115
- Baseline,10000,infovqa_val_anls,0.263290074230132,0.007186788766942786
116
- Baseline,10000,mme_total_score,1240.8218287314926,
117
- Baseline,10000,mmmu_val_mmmu_acc,0.28778,
118
- Baseline,10000,mmstar_average,0.32972717906018517,
119
- Baseline,10000,ocrbench_ocrbench_accuracy,0.517,
120
- Baseline,10000,seedbench_seed_all,0.5217342968315731,
121
- Baseline,10000,textvqa_val_exact_match,0.5261600000000001,0.006785774843600811
122
- Baseline,11000,ai2d_exact_match,0.422279792746114,0.008889771831066474
123
- Baseline,11000,average,0.4561398159525099,
124
- Baseline,11000,average_rank,3.0,
125
- Baseline,11000,chartqa_relaxed_overall,0.6104,0.009755142291143075
126
- Baseline,11000,docvqa_val_anls,0.6373130149166712,0.006128022584995044
127
- Baseline,11000,infovqa_val_anls,0.24419378339723755,0.006897644885887063
128
- Baseline,11000,mme_total_score,1322.9488795518205,
129
- Baseline,11000,mmmu_val_mmmu_acc,0.27778,
130
- Baseline,11000,mmstar_average,0.3298563439522548,
131
- Baseline,11000,ocrbench_ocrbench_accuracy,0.521,
132
- Baseline,11000,seedbench_seed_all,0.5237354085603113,
133
- Baseline,11000,textvqa_val_exact_match,0.5387,0.006770851562852138
134
- Baseline,12000,ai2d_exact_match,0.42001295336787564,0.008883255931688034
135
- Baseline,12000,average,0.4582751140055433,
136
- Baseline,12000,average_rank,3.5,
137
- Baseline,12000,chartqa_relaxed_overall,0.618,0.009719474639861454
138
- Baseline,12000,docvqa_val_anls,0.6393961983751871,0.0061228747388476674
139
- Baseline,12000,infovqa_val_anls,0.24798874058574302,0.006855374548993139
140
- Baseline,12000,mme_total_score,1225.6453581432572,
141
- Baseline,12000,mmmu_val_mmmu_acc,0.27889,
142
- Baseline,12000,mmstar_average,0.34010867846816534,
143
- Baseline,12000,ocrbench_ocrbench_accuracy,0.512,
144
- Baseline,12000,seedbench_seed_all,0.5350194552529183,
145
- Baseline,12000,textvqa_val_exact_match,0.5330600000000001,0.006777713092109446
146
- Baseline,13000,ai2d_exact_match,0.4375,0.008928571428571428
147
- Baseline,13000,average,0.4692868662590049,
148
- Baseline,13000,average_rank,2.7,
149
- Baseline,13000,chartqa_relaxed_overall,0.6148,0.00973479791861169
150
- Baseline,13000,docvqa_val_anls,0.6511374872549951,0.006086953065248391
151
- Baseline,13000,infovqa_val_anls,0.24465055100441893,0.006808432538374664
152
- Baseline,13000,mme_total_score,1281.7122849139657,
153
- Baseline,13000,mmmu_val_mmmu_acc,0.28222,
154
- Baseline,13000,mmstar_average,0.3453069542917521,
155
- Baseline,13000,ocrbench_ocrbench_accuracy,0.549,
156
- Baseline,13000,seedbench_seed_all,0.5442468037798777,
157
- Baseline,13000,textvqa_val_exact_match,0.55472,0.0067416788982325
158
- Baseline,14000,ai2d_exact_match,0.4572538860103627,0.00896620675297095
159
- Baseline,14000,average,0.47352486841689195,
160
- Baseline,14000,average_rank,2.5,
161
- Baseline,14000,chartqa_relaxed_overall,0.6172,0.009723347231923635
162
- Baseline,14000,docvqa_val_anls,0.6502269393708169,0.006057950730638126
163
- Baseline,14000,infovqa_val_anls,0.25805460837190913,0.007037735231659539
164
- Baseline,14000,mme_total_score,1309.1444577831132,
165
- Baseline,14000,mmmu_val_mmmu_acc,0.28111,
166
- Baseline,14000,mmstar_average,0.34575818188776586,
167
- Baseline,14000,ocrbench_ocrbench_accuracy,0.551,
168
- Baseline,14000,seedbench_seed_all,0.5483602001111729,
169
- Baseline,14000,textvqa_val_exact_match,0.55276,0.006751206724612103
170
- Baseline,15000,ai2d_exact_match,0.45045336787564766,0.008954861634252399
171
- Baseline,15000,average,0.47878665012878824,
172
- Baseline,15000,average_rank,2.6,
173
- Baseline,15000,chartqa_relaxed_overall,0.612,0.009747841205275417
174
- Baseline,15000,docvqa_val_anls,0.6621413031955148,0.006056838050222495
175
- Baseline,15000,infovqa_val_anls,0.2706898598157733,0.007200315730154543
176
- Baseline,15000,mme_total_score,1384.2171868747498,
177
- Baseline,15000,mmmu_val_mmmu_acc,0.30222,
178
- Baseline,15000,mmstar_average,0.35408135695920684,
179
- Baseline,15000,ocrbench_ocrbench_accuracy,0.558,
180
- Baseline,15000,seedbench_seed_all,0.5411339633129516,
181
- Baseline,15000,textvqa_val_exact_match,0.5583600000000001,0.0067279027203879065
182
- Baseline,16000,ai2d_exact_match,0.45077720207253885,0.008955440137395838
183
- Baseline,16000,average,0.47665128022935843,
184
- Baseline,16000,average_rank,3.0,
185
- Baseline,16000,chartqa_relaxed_overall,0.632,0.00964715642305132
186
- Baseline,16000,docvqa_val_anls,0.6709415729142987,0.005999818105621502
187
- Baseline,16000,infovqa_val_anls,0.26050032542402035,0.006997451875879188
188
- Baseline,16000,mme_total_score,1317.8491396558625,
189
- Baseline,16000,mmmu_val_mmmu_acc,0.27556,
190
- Baseline,16000,mmstar_average,0.33214333327093315,
191
- Baseline,16000,ocrbench_ocrbench_accuracy,0.56,
192
- Baseline,16000,seedbench_seed_all,0.5463590883824346,
193
- Baseline,16000,textvqa_val_exact_match,0.56158,0.006723854754867398
194
- Baseline,17000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
195
- Baseline,17000,average,0.4777141780162423,
196
- Baseline,17000,average_rank,2.5,
197
- Baseline,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
198
- Baseline,17000,docvqa_val_anls,0.6796338519136422,0.005948761388267941
199
- Baseline,17000,infovqa_val_anls,0.28070956072505215,0.007298333094144192
200
- Baseline,17000,mme_total_score,1381.9161664665867,
201
- Baseline,17000,mmmu_val_mmmu_acc,0.27667,
202
- Baseline,17000,mmstar_average,0.3370289492329521,
203
- Baseline,17000,ocrbench_ocrbench_accuracy,0.519,
204
- Baseline,17000,seedbench_seed_all,0.5510283490828238,
205
- Baseline,17000,textvqa_val_exact_match,0.56416,0.006724830373229479
206
- Baseline,18000,ai2d_exact_match,0.46567357512953367,0.008977921602780726
207
- Baseline,18000,average,0.4819834595278701,
208
- Baseline,18000,average_rank,2.9,
209
- Baseline,18000,chartqa_relaxed_overall,0.6376,0.009615793331418735
210
- Baseline,18000,docvqa_val_anls,0.6775884603912571,0.005972234236435759
211
- Baseline,18000,infovqa_val_anls,0.27154318420389256,0.007164903131667027
212
- Baseline,18000,mme_total_score,1336.922769107643,
213
- Baseline,18000,mmmu_val_mmmu_acc,0.28667,
214
- Baseline,18000,mmstar_average,0.34482796716566916,
215
- Baseline,18000,ocrbench_ocrbench_accuracy,0.533,
216
- Baseline,18000,seedbench_seed_all,0.5543079488604781,
217
- Baseline,18000,textvqa_val_exact_match,0.5666399999999999,0.006713392287599574
218
- Baseline,19000,ai2d_exact_match,0.4682642487046632,0.008981008686994101
219
- Baseline,19000,average,0.4899006713916878,
220
- Baseline,19000,average_rank,2.7,
221
- Baseline,19000,chartqa_relaxed_overall,0.6444,0.009575809858898698
222
- Baseline,19000,docvqa_val_anls,0.678226526479947,0.005970619221588814
223
- Baseline,19000,infovqa_val_anls,0.26993847247278,0.0071348470764911525
224
- Baseline,19000,mme_total_score,1406.6628651460583,
225
- Baseline,19000,mmmu_val_mmmu_acc,0.28333,
226
- Baseline,19000,mmstar_average,0.356220913822775,
227
- Baseline,19000,ocrbench_ocrbench_accuracy,0.577,
228
- Baseline,19000,seedbench_seed_all,0.554585881045025,
229
- Baseline,19000,textvqa_val_exact_match,0.57714,0.0066918487914812905
230
- Baseline,20000,ai2d_exact_match,0.47571243523316065,0.00898853090258662
231
- Baseline,20000,average,0.4873169067639118,
232
- Baseline,20000,average_rank,3.1,
233
- Baseline,20000,chartqa_relaxed_overall,0.6336,0.009638338810708618
234
- Baseline,20000,docvqa_val_anls,0.6895214454380043,0.005896462073053767
235
- Baseline,20000,infovqa_val_anls,0.2655657550458317,0.007033265532032538
236
- Baseline,20000,mme_total_score,1324.6738695478193,
237
- Baseline,20000,mmmu_val_mmmu_acc,0.30111,
238
- Baseline,20000,mmstar_average,0.33806766134497995,
239
- Baseline,20000,ocrbench_ocrbench_accuracy,0.555,
240
- Baseline,20000,seedbench_seed_all,0.5587548638132296,
241
- Baseline,20000,textvqa_val_exact_match,0.56852,0.006720151338087659
242
- ≥2,1000,ai2d_exact_match,0.2645725388601036,0.007939149662089442
243
- ≥2,1000,average,0.2722931646460497,
244
- ≥2,1000,average_rank,3.2,
245
- ≥2,1000,chartqa_relaxed_overall,0.3664,0.009638338810708616
246
- ≥2,1000,docvqa_val_anls,0.35825461497275807,0.005864292098743202
247
- ≥2,1000,infovqa_val_anls,0.16722293767954274,0.0061333612650745235
248
- ≥2,1000,mme_total_score,994.9906962785115,
249
- ≥2,1000,mmmu_val_mmmu_acc,0.25111,
250
- ≥2,1000,mmstar_average,0.2099224814637991,
251
- ≥2,1000,ocrbench_ocrbench_accuracy,0.304,
252
- ≥2,1000,seedbench_seed_all,0.24463590883824346,
253
- ≥2,1000,textvqa_val_exact_match,0.28452000000000005,0.006179555914647949
254
- ≥2,2000,ai2d_exact_match,0.2648963730569948,0.007942257693619753
255
- ≥2,2000,average,0.3161289250086133,
256
- ≥2,2000,average_rank,3.2,
257
- ≥2,2000,chartqa_relaxed_overall,0.4476,0.00994692276581072
258
- ≥2,2000,docvqa_val_anls,0.44553207035528164,0.006176982458046509
259
- ≥2,2000,infovqa_val_anls,0.19690312157526974,0.00648399793536667
260
- ≥2,2000,mme_total_score,1054.2768107242898,
261
- ≥2,2000,mmmu_val_mmmu_acc,0.24778,
262
- ≥2,2000,mmstar_average,0.20779488571532076,
263
- ≥2,2000,ocrbench_ocrbench_accuracy,0.383,
264
- ≥2,2000,seedbench_seed_all,0.2529738743746526,
265
- ≥2,2000,textvqa_val_exact_match,0.39868,0.006677826756815335
266
- ≥2,3000,ai2d_exact_match,0.2697538860103627,0.007988222765138163
267
- ≥2,3000,average,0.34461871112110076,
268
- ≥2,3000,average_rank,3.7,
269
- ≥2,3000,chartqa_relaxed_overall,0.502,0.010001920583875201
270
- ≥2,3000,docvqa_val_anls,0.4943706505276063,0.006276617082627261
271
- ≥2,3000,infovqa_val_anls,0.21287605644341218,0.006682253709215569
272
- ≥2,3000,mme_total_score,1162.2701080432173,
273
- ≥2,3000,mmmu_val_mmmu_acc,0.25556,
274
- ��2,3000,mmstar_average,0.21427247636922603,
275
- ≥2,3000,ocrbench_ocrbench_accuracy,0.449,
276
- ≥2,3000,seedbench_seed_all,0.2715953307392996,
277
- ≥2,3000,textvqa_val_exact_match,0.43213999999999997,0.006742795943777913
278
- ≥2,4000,ai2d_exact_match,0.27525906735751293,0.008038849490577975
279
- ≥2,4000,average,0.37379440715652495,
280
- ≥2,4000,average_rank,2.6,
281
- ≥2,4000,chartqa_relaxed_overall,0.5356,0.009976616117083942
282
- ≥2,4000,docvqa_val_anls,0.5415736777563739,0.006259488230977563
283
- ≥2,4000,infovqa_val_anls,0.22392444384387208,0.00676041701311943
284
- ≥2,4000,mme_total_score,1195.5438175270108,
285
- ≥2,4000,mmmu_val_mmmu_acc,0.26667,
286
- ≥2,4000,mmstar_average,0.2507897461569136,
287
- ≥2,4000,ocrbench_ocrbench_accuracy,0.462,
288
- ≥2,4000,seedbench_seed_all,0.34291272929405225,
289
- ≥2,4000,textvqa_val_exact_match,0.46542,0.0067795602517745565
290
- ≥2,5000,ai2d_exact_match,0.31055699481865284,0.008328207321163279
291
- ≥2,5000,average,0.39445964778826137,
292
- ≥2,5000,average_rank,3.3,
293
- ≥2,5000,chartqa_relaxed_overall,0.552,0.00994776272300849
294
- ≥2,5000,docvqa_val_anls,0.5556927230238289,0.006299299461817651
295
- ≥2,5000,infovqa_val_anls,0.24261245038285142,0.007075738778751112
296
- ≥2,5000,mme_total_score,1220.672168867547,
297
- ≥2,5000,mmmu_val_mmmu_acc,0.27444,
298
- ≥2,5000,mmstar_average,0.2522926162881413,
299
- ≥2,5000,ocrbench_ocrbench_accuracy,0.467,
300
- ≥2,5000,seedbench_seed_all,0.42768204558087825,
301
- ≥2,5000,textvqa_val_exact_match,0.46785999999999994,0.006777889939974511
302
- ≥2,6000,ai2d_exact_match,0.3325777202072539,0.008479663360791275
303
- ≥2,6000,average,0.4101998600043759,
304
- ≥2,6000,average_rank,3.7,
305
- ≥2,6000,chartqa_relaxed_overall,0.5672,0.009911254067113462
306
- ≥2,6000,docvqa_val_anls,0.5702012141050906,0.006263916894054504
307
- ≥2,6000,infovqa_val_anls,0.21632587505016104,0.006473865748732477
308
- ≥2,6000,mme_total_score,1313.7047819127652,
309
- ≥2,6000,mmmu_val_mmmu_acc,0.28,
310
- ≥2,6000,mmstar_average,0.28566177948176935,
311
- ≥2,6000,ocrbench_ocrbench_accuracy,0.486,
312
- ≥2,6000,seedbench_seed_all,0.4698721511951084,
313
- ≥2,6000,textvqa_val_exact_match,0.48396000000000006,0.006801425994533192
314
- ≥2,7000,ai2d_exact_match,0.35200777202072536,0.00859592682822483
315
- ≥2,7000,average,0.4204955224344633,
316
- ≥2,7000,average_rank,4.0,
317
- ≥2,7000,chartqa_relaxed_overall,0.5712,0.00990007214980924
318
- ≥2,7000,docvqa_val_anls,0.5850734578344774,0.006202520219850679
319
- ≥2,7000,infovqa_val_anls,0.23449023638527144,0.0067906990453115955
320
- ≥2,7000,mme_total_score,1247.423969587835,
321
- ≥2,7000,mmmu_val_mmmu_acc,0.28444,
322
- ≥2,7000,mmstar_average,0.29053864145068503,
323
- ≥2,7000,ocrbench_ocrbench_accuracy,0.487,
324
- ≥2,7000,seedbench_seed_all,0.48526959421901056,
325
- ≥2,7000,textvqa_val_exact_match,0.49444000000000005,0.006796105847537853
326
- ≥2,8000,ai2d_exact_match,0.3746761658031088,0.008711886524907496
327
- ≥2,8000,average,0.43663916832315425,
328
- ≥2,8000,average_rank,2.9,
329
- ≥2,8000,chartqa_relaxed_overall,0.5816,0.00986790384075991
330
- ≥2,8000,docvqa_val_anls,0.6028798426362394,0.006214872354058686
331
- ≥2,8000,infovqa_val_anls,0.2535281850303886,0.0070045473889607445
332
- ≥2,8000,mme_total_score,1300.5965386154462,
333
- ≥2,8000,mmmu_val_mmmu_acc,0.27333,
334
- ≥2,8000,mmstar_average,0.310944925107356,
335
- ≥2,8000,ocrbench_ocrbench_accuracy,0.516,
336
- ≥2,8000,seedbench_seed_all,0.5041133963312951,
337
- ≥2,8000,textvqa_val_exact_match,0.51268,0.006798079603627737
338
- ≥2,9000,ai2d_exact_match,0.3795336787564767,0.00873405559083709
339
- ≥2,9000,average,0.43759974296352216,
340
- ≥2,9000,average_rank,2.9,
341
- ≥2,9000,chartqa_relaxed_overall,0.5884,0.009844437067525526
342
- ≥2,9000,docvqa_val_anls,0.6175894644110065,0.0061700253612544395
343
- ≥2,9000,infovqa_val_anls,0.24471327484068725,0.006934982517240646
344
- ≥2,9000,mme_total_score,1258.1754701880752,
345
- ≥2,9000,mmmu_val_mmmu_acc,0.27,
346
- ≥2,9000,mmstar_average,0.2988526527658083,
347
- ≥2,9000,ocrbench_ocrbench_accuracy,0.514,
348
- ≥2,9000,seedbench_seed_all,0.5155086158977209,
349
- ≥2,9000,textvqa_val_exact_match,0.5098,0.00680062068405066
350
- ≥2,10000,ai2d_exact_match,0.407059585492228,0.008842319527489083
351
- ≥2,10000,average,0.45127176699921406,
352
- ≥2,10000,average_rank,3.1,
353
- ≥2,10000,chartqa_relaxed_overall,0.5956,0.009817474681589429
354
- ≥2,10000,docvqa_val_anls,0.6286443353240219,0.006128441640319587
355
- ≥2,10000,infovqa_val_anls,0.25277210900180563,0.007055702724548255
356
- ≥2,10000,mme_total_score,1320.1028411364546,
357
- ≥2,10000,mmmu_val_mmmu_acc,0.27556,
358
- ≥2,10000,mmstar_average,0.3429750538307907,
359
- ≥2,10000,ocrbench_ocrbench_accuracy,0.523,
360
- ≥2,10000,seedbench_seed_all,0.51467481934408,
361
- ≥2,10000,textvqa_val_exact_match,0.5211600000000001,0.006783601870014644
362
- ≥2,11000,ai2d_exact_match,0.41580310880829013,0.008870644443998564
363
- ≥2,11000,average,0.4525862975952584,
364
- ≥2,11000,average_rank,3.5,
365
- ≥2,11000,chartqa_relaxed_overall,0.598,0.009808000752013664
366
- ≥2,11000,docvqa_val_anls,0.6307438129106796,0.006133911991297053
367
- ≥2,11000,infovqa_val_anls,0.25390014221903434,0.007050537280004977
368
- ≥2,11000,mme_total_score,1302.5287114845937,
369
- ≥2,11000,mmmu_val_mmmu_acc,0.29333,
370
- ≥2,11000,mmstar_average,0.303972877343168,
371
- ���2,11000,ocrbench_ocrbench_accuracy,0.523,
372
- ≥2,11000,seedbench_seed_all,0.5281267370761534,
373
- ≥2,11000,textvqa_val_exact_match,0.5264,0.006786826961404041
374
- ≥2,12000,ai2d_exact_match,0.43426165803108807,0.008921034830887027
375
- ≥2,12000,average,0.46342874141175217,
376
- ≥2,12000,average_rank,2.7,
377
- ≥2,12000,chartqa_relaxed_overall,0.6188,0.009715574144248037
378
- ≥2,12000,docvqa_val_anls,0.6419729722202083,0.006094582531110984
379
- ≥2,12000,infovqa_val_anls,0.24776952598966778,0.006784112219881613
380
- ≥2,12000,mme_total_score,1255.4957983193276,
381
- ≥2,12000,mmmu_val_mmmu_acc,0.27111,
382
- ≥2,12000,mmstar_average,0.3424608032908198,
383
- ≥2,12000,ocrbench_ocrbench_accuracy,0.541,
384
- ≥2,12000,seedbench_seed_all,0.5306837131739855,
385
- ≥2,12000,textvqa_val_exact_match,0.5428,0.006758192556691964
386
- ≥2,13000,ai2d_exact_match,0.42843264248704666,0.008906491762178375
387
- ≥2,13000,average,0.4611120038339278,
388
- ≥2,13000,average_rank,3.8,
389
- ≥2,13000,chartqa_relaxed_overall,0.606,0.00977465178546074
390
- ≥2,13000,docvqa_val_anls,0.6433656711922792,0.0061086851054902285
391
- ≥2,13000,infovqa_val_anls,0.2535479547381062,0.006989226376396767
392
- ≥2,13000,mme_total_score,1360.003101240496,
393
- ≥2,13000,mmmu_val_mmmu_acc,0.28556,
394
- ≥2,13000,mmstar_average,0.3320394092229932,
395
- ≥2,13000,ocrbench_ocrbench_accuracy,0.526,
396
- ≥2,13000,seedbench_seed_all,0.5362423568649249,
397
- ≥2,13000,textvqa_val_exact_match,0.53882,0.006765393974568386
398
- ≥2,14000,ai2d_exact_match,0.44689119170984454,0.008948245073044956
399
- ≥2,14000,average,0.47130833654714216,
400
- ≥2,14000,average_rank,2.8,
401
- ≥2,14000,chartqa_relaxed_overall,0.6216,0.009701702181065136
402
- ≥2,14000,docvqa_val_anls,0.6619108814388047,0.006015398975274413
403
- ≥2,14000,infovqa_val_anls,0.2567040650730957,0.006986745571340195
404
- ≥2,14000,mme_total_score,1310.3628451380553,
405
- ≥2,14000,mmmu_val_mmmu_acc,0.28333,
406
- ≥2,14000,mmstar_average,0.3315916867003111,
407
- ≥2,14000,ocrbench_ocrbench_accuracy,0.547,
408
- ≥2,14000,seedbench_seed_all,0.5409672040022234,
409
- ≥2,14000,textvqa_val_exact_match,0.55178,0.006748546131944198
410
- ≥2,15000,ai2d_exact_match,0.4523963730569948,0.00895827521082005
411
- ≥2,15000,average,0.4720211465604895,
412
- ≥2,15000,average_rank,3.5,
413
- ≥2,15000,chartqa_relaxed_overall,0.62,0.009709671008043154
414
- ≥2,15000,docvqa_val_anls,0.6679183447758706,0.005982903367170995
415
- ≥2,15000,infovqa_val_anls,0.24815705436683513,0.006864270716284432
416
- ≥2,15000,mme_total_score,1236.2534013605443,
417
- ≥2,15000,mmmu_val_mmmu_acc,0.29889,
418
- ≥2,15000,mmstar_average,0.3351456007635487,
419
- ≥2,15000,ocrbench_ocrbench_accuracy,0.527,
420
- ≥2,15000,seedbench_seed_all,0.5453029460811561,
421
- ≥2,15000,textvqa_val_exact_match,0.55338,0.006735012041373013
422
- ≥2,16000,ai2d_exact_match,0.44624352331606215,0.008946992176353898
423
- ≥2,16000,average,0.4766960932538844,
424
- ≥2,16000,average_rank,3.2,
425
- ≥2,16000,chartqa_relaxed_overall,0.612,0.009747841205275417
426
- ≥2,16000,docvqa_val_anls,0.6754589054855508,0.005966817690473989
427
- ≥2,16000,infovqa_val_anls,0.27323519213464514,0.007206289716945655
428
- ≥2,16000,mme_total_score,1305.906762705082,
429
- ≥2,16000,mmmu_val_mmmu_acc,0.29,
430
- ≥2,16000,mmstar_average,0.34328884147265926,
431
- ≥2,16000,ocrbench_ocrbench_accuracy,0.555,
432
- ≥2,16000,seedbench_seed_all,0.5410783768760422,
433
- ≥2,16000,textvqa_val_exact_match,0.55396,0.00674076785464787
434
- ≥2,17000,ai2d_exact_match,0.4485103626943005,0.008951310133709686
435
- ≥2,17000,average,0.4803744475549501,
436
- ≥2,17000,average_rank,3.3,
437
- ≥2,17000,chartqa_relaxed_overall,0.6352,0.009629406741314642
438
- ≥2,17000,docvqa_val_anls,0.6735387256928971,0.006001868055856522
439
- ≥2,17000,infovqa_val_anls,0.2713449738427,0.007231154690666275
440
- ≥2,17000,mme_total_score,1302.8314325730291,
441
- ≥2,17000,mmmu_val_mmmu_acc,0.28667,
442
- ≥2,17000,mmstar_average,0.33631999578132954,
443
- ≥2,17000,ocrbench_ocrbench_accuracy,0.571,
444
- ≥2,17000,seedbench_seed_all,0.542745969983324,
445
- ≥2,17000,textvqa_val_exact_match,0.5580400000000001,0.006741465801458199
446
- ≥2,18000,ai2d_exact_match,0.46113989637305697,0.008971933568013592
447
- ≥2,18000,average,0.48745721111983964,
448
- ≥2,18000,average_rank,2.6,
449
- ≥2,18000,chartqa_relaxed_overall,0.6276,0.009670817229291067
450
- ≥2,18000,docvqa_val_anls,0.6812777947859573,0.005935773909547658
451
- ≥2,18000,infovqa_val_anls,0.27095882924867687,0.007164605404977649
452
- ≥2,18000,mme_total_score,1289.7513005202081,
453
- ≥2,18000,mmmu_val_mmmu_acc,0.31556,
454
- ≥2,18000,mmstar_average,0.35401030852022664,
455
- ≥2,18000,ocrbench_ocrbench_accuracy,0.564,
456
- ≥2,18000,seedbench_seed_all,0.5505280711506393,
457
- ≥2,18000,textvqa_val_exact_match,0.5620400000000001,0.00673487040527694
458
- ≥2,19000,ai2d_exact_match,0.4698834196891192,0.008982814668850815
459
- ≥2,19000,average,0.48664836716175586,
460
- ≥2,19000,average_rank,3.2,
461
- ≥2,19000,chartqa_relaxed_overall,0.6276,0.009670817229291067
462
- ≥2,19000,docvqa_val_anls,0.6838077764263535,0.005944136929785695
463
- ≥2,19000,infovqa_val_anls,0.26757170067350106,0.007096398035000058
464
- ≥2,19000,mme_total_score,1310.4946978791518,
465
- ≥2,19000,mmmu_val_mmmu_acc,0.29444,
466
- ≥2,19000,mmstar_average,0.365800601107629,
467
- ≥2,19000,ocrbench_ocrbench_accuracy,0.559,
468
- ≥2,19000,seedbench_seed_all,0.5532518065591996,
469
- ≥2,19000,textvqa_val_exact_match,0.55848,0.006735717623117797
470
- ≥2,20000,ai2d_exact_match,0.4727979274611399,0.008985826352357515
471
- ≥2,20000,average,0.4887875980209429,
472
- ≥2,20000,average_rank,3.4,
473
- ≥2,20000,chartqa_relaxed_overall,0.6392,0.00960657371300514
474
- ≥2,20000,docvqa_val_anls,0.6828620051596259,0.005923332769971399
475
- ≥2,20000,infovqa_val_anls,0.2701274975234547,0.007055868134029247
476
- ≥2,20000,mme_total_score,1323.9108643457382,
477
- ≥2,20000,mmmu_val_mmmu_acc,0.30222,
478
- ≥2,20000,mmstar_average,0.33931189145504953,
479
- ≥2,20000,ocrbench_ocrbench_accuracy,0.57,
480
- ≥2,20000,seedbench_seed_all,0.5563090605892163,
481
- ≥2,20000,textvqa_val_exact_match,0.56626,0.0067178082936069205
482
- ≥3,1000,ai2d_exact_match,0.2691062176165803,0.007982164708643914
483
- ≥3,1000,average,0.27573784261835144,
484
- ≥3,1000,average_rank,2.8,
485
- ≥3,1000,chartqa_relaxed_overall,0.352,0.009553790345406665
486
- ≥3,1000,docvqa_val_anls,0.3425840937939014,0.005755186508181206
487
- ≥3,1000,infovqa_val_anls,0.1714752271538445,0.006218691549786442
488
- ≥3,1000,mme_total_score,1013.1872749099639,
489
- ≥3,1000,mmmu_val_mmmu_acc,0.24778,
490
- ≥3,1000,mmstar_average,0.2075589805205699,
491
- ≥3,1000,ocrbench_ocrbench_accuracy,0.324,
492
- ≥3,1000,seedbench_seed_all,0.24891606448026682,
493
- ≥3,1000,textvqa_val_exact_match,0.31822,0.006368399926474836
494
- ≥3,2000,ai2d_exact_match,0.25647668393782386,0.007859644922870102
495
- ≥3,2000,average,0.32059377128504934,
496
- ≥3,2000,average_rank,2.8,
497
- ≥3,2000,chartqa_relaxed_overall,0.4628,0.009974279848861338
498
- ≥3,2000,docvqa_val_anls,0.4518369496978485,0.00619300217721929
499
- ≥3,2000,infovqa_val_anls,0.21204013425009277,0.006820894774458214
500
- ≥3,2000,mme_total_score,1118.8858543417368,
501
- ≥3,2000,mmmu_val_mmmu_acc,0.25222,
502
- ≥3,2000,mmstar_average,0.20454842826555975,
503
- ≥3,2000,ocrbench_ocrbench_accuracy,0.376,
504
- ≥3,2000,seedbench_seed_all,0.25514174541411894,
505
- ≥3,2000,textvqa_val_exact_match,0.41428000000000004,0.006714956027174666
506
- ≥3,3000,ai2d_exact_match,0.25259067357512954,0.007820231277456426
507
- ≥3,3000,average,0.35341646277484595,
508
- ≥3,3000,average_rank,2.4,
509
- ≥3,3000,chartqa_relaxed_overall,0.5208,0.00999334232158103
510
- ≥3,3000,docvqa_val_anls,0.49758866181984457,0.00626460182861003
511
- ≥3,3000,infovqa_val_anls,0.21333414080666746,0.0067509043256437935
512
- ≥3,3000,mme_total_score,1165.3744497799119,
513
- ≥3,3000,mmmu_val_mmmu_acc,0.26,
514
- ≥3,3000,mmstar_average,0.2652435492500152,
515
- ≥3,3000,ocrbench_ocrbench_accuracy,0.442,
516
- ≥3,3000,seedbench_seed_all,0.29205113952195666,
517
- ≥3,3000,textvqa_val_exact_match,0.43714,0.006763850531672249
518
- ≥3,4000,ai2d_exact_match,0.28303108808290156,0.008107723290508887
519
- ≥3,4000,average,0.37496255619498237,
520
- ≥3,4000,average_rank,3.4,
521
- ≥3,4000,chartqa_relaxed_overall,0.5412,0.009967987174315731
522
- ≥3,4000,docvqa_val_anls,0.5296261512617491,0.006274192303767133
523
- ≥3,4000,infovqa_val_anls,0.2050381576936679,0.006416570814061769
524
- ≥3,4000,mme_total_score,1119.7681072428973,
525
- ≥3,4000,mmmu_val_mmmu_acc,0.25556,
526
- ≥3,4000,mmstar_average,0.24897141082880767,
527
- ≥3,4000,ocrbench_ocrbench_accuracy,0.47,
528
- ≥3,4000,seedbench_seed_all,0.3811561978877154,
529
- ≥3,4000,textvqa_val_exact_match,0.46007999999999993,0.006793769924125808
530
- ≥3,5000,ai2d_exact_match,0.3248056994818653,0.008428647470081763
531
- ≥3,5000,average,0.3977887563101667,
532
- ≥3,5000,average_rank,2.8,
533
- ≥3,5000,chartqa_relaxed_overall,0.5544,0.009942625323290008
534
- ≥3,5000,docvqa_val_anls,0.553669449701632,0.006282439058750721
535
- ≥3,5000,infovqa_val_anls,0.20821650889148954,0.006430552192683275
536
- ≥3,5000,mme_total_score,1326.9777911164465,
537
- ≥3,5000,mmmu_val_mmmu_acc,0.26444,
538
- ≥3,5000,mmstar_average,0.279759822424129,
539
- ≥3,5000,ocrbench_ocrbench_accuracy,0.487,
540
- ≥3,5000,seedbench_seed_all,0.43718732629238466,
541
- ≥3,5000,textvqa_val_exact_match,0.47062,0.0067917147023207275
542
- ≥3,6000,ai2d_exact_match,0.3536269430051813,0.008604903043803527
543
- ≥3,6000,average,0.41524300122458385,
544
- ≥3,6000,average_rank,3.1,
545
- ≥3,6000,chartqa_relaxed_overall,0.568,0.009909070383761948
546
- ≥3,6000,docvqa_val_anls,0.5722640243712676,0.00625854154899254
547
- ≥3,6000,infovqa_val_anls,0.2204869348964998,0.00662088578415522
548
- ≥3,6000,mme_total_score,1270.3575430172068,
549
- ≥3,6000,mmmu_val_mmmu_acc,0.26556,
550
- ≥3,6000,mmstar_average,0.2958896090262379,
551
- ≥3,6000,ocrbench_ocrbench_accuracy,0.497,
552
- ≥3,6000,seedbench_seed_all,0.47909949972206783,
553
- ≥3,6000,textvqa_val_exact_match,0.48526,0.006795924028171543
554
- ≥3,7000,ai2d_exact_match,0.3805051813471503,0.00873837769131663
555
- ≥3,7000,average,0.42920372592352884,
556
- ≥3,7000,average_rank,2.7,
557
- ≥3,7000,chartqa_relaxed_overall,0.5728,0.009895414680177737
558
- ≥3,7000,docvqa_val_anls,0.5922749765517075,0.006249497802747461
559
- ≥3,7000,infovqa_val_anls,0.23025261139769496,0.006777932440928761
560
- ≥3,7000,mme_total_score,1289.3664465786314,
561
- ≥3,7000,mmmu_val_mmmu_acc,0.27111,
562
- ≥3,7000,mmstar_average,0.3153601470057574,
563
- ≥3,7000,ocrbench_ocrbench_accuracy,0.498,
564
- ≥3,7000,seedbench_seed_all,0.4991106170094497,
565
- ≥3,7000,textvqa_val_exact_match,0.50342,0.006801949281110862
566
- ≥3,8000,ai2d_exact_match,0.39799222797927464,0.008809880751131852
567
- ≥3,8000,average,0.438180751977588,
568
- ≥3,8000,average_rank,2.4,
569
- ≥3,8000,chartqa_relaxed_overall,0.5844,0.009858475126140203
570
- ≥3,8000,docvqa_val_anls,0.6044755547364623,0.006202062618138765
571
- ≥3,8000,infovqa_val_anls,0.21693088745597935,0.006529416377309533
572
- ≥3,8000,mme_total_score,1187.3639455782313,
573
- ≥3,8000,mmmu_val_mmmu_acc,0.28667,
574
- ≥3,8000,mmstar_average,0.31735843114519735,
575
- ≥3,8000,ocrbench_ocrbench_accuracy,0.506,
576
- ≥3,8000,seedbench_seed_all,0.5193996664813786,
577
- ≥3,8000,textvqa_val_exact_match,0.5104,0.0067972647853171315
578
- ≥3,9000,ai2d_exact_match,0.407059585492228,0.008842319527489083
579
- ≥3,9000,average,0.44395606448032265,
580
- ≥3,9000,average_rank,3.0,
581
- ≥3,9000,chartqa_relaxed_overall,0.598,0.009808000752013664
582
- ≥3,9000,docvqa_val_anls,0.6107522318987826,0.006184930065074595
583
- ≥3,9000,infovqa_val_anls,0.2347778400526839,0.0067525186273140235
584
- ≥3,9000,mme_total_score,1195.0110044017606,
585
- ≥3,9000,mmmu_val_mmmu_acc,0.28222,
586
- ≥3,9000,mmstar_average,0.3264280968647572,
587
- ≥3,9000,ocrbench_ocrbench_accuracy,0.521,
588
- ≥3,9000,seedbench_seed_all,0.5162868260144525,
589
- ≥3,9000,textvqa_val_exact_match,0.4990799999999999,0.00679372222366579
590
- ≥3,10000,ai2d_exact_match,0.41580310880829013,0.008870644443998564
591
- ≥3,10000,average,0.4524021135685592,
592
- ≥3,10000,average_rank,2.5,
593
- ≥3,10000,chartqa_relaxed_overall,0.5992,0.00980317218424473
594
- ≥3,10000,docvqa_val_anls,0.6291907180725226,0.0061343676879221844
595
- ≥3,10000,infovqa_val_anls,0.2282836442456148,0.006711844883510513
596
- ≥3,10000,mme_total_score,1326.8972589035614,
597
- ≥3,10000,mmmu_val_mmmu_acc,0.30111,
598
- ≥3,10000,mmstar_average,0.3402582102457474,
599
- ≥3,10000,ocrbench_ocrbench_accuracy,0.522,
600
- ≥3,10000,seedbench_seed_all,0.5240133407448583,
601
- ≥3,10000,textvqa_val_exact_match,0.51176,0.006789754092169055
602
- ≥3,11000,ai2d_exact_match,0.42389896373056996,0.008894308540753343
603
- ≥3,11000,average,0.45530296075039445,
604
- ≥3,11000,average_rank,3.3,
605
- ≥3,11000,chartqa_relaxed_overall,0.5992,0.00980317218424473
606
- ≥3,11000,docvqa_val_anls,0.637004884118944,0.0060952660672868655
607
- ≥3,11000,infovqa_val_anls,0.24182483065748125,0.006800414154487266
608
- ≥3,11000,mme_total_score,1229.9441776710685,
609
- ≥3,11000,mmmu_val_mmmu_acc,0.28556,
610
- ≥3,11000,mmstar_average,0.3210406141609519,
611
- ≥3,11000,ocrbench_ocrbench_accuracy,0.532,
612
- ≥3,11000,seedbench_seed_all,0.5272373540856031,
613
- ≥3,11000,textvqa_val_exact_match,0.52996,0.006774485841130848
614
- ≥3,12000,ai2d_exact_match,0.4378238341968912,0.008929303814062614
615
- ≥3,12000,average,0.4603808175211579,
616
- ≥3,12000,average_rank,2.8,
617
- ≥3,12000,chartqa_relaxed_overall,0.6036,0.009784943231599163
618
- ≥3,12000,docvqa_val_anls,0.6425836471445318,0.006082856374953106
619
- ≥3,12000,infovqa_val_anls,0.23921346499497054,0.00674373988949671
620
- ≥3,12000,mme_total_score,1253.4613845538215,
621
- ≥3,12000,mmmu_val_mmmu_acc,0.28,
622
- ≥3,12000,mmstar_average,0.3402058443723711,
623
- ≥3,12000,ocrbench_ocrbench_accuracy,0.533,
624
- ≥3,12000,seedbench_seed_all,0.5370205669816565,
625
- ≥3,12000,textvqa_val_exact_match,0.52998,0.006788538632972067
626
- ≥3,13000,ai2d_exact_match,0.4410621761658031,0.0089364152923413
627
- ≥3,13000,average,0.46617815773624777,
628
- ≥3,13000,average_rank,2.8,
629
- ≥3,13000,chartqa_relaxed_overall,0.6116,0.009749676839741497
630
- ≥3,13000,docvqa_val_anls,0.6435913615068958,0.006093449845266186
631
- ≥3,13000,infovqa_val_anls,0.24655403627027533,0.0068431739840280935
632
- ≥3,13000,mme_total_score,1338.6154461784713,
633
- ≥3,13000,mmmu_val_mmmu_acc,0.29556,
634
- ≥3,13000,mmstar_average,0.33746561777886447,
635
- ≥3,13000,ocrbench_ocrbench_accuracy,0.543,
636
- ≥3,13000,seedbench_seed_all,0.5384102279043913,
637
- ≥3,13000,textvqa_val_exact_match,0.5383600000000001,0.006773985492742893
638
- ≥3,14000,ai2d_exact_match,0.4426813471502591,0.008939826412531762
639
- ≥3,14000,average,0.46514162030247774,
640
- ≥3,14000,average_rank,3.6,
641
- ≥3,14000,chartqa_relaxed_overall,0.6104,0.009755142291143075
642
- ≥3,14000,docvqa_val_anls,0.6522898002805984,0.006013616663077038
643
- ≥3,14000,infovqa_val_anls,0.23824160343368236,0.006685403314320424
644
- ≥3,14000,mme_total_score,1290.797318927571,
645
- ≥3,14000,mmmu_val_mmmu_acc,0.29111,
646
- ≥3,14000,mmstar_average,0.34665083130189556,
647
- ≥3,14000,ocrbench_ocrbench_accuracy,0.533,
648
- ≥3,14000,seedbench_seed_all,0.5418010005558643,
649
- ≥3,14000,textvqa_val_exact_match,0.5300999999999999,0.006785072250248203
650
- ≥3,15000,ai2d_exact_match,0.4536917098445596,0.00896047438220532
651
- ≥3,15000,average,0.47760694744777243,
652
- ≥3,15000,average_rank,2.9,
653
- ≥3,15000,chartqa_relaxed_overall,0.612,0.009747841205275417
654
- ≥3,15000,docvqa_val_anls,0.6656498012528964,0.006035466987037702
655
- ≥3,15000,infovqa_val_anls,0.2625991131461808,0.007063916588796129
656
- ≥3,15000,mme_total_score,1285.4465786314527,
657
- ≥3,15000,mmmu_val_mmmu_acc,0.30222,
658
- ≥3,15000,mmstar_average,0.3502185231309507,
659
- ≥3,15000,ocrbench_ocrbench_accuracy,0.558,
660
- ≥3,15000,seedbench_seed_all,0.5500833796553641,
661
- ≥3,15000,textvqa_val_exact_match,0.544,0.0067575389652278954
662
- ≥3,16000,ai2d_exact_match,0.4689119170984456,0.008981742470016596
663
- ≥3,16000,average,0.4804309718902879,
664
- ≥3,16000,average_rank,2.5,
665
- ≥3,16000,chartqa_relaxed_overall,0.6204,0.009707689307588963
666
- ≥3,16000,docvqa_val_anls,0.6742164965149466,0.0059800657435710326
667
- ≥3,16000,infovqa_val_anls,0.2633355771988975,0.00704601997176055
668
- ≥3,16000,mme_total_score,1288.4584833933575,
669
- ≥3,16000,mmmu_val_mmmu_acc,0.29556,
670
- ≥3,16000,mmstar_average,0.3443487528651147,
671
- ≥3,16000,ocrbench_ocrbench_accuracy,0.55,
672
- ≥3,16000,seedbench_seed_all,0.5508060033351863,
673
- ≥3,16000,textvqa_val_exact_match,0.5563,0.006742548063668376
674
- ≥3,17000,ai2d_exact_match,0.45595854922279794,0.008964175733819342
675
- ≥3,17000,average,0.4809373657329622,
676
- ≥3,17000,average_rank,3.3,
677
- ≥3,17000,chartqa_relaxed_overall,0.6204,0.009707689307588963
678
- ≥3,17000,docvqa_val_anls,0.6739488016448908,0.005975889304414765
679
- ≥3,17000,infovqa_val_anls,0.2580649809644441,0.007031141926644411
680
- ≥3,17000,mme_total_score,1230.4375750300119,
681
- ≥3,17000,mmmu_val_mmmu_acc,0.29444,
682
- ≥3,17000,mmstar_average,0.3444925534276732,
683
- ≥3,17000,ocrbench_ocrbench_accuracy,0.578,
684
- ≥3,17000,seedbench_seed_all,0.5565314063368538,
685
- ≥3,17000,textvqa_val_exact_match,0.5466,0.006752985159298985
686
- ≥3,18000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
687
- ≥3,18000,average,0.48088758936650067,
688
- ≥3,18000,average_rank,3.5,
689
- ≥3,18000,chartqa_relaxed_overall,0.6252,0.009683361554563506
690
- ≥3,18000,docvqa_val_anls,0.675384499731014,0.005997750609265588
691
- ≥3,18000,infovqa_val_anls,0.2579974692510198,0.0070128299378415275
692
- ≥3,18000,mme_total_score,1234.843237294918,
693
- ≥3,18000,mmmu_val_mmmu_acc,0.3,
694
- ≥3,18000,mmstar_average,0.3363850750308216,
695
- ≥3,18000,ocrbench_ocrbench_accuracy,0.566,
696
- ≥3,18000,seedbench_seed_all,0.5558643690939411,
697
- ≥3,18000,textvqa_val_exact_match,0.55196,0.006755291146330729
698
- ≥3,19000,ai2d_exact_match,0.4634067357512953,0.008975020819363737
699
- ≥3,19000,average,0.4861360634692545,
700
- ≥3,19000,average_rank,3.3,
701
- ≥3,19000,chartqa_relaxed_overall,0.6312,0.009651522406019766
702
- ≥3,19000,docvqa_val_anls,0.6819220996842664,0.005927423649467908
703
- ≥3,19000,infovqa_val_anls,0.26277439983326806,0.007102707331042042
704
- ≥3,19000,mme_total_score,1337.9653861544616,
705
- ≥3,19000,mmmu_val_mmmu_acc,0.29889,
706
- ≥3,19000,mmstar_average,0.34778832316957964,
707
- ≥3,19000,ocrbench_ocrbench_accuracy,0.574,
708
- ≥3,19000,seedbench_seed_all,0.5614230127848805,
709
- ≥3,19000,textvqa_val_exact_match,0.55382,0.006743039020727005
710
- ≥3,20000,ai2d_exact_match,0.4841321243523316,0.008994621193008031
711
- ≥3,20000,average,0.4916087790351852,
712
- ≥3,20000,average_rank,2.3,
713
- ≥3,20000,chartqa_relaxed_overall,0.638,0.009613499245701268
714
- ≥3,20000,docvqa_val_anls,0.6839168937073106,0.005936410873687919
715
- ≥3,20000,infovqa_val_anls,0.25441216838205727,0.006890877173562315
716
- ≥3,20000,mme_total_score,1330.3037214885953,
717
- ≥3,20000,mmmu_val_mmmu_acc,0.31,
718
- ≥3,20000,mmstar_average,0.35052721898280503,
719
- ≥3,20000,ocrbench_ocrbench_accuracy,0.572,
720
- ≥3,20000,seedbench_seed_all,0.5630906058921623,
721
- ≥3,20000,textvqa_val_exact_match,0.5684000000000001,0.00672360984783302
722
- ≥4,1000,ai2d_exact_match,0.26360103626943004,0.00792979255467583
723
- ≥4,1000,average,0.26922373369534647,
724
- ≥4,1000,average_rank,3.3,
725
- ≥4,1000,chartqa_relaxed_overall,0.3488,0.009533718094861256
726
- ≥4,1000,docvqa_val_anls,0.3599045480096881,0.005885735735631119
727
- ≥4,1000,infovqa_val_anls,0.17148252623256244,0.0061724612150041895
728
- ≥4,1000,mme_total_score,1104.3533413365346,
729
- ≥4,1000,mmmu_val_mmmu_acc,0.24,
730
- ≥4,1000,mmstar_average,0.21109041770474804,
731
- ≥4,1000,ocrbench_ocrbench_accuracy,0.29,
732
- ≥4,1000,seedbench_seed_all,0.24313507504168982,
733
- ≥4,1000,textvqa_val_exact_match,0.295,0.006241441429527609
734
- ≥4,2000,ai2d_exact_match,0.26295336787564766,0.007923526907377255
735
- ≥4,2000,average,0.3192621308996215,
736
- ≥4,2000,average_rank,2.9,
737
- ≥4,2000,chartqa_relaxed_overall,0.4644,0.009976616117083942
738
- ≥4,2000,docvqa_val_anls,0.44610634422212336,0.006125661837378556
739
- ≥4,2000,infovqa_val_anls,0.19012118870963063,0.006420072608935975
740
- ≥4,2000,mme_total_score,1052.5613245298118,
741
- ≥4,2000,mmmu_val_mmmu_acc,0.23889,
742
- ≥4,2000,mmstar_average,0.22088912220303317,
743
- ≥4,2000,ocrbench_ocrbench_accuracy,0.389,
744
- ≥4,2000,seedbench_seed_all,0.262479155086159,
745
- ≥4,2000,textvqa_val_exact_match,0.39852,0.006693677836929181
746
- ≥4,3000,ai2d_exact_match,0.2545336787564767,0.007840040862810524
747
- ≥4,3000,average,0.34899183633853254,
748
- ≥4,3000,average_rank,3.1,
749
- ≥4,3000,chartqa_relaxed_overall,0.5144,0.009997851710018818
750
- ≥4,3000,docvqa_val_anls,0.5122633926443586,0.006250170224123374
751
- ≥4,3000,infovqa_val_anls,0.21839296983497156,0.006786311152255019
752
- ≥4,3000,mme_total_score,1148.9873949579833,
753
- ≥4,3000,mmmu_val_mmmu_acc,0.24667,
754
- ≥4,3000,mmstar_average,0.23884910949080793,
755
- ≥4,3000,ocrbench_ocrbench_accuracy,0.426,
756
- ≥4,3000,seedbench_seed_all,0.29927737632017787,
757
- ≥4,3000,textvqa_val_exact_match,0.43054,0.006761938068430401
758
- ≥4,4000,ai2d_exact_match,0.2814119170984456,0.00809362228799086
759
- ≥4,4000,average,0.3808723899304912,
760
- ≥4,4000,average_rank,2.3,
761
- ≥4,4000,chartqa_relaxed_overall,0.536,0.009976041728231964
762
- ≥4,4000,docvqa_val_anls,0.5444976153718191,0.006262351643342788
763
- ≥4,4000,infovqa_val_anls,0.22943118895386538,0.006865542219383826
764
- ≥4,4000,mme_total_score,1161.4330732292917,
765
- ≥4,4000,mmmu_val_mmmu_acc,0.26889,
766
- ≥4,4000,mmstar_average,0.2546319608241094,
767
- ≥4,4000,ocrbench_ocrbench_accuracy,0.459,
768
- ≥4,4000,seedbench_seed_all,0.39988882712618123,
769
- ≥4,4000,textvqa_val_exact_match,0.4541,0.006780990662644609
770
- ≥4,5000,ai2d_exact_match,0.31573834196891193,0.00836578020190971
771
- ≥4,5000,average,0.4004212057382194,
772
- ≥4,5000,average_rank,2.7,
773
- ≥4,5000,chartqa_relaxed_overall,0.5544,0.009942625323290008
774
- ≥4,5000,docvqa_val_anls,0.556855142418819,0.006267140081468451
775
- ≥4,5000,infovqa_val_anls,0.23435340618373432,0.006883129487757931
776
- ≥4,5000,mme_total_score,1145.157863145258,
777
- ≥4,5000,mmmu_val_mmmu_acc,0.26556,
778
- ≥4,5000,mmstar_average,0.2888277743020811,
779
- ≥4,5000,ocrbench_ocrbench_accuracy,0.475,
780
- ≥4,5000,seedbench_seed_all,0.445136186770428,
781
- ≥4,5000,textvqa_val_exact_match,0.46792,0.0067973094238147356
782
- ≥4,6000,ai2d_exact_match,0.38471502590673573,0.008756678690415541
783
- ≥4,6000,average,0.42131977921781544,
784
- ≥4,6000,average_rank,3.0,
785
- ≥4,6000,chartqa_relaxed_overall,0.556,0.00993907007952043
786
- ≥4,6000,docvqa_val_anls,0.5727106862384739,0.006269180765398416
787
- ≥4,6000,infovqa_val_anls,0.2310709838980833,0.006744459748098398
788
- ≥4,6000,mme_total_score,1139.8311324529811,
789
- ≥4,6000,mmmu_val_mmmu_acc,0.27,
790
- ≥4,6000,mmstar_average,0.30779610290926424,
791
- ≥4,6000,ocrbench_ocrbench_accuracy,0.492,
792
- ≥4,6000,seedbench_seed_all,0.4933852140077821,
793
- ≥4,6000,textvqa_val_exact_match,0.4841999999999999,0.006796772117869219
794
- ≥4,7000,ai2d_exact_match,0.39281088082901555,0.008789930274160654
795
- ≥4,7000,average,0.42891500537341953,
796
- ≥4,7000,average_rank,2.9,
797
- ≥4,7000,chartqa_relaxed_overall,0.576,0.009885782289560632
798
- ≥4,7000,docvqa_val_anls,0.5907488324071782,0.006231156163373406
799
- ≥4,7000,infovqa_val_anls,0.24013816441297325,0.006930097636315065
800
- ≥4,7000,mme_total_score,1162.137755102041,
801
- ≥4,7000,mmmu_val_mmmu_acc,0.27556,
802
- ≥4,7000,mmstar_average,0.29752599783778977,
803
- ≥4,7000,ocrbench_ocrbench_accuracy,0.504,
804
- ≥4,7000,seedbench_seed_all,0.5001111728738188,
805
- ≥4,7000,textvqa_val_exact_match,0.48333999999999994,0.006805450147517214
806
- ≥4,8000,ai2d_exact_match,0.4164507772020725,0.008872627955954676
807
- ≥4,8000,average,0.43574351275219425,
808
- ≥4,8000,average_rank,3.5,
809
- ≥4,8000,chartqa_relaxed_overall,0.5808,0.009870537726284339
810
- ≥4,8000,docvqa_val_anls,0.6057226019616091,0.0061946427553956785
811
- ≥4,8000,infovqa_val_anls,0.2476713069705094,0.006953489019987495
812
- ≥4,8000,mme_total_score,1170.280612244898,
813
- ≥4,8000,mmmu_val_mmmu_acc,0.26778,
814
- ≥4,8000,mmstar_average,0.30520454953605713,
815
- ≥4,8000,ocrbench_ocrbench_accuracy,0.496,
816
- ≥4,8000,seedbench_seed_all,0.5082823790994997,
817
- ≥4,8000,textvqa_val_exact_match,0.49378,0.006806491606223952
818
- ≥4,9000,ai2d_exact_match,0.42357512953367876,0.008893409023558714
819
- ≥4,9000,average,0.441337144868937,
820
- ≥4,9000,average_rank,3.4,
821
- ≥4,9000,chartqa_relaxed_overall,0.578,0.00987954665846924
822
- ≥4,9000,docvqa_val_anls,0.6243353881540346,0.006123815047404004
823
- ≥4,9000,infovqa_val_anls,0.2437398253282973,0.00692277294272151
824
- ≥4,9000,mme_total_score,1255.001700680272,
825
- ≥4,9000,mmmu_val_mmmu_acc,0.26778,
826
- ≥4,9000,mmstar_average,0.31167080905344985,
827
- ≥4,9000,ocrbench_ocrbench_accuracy,0.512,
828
- ≥4,9000,seedbench_seed_all,0.5116731517509727,
829
- ≥4,9000,textvqa_val_exact_match,0.49926000000000004,0.006799642454386958
830
- ≥4,10000,ai2d_exact_match,0.44462435233160624,0.00894379269709736
831
- ≥4,10000,average,0.4536388119594498,
832
- ≥4,10000,average_rank,3.6,
833
- ≥4,10000,chartqa_relaxed_overall,0.5992,0.00980317218424473
834
- ≥4,10000,docvqa_val_anls,0.6264595846035441,0.006147505656275056
835
- ≥4,10000,infovqa_val_anls,0.2598110483089896,0.00706252458320144
836
- ≥4,10000,mme_total_score,1192.952080832333,
837
- ≥4,10000,mmmu_val_mmmu_acc,0.28556,
838
- ≥4,10000,mmstar_average,0.3186673407344323,
839
- ≥4,10000,ocrbench_ocrbench_accuracy,0.52,
840
- ≥4,10000,seedbench_seed_all,0.5205669816564759,
841
- ≥4,10000,textvqa_val_exact_match,0.5078600000000001,0.006802447996107573
842
- ≥4,11000,ai2d_exact_match,0.4536917098445596,0.008960474382205324
843
- ≥4,11000,average,0.46152725733636885,
844
- ≥4,11000,average_rank,2.3,
845
- ≥4,11000,chartqa_relaxed_overall,0.6004,0.009798282427824488
846
- ≥4,11000,docvqa_val_anls,0.6401993666501584,0.0060898160255800525
847
- ≥4,11000,infovqa_val_anls,0.2552761209118603,0.007046581941151624
848
- ≥4,11000,mme_total_score,1246.6340536214486,
849
- ≥4,11000,mmmu_val_mmmu_acc,0.28,
850
- ≥4,11000,mmstar_average,0.3347344054467562,
851
- ≥4,11000,ocrbench_ocrbench_accuracy,0.533,
852
- ≥4,11000,seedbench_seed_all,0.5306837131739855,
853
- ≥4,11000,textvqa_val_exact_match,0.5257599999999999,0.006772980077619183
854
- ≥4,12000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
855
- ≥4,12000,average,0.46100484234717837,
856
- ≥4,12000,average_rank,3.7,
857
- ≥4,12000,chartqa_relaxed_overall,0.5956,0.009817474681589429
858
- ≥4,12000,docvqa_val_anls,0.6409268162702743,0.006097072959583667
859
- ≥4,12000,infovqa_val_anls,0.26230050824120466,0.007170670588017343
860
- ≥4,12000,mme_total_score,1168.390556222489,
861
- ≥4,12000,mmmu_val_mmmu_acc,0.26889,
862
- ≥4,12000,mmstar_average,0.3293674421306994,
863
- ≥4,12000,ocrbench_ocrbench_accuracy,0.538,
864
- ≥4,12000,seedbench_seed_all,0.5314619232907171,
865
- ≥4,12000,textvqa_val_exact_match,0.5233,0.006791483405661084
866
- ≥4,13000,ai2d_exact_match,0.46081606217616583,0.008971477299154906
867
- ≥4,13000,average,0.46897968661537504,
868
- ≥4,13000,average_rank,3.0,
869
- ≥4,13000,chartqa_relaxed_overall,0.6084,0.00976411343463736
870
- ≥4,13000,docvqa_val_anls,0.6557097904355208,0.006045284321472833
871
- ≥4,13000,infovqa_val_anls,0.25716935409374025,0.007037968981507592
872
- ≥4,13000,mme_total_score,1214.4760904361744,
873
- ≥4,13000,mmmu_val_mmmu_acc,0.27444,
874
- ≥4,13000,mmstar_average,0.35062705343328215,
875
- ≥4,13000,ocrbench_ocrbench_accuracy,0.542,
876
- ≥4,13000,seedbench_seed_all,0.5388549193996665,
877
- ≥4,13000,textvqa_val_exact_match,0.5328,0.006772208248489718
878
- ≥4,14000,ai2d_exact_match,0.4637305699481865,0.008975446629055962
879
- ≥4,14000,average,0.46882712562329804,
880
- ≥4,14000,average_rank,3.4,
881
- ≥4,14000,chartqa_relaxed_overall,0.6052,0.009778109662477129
882
- ≥4,14000,docvqa_val_anls,0.6600293980607723,0.006003818486747537
883
- ≥4,14000,infovqa_val_anls,0.2604896578960276,0.0070806001081496605
884
- ≥4,14000,mme_total_score,1180.2360944377751,
885
- ≥4,14000,mmmu_val_mmmu_acc,0.29889,
886
- ≥4,14000,mmstar_average,0.3370405135985262,
887
- ≥4,14000,ocrbench_ocrbench_accuracy,0.532,
888
- ≥4,14000,seedbench_seed_all,0.5311839911061701,
889
- ≥4,14000,textvqa_val_exact_match,0.53088,0.006765681045393848
890
- ≥4,15000,ai2d_exact_match,0.469559585492228,0.008982461065390123
891
- ≥4,15000,average,0.47678210727691706,
892
- ≥4,15000,average_rank,3.0,
893
- ≥4,15000,chartqa_relaxed_overall,0.6228,0.009695651925812239
894
- ≥4,15000,docvqa_val_anls,0.668732849209273,0.006002172541493102
895
- ≥4,15000,infovqa_val_anls,0.2541377129865746,0.006911037097155498
896
- ≥4,15000,mme_total_score,1198.8395358143257,
897
- ≥4,15000,mmmu_val_mmmu_acc,0.28111,
898
- ≥4,15000,mmstar_average,0.3574887121899482,
899
- ≥4,15000,ocrbench_ocrbench_accuracy,0.558,
900
- ≥4,15000,seedbench_seed_all,0.5421901056142301,
901
- ≥4,15000,textvqa_val_exact_match,0.53702,0.0067620891069120025
902
- ≥4,16000,ai2d_exact_match,0.4689119170984456,0.00898174247001659
903
- ≥4,16000,average,0.47623501147363423,
904
- ≥4,16000,average_rank,3.7,
905
- ≥4,16000,chartqa_relaxed_overall,0.6184,0.009717527882093043
906
- ≥4,16000,docvqa_val_anls,0.664711612332228,0.006033753206179003
907
- ≥4,16000,infovqa_val_anls,0.26137627968800997,0.0069587136315641595
908
- ≥4,16000,mme_total_score,1223.327631052421,
909
- ≥4,16000,mmmu_val_mmmu_acc,0.27778,
910
- ≥4,16000,mmstar_average,0.3532221312757646,
911
- ≥4,16000,ocrbench_ocrbench_accuracy,0.545,
912
- ≥4,16000,seedbench_seed_all,0.5476931628682602,
913
- ≥4,16000,textvqa_val_exact_match,0.54902,0.006730591957147508
914
- ≥4,17000,ai2d_exact_match,0.47830310880829013,0.008990677331728418
915
- ≥4,17000,average,0.4815150623543914,
916
- ≥4,17000,average_rank,2.8,
917
- ≥4,17000,chartqa_relaxed_overall,0.6208,0.009705700605814084
918
- ≥4,17000,docvqa_val_anls,0.6784945768946954,0.005958779114256312
919
- ≥4,17000,infovqa_val_anls,0.27415576971914574,0.007211057524316044
920
- ≥4,17000,mme_total_score,1267.6510604241696,
921
- ≥4,17000,mmmu_val_mmmu_acc,0.27889,
922
- ≥4,17000,mmstar_average,0.35485659715149337,
923
- ≥4,17000,ocrbench_ocrbench_accuracy,0.55,
924
- ≥4,17000,seedbench_seed_all,0.5479155086158978,
925
- ≥4,17000,textvqa_val_exact_match,0.5502199999999999,0.006738803500215962
926
- ≥4,18000,ai2d_exact_match,0.4795984455958549,0.008991659681159872
927
- ≥4,18000,average,0.4839656525796875,
928
- ≥4,18000,average_rank,3.1,
929
- ≥4,18000,chartqa_relaxed_overall,0.6228,0.009695651925812239
930
- ≥4,18000,docvqa_val_anls,0.680615041882376,0.005957029786047422
931
- ≥4,18000,infovqa_val_anls,0.27507992619170296,0.007267921800589956
932
- ≥4,18000,mme_total_score,1226.5048019207684,
933
- ≥4,18000,mmmu_val_mmmu_acc,0.28111,
934
- ≥4,18000,mmstar_average,0.35607565298805366,
935
- ≥4,18000,ocrbench_ocrbench_accuracy,0.555,
936
- ≥4,18000,seedbench_seed_all,0.5532518065591996,
937
- ≥4,18000,textvqa_val_exact_match,0.55216,0.006730239676654988
938
- ≥4,19000,ai2d_exact_match,0.4734455958549223,0.008986453895645547
939
- ≥4,19000,average,0.485443851233213,
940
- ≥4,19000,average_rank,3.0,
941
- ≥4,19000,chartqa_relaxed_overall,0.6276,0.009670817229291067
942
- ≥4,19000,docvqa_val_anls,0.690884348495626,0.005908240141234498
943
- ≥4,19000,infovqa_val_anls,0.2676836840845966,0.007165567282387595
944
- ≥4,19000,mme_total_score,1323.2516006402561,
945
- ≥4,19000,mmmu_val_mmmu_acc,0.28556,
946
- ≥4,19000,mmstar_average,0.33406913716627346,
947
- ≥4,19000,ocrbench_ocrbench_accuracy,0.584,
948
- ≥4,19000,seedbench_seed_all,0.5414118954974986,
949
- ≥4,19000,textvqa_val_exact_match,0.56434,0.006692191716171407
950
- ≥4,20000,ai2d_exact_match,0.4876943005181347,0.008996428218289526
951
- ≥4,20000,average,0.4906341423361293,
952
- ≥4,20000,average_rank,3.3,
953
- ≥4,20000,chartqa_relaxed_overall,0.6284,0.009666579183001631
954
- ≥4,20000,docvqa_val_anls,0.6887236251150223,0.005918556723502163
955
- ≥4,20000,infovqa_val_anls,0.2809124119459898,0.007354611102020885
956
- ≥4,20000,mme_total_score,1254.5532212885155,
957
- ≥4,20000,mmmu_val_mmmu_acc,0.29333,
958
- ≥4,20000,mmstar_average,0.34736535367392096,
959
- ≥4,20000,ocrbench_ocrbench_accuracy,0.572,
960
- ≥4,20000,seedbench_seed_all,0.5508615897720957,
961
- ≥4,20000,textvqa_val_exact_match,0.56642,0.00672606309106159
962
- ≥5,1000,ai2d_exact_match,0.26327720207253885,0.007926662492947056
963
- ≥5,1000,average,0.27709006947371073,
964
- ≥5,1000,average_rank,2.6,
965
- ≥5,1000,chartqa_relaxed_overall,0.3412,0.009484144853461517
966
- ≥5,1000,docvqa_val_anls,0.36296241117667905,0.005852839558467308
967
- ≥5,1000,infovqa_val_anls,0.17994878830754762,0.006336933369747534
968
- ≥5,1000,mme_total_score,968.375450180072,
969
- ≥5,1000,mmmu_val_mmmu_acc,0.26667,
970
- ≥5,1000,mmstar_average,0.22684359669162246,
971
- ≥5,1000,ocrbench_ocrbench_accuracy,0.301,
972
- ≥5,1000,seedbench_seed_all,0.25152862701500833,
973
- ≥5,1000,textvqa_val_exact_match,0.30038,0.006282823083071704
974
- ≥5,2000,ai2d_exact_match,0.27331606217616583,0.008021157484423327
975
- ≥5,2000,average,0.318491261297989,
976
- ≥5,2000,average_rank,3.2,
977
- ≥5,2000,chartqa_relaxed_overall,0.4524,0.009956573172519544
978
- ≥5,2000,docvqa_val_anls,0.4578740641673747,0.006180081722767688
979
- ≥5,2000,infovqa_val_anls,0.1919057230410833,0.006401757863597739
980
- ≥5,2000,mme_total_score,1031.2603041216487,
981
- ≥5,2000,mmmu_val_mmmu_acc,0.24667,
982
- ≥5,2000,mmstar_average,0.21129996032951712,
983
- ≥5,2000,ocrbench_ocrbench_accuracy,0.383,
984
- ≥5,2000,seedbench_seed_all,0.25597554196775985,
985
- ≥5,2000,textvqa_val_exact_match,0.39398,0.0066750028503822015
986
- ≥5,3000,ai2d_exact_match,0.2661917098445596,0.007954634970279373
987
- ≥5,3000,average,0.3470898411915701,
988
- ≥5,3000,average_rank,3.1,
989
- ≥5,3000,chartqa_relaxed_overall,0.4888,0.009999490983443667
990
- ≥5,3000,docvqa_val_anls,0.5063663265388635,0.006269377896147078
991
- ≥5,3000,infovqa_val_anls,0.2002412084672373,0.006449644926640854
992
- ≥5,3000,mme_total_score,1176.8578431372548,
993
- ≥5,3000,mmmu_val_mmmu_acc,0.25889,
994
- ≥5,3000,mmstar_average,0.2226891646728035,
995
- ≥5,3000,ocrbench_ocrbench_accuracy,0.422,
996
- ≥5,3000,seedbench_seed_all,0.32229016120066706,
997
- ≥5,3000,textvqa_val_exact_match,0.43633999999999995,0.006743513614961789
998
- ≥5,4000,ai2d_exact_match,0.32091968911917096,0.008402150106895235
999
- ≥5,4000,average,0.38454946481840957,
1000
- ≥5,4000,average_rank,3.0,
1001
- ≥5,4000,chartqa_relaxed_overall,0.5244,0.009990083919101193
1002
- ≥5,4000,docvqa_val_anls,0.5408182220870532,0.0062304604635426315
1003
- ≥5,4000,infovqa_val_anls,0.21034975209325477,0.006529781109938355
1004
- ≥5,4000,mme_total_score,1186.4263705482194,
1005
- ≥5,4000,mmmu_val_mmmu_acc,0.26556,
1006
- ≥5,4000,mmstar_average,0.26918979355147643,
1007
- ≥5,4000,ocrbench_ocrbench_accuracy,0.452,
1008
- ≥5,4000,seedbench_seed_all,0.4339077265147304,
1009
- ≥5,4000,textvqa_val_exact_match,0.4438,0.006776008770579609
1010
- ≥5,5000,ai2d_exact_match,0.3494170984455959,0.008581339503665948
1011
- ≥5,5000,average,0.4053929772745627,
1012
- ≥5,5000,average_rank,2.9,
1013
- ≥5,5000,chartqa_relaxed_overall,0.546,0.009959582185560013
1014
- ≥5,5000,docvqa_val_anls,0.5611769594797935,0.006252030837783964
1015
- ≥5,5000,infovqa_val_anls,0.2283202771889911,0.006874345513158979
1016
- ≥5,5000,mme_total_score,1179.6603641456581,
1017
- ≥5,5000,mmmu_val_mmmu_acc,0.27556,
1018
- ≥5,5000,mmstar_average,0.28276518409209217,
1019
- ≥5,5000,ocrbench_ocrbench_accuracy,0.464,
1020
- ≥5,5000,seedbench_seed_all,0.4750972762645914,
1021
- ≥5,5000,textvqa_val_exact_match,0.4662,0.0067984671677640855
1022
- ≥5,6000,ai2d_exact_match,0.3636658031088083,0.008658158841882573
1023
- ≥5,6000,average,0.41623598541202544,
1024
- ≥5,6000,average_rank,2.6,
1025
- ≥5,6000,chartqa_relaxed_overall,0.5584,0.009933541468098847
1026
- ≥5,6000,docvqa_val_anls,0.5839255211800125,0.006223251970774856
1027
- ≥5,6000,infovqa_val_anls,0.23899504944949723,0.007013133491201096
1028
- ≥5,6000,mme_total_score,1252.7314925970388,
1029
- ≥5,6000,mmmu_val_mmmu_acc,0.27222,
1030
- ≥5,6000,mmstar_average,0.3101670336024846,
1031
- ≥5,6000,ocrbench_ocrbench_accuracy,0.473,
1032
- ≥5,6000,seedbench_seed_all,0.49483046136742637,
1033
- ≥5,6000,textvqa_val_exact_match,0.45092,0.006772193384764505
1034
- ≥5,7000,ai2d_exact_match,0.42033678756476683,0.008884198538329093
1035
- ≥5,7000,average,0.4338560588435303,
1036
- ≥5,7000,average_rank,2.5,
1037
- ≥5,7000,chartqa_relaxed_overall,0.5692,0.00990574548014469
1038
- ≥5,7000,docvqa_val_anls,0.5924368390904757,0.006231022369252223
1039
- ≥5,7000,infovqa_val_anls,0.23945153983485024,0.007006534034576772
1040
- ≥5,7000,mme_total_score,1315.113445378151,
1041
- ≥5,7000,mmmu_val_mmmu_acc,0.3,
1042
- ≥5,7000,mmstar_average,0.31063340423564356,
1043
- ≥5,7000,ocrbench_ocrbench_accuracy,0.488,
1044
- ≥5,7000,seedbench_seed_all,0.5067259588660367,
1045
- ≥5,7000,textvqa_val_exact_match,0.47791999999999996,0.006793800546466833
1046
- ≥5,8000,ai2d_exact_match,0.42908031088082904,0.008908169846895226
1047
- ≥5,8000,average,0.43778255861533233,
1048
- ≥5,8000,average_rank,3.0,
1049
- ≥5,8000,chartqa_relaxed_overall,0.5752,0.009888230116554488
1050
- ≥5,8000,docvqa_val_anls,0.6032859006895523,0.006193925022795706
1051
- ≥5,8000,infovqa_val_anls,0.24493490021598546,0.007008771158507111
1052
- ≥5,8000,mme_total_score,1304.6824729891955,
1053
- ≥5,8000,mmmu_val_mmmu_acc,0.28667,
1054
- ≥5,8000,mmstar_average,0.31703546216629863,
1055
- ≥5,8000,ocrbench_ocrbench_accuracy,0.487,
1056
- ≥5,8000,seedbench_seed_all,0.5096164535853251,
1057
- ≥5,8000,textvqa_val_exact_match,0.48722,0.006804659800386776
1058
- ≥5,9000,ai2d_exact_match,0.42940414507772023,0.008909003051055709
1059
- ≥5,9000,average,0.44649777930382,
1060
- ≥5,9000,average_rank,2.5,
1061
- ≥5,9000,chartqa_relaxed_overall,0.5792,0.009875725592704212
1062
- ≥5,9000,docvqa_val_anls,0.6158422097964253,0.00617698110304048
1063
- ≥5,9000,infovqa_val_anls,0.24039717009699607,0.0068877247346275485
1064
- ≥5,9000,mme_total_score,1379.7254901960782,
1065
- ≥5,9000,mmmu_val_mmmu_acc,0.29889,
1066
- ≥5,9000,mmstar_average,0.3280690123874737,
1067
- ≥5,9000,ocrbench_ocrbench_accuracy,0.513,
1068
- ≥5,9000,seedbench_seed_all,0.5234574763757643,
1069
- ≥5,9000,textvqa_val_exact_match,0.4902200000000001,0.006801597067199211
1070
- ≥5,10000,ai2d_exact_match,0.45012953367875647,0.00895427929990258
1071
- ≥5,10000,average,0.4555663389491801,
1072
- ≥5,10000,average_rank,2.9,
1073
- ≥5,10000,chartqa_relaxed_overall,0.5844,0.009858475126140203
1074
- ≥5,10000,docvqa_val_anls,0.6189420793161403,0.006040465868816934
1075
- ≥5,10000,infovqa_val_anls,0.24850918819779613,0.007091394184737253
1076
- ≥5,10000,mme_total_score,1235.7704081632655,
1077
- ≥5,10000,mmmu_val_mmmu_acc,0.27667,
1078
- ≥5,10000,mmstar_average,0.34675895640940496,
1079
- ≥5,10000,ocrbench_ocrbench_accuracy,0.528,
1080
- ≥5,10000,seedbench_seed_all,0.5291272929405225,
1081
- ≥5,10000,textvqa_val_exact_match,0.51756,0.006786717998284417
1082
- ≥5,11000,ai2d_exact_match,0.4566062176165803,0.008965198879336196
1083
- ≥5,11000,average,0.458748059148796,
1084
- ≥5,11000,average_rank,2.9,
1085
- ≥5,11000,chartqa_relaxed_overall,0.5916,0.0098327233755248
1086
- ≥5,11000,docvqa_val_anls,0.633602507666147,0.006134122729213928
1087
- ≥5,11000,infovqa_val_anls,0.2621320066294427,0.007275786683175354
1088
- ≥5,11000,mme_total_score,1326.4276710684273,
1089
- ≥5,11000,mmmu_val_mmmu_acc,0.27667,
1090
- ≥5,11000,mmstar_average,0.34479339575773355,
1091
- ≥5,11000,ocrbench_ocrbench_accuracy,0.517,
1092
- ≥5,11000,seedbench_seed_all,0.5311284046692607,
1093
- ≥5,11000,textvqa_val_exact_match,0.5152000000000001,0.006786619456012555
1094
- ≥5,12000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
1095
- ≥5,12000,average,0.4644995480385772,
1096
- ≥5,12000,average_rank,2.3,
1097
- ≥5,12000,chartqa_relaxed_overall,0.596,0.009815912634917984
1098
- ≥5,12000,docvqa_val_anls,0.6453485539631237,0.006065269954977215
1099
- ≥5,12000,infovqa_val_anls,0.2685572578806166,0.007278550841020009
1100
- ≥5,12000,mme_total_score,1374.9406762705082,
1101
- ≥5,12000,mmmu_val_mmmu_acc,0.28444,
1102
- ≥5,12000,mmstar_average,0.35205377405882654,
1103
- ≥5,12000,ocrbench_ocrbench_accuracy,0.519,
1104
- ≥5,12000,seedbench_seed_all,0.5350194552529183,
1105
- ≥5,12000,textvqa_val_exact_match,0.52088,0.006777757204160069
1106
- ≥5,13000,ai2d_exact_match,0.4640544041450777,0.008975868633841907
1107
- ≥5,13000,average,0.4696984757423332,
1108
- ≥5,13000,average_rank,2.7,
1109
- ≥5,13000,chartqa_relaxed_overall,0.608,0.00976588700628918
1110
- ≥5,13000,docvqa_val_anls,0.6599237778239753,0.006035894149838363
1111
- ≥5,13000,infovqa_val_anls,0.25759117282312316,0.007107246020667877
1112
- ≥5,13000,mme_total_score,1326.0453181272508,
1113
- ≥5,13000,mmmu_val_mmmu_acc,0.28667,
1114
- ≥5,13000,mmstar_average,0.35252858336464304,
1115
- ≥5,13000,ocrbench_ocrbench_accuracy,0.533,
1116
- ≥5,13000,seedbench_seed_all,0.5330183435241801,
1117
- ≥5,13000,textvqa_val_exact_match,0.5325,0.006770636476998357
1118
- ≥5,14000,ai2d_exact_match,0.4689119170984456,0.00898174247001659
1119
- ≥5,14000,average,0.47293227498131896,
1120
- ≥5,14000,average_rank,2.7,
1121
- ≥5,14000,chartqa_relaxed_overall,0.614,0.009738559226822298
1122
- ≥5,14000,docvqa_val_anls,0.6583491716485876,0.0060256160547597325
1123
- ≥5,14000,infovqa_val_anls,0.26613522559599984,0.0071532088405842145
1124
- ≥5,14000,mme_total_score,1278.5425170068027,
1125
- ≥5,14000,mmmu_val_mmmu_acc,0.28,
1126
- ≥5,14000,mmstar_average,0.35624004153386235,
1127
- ≥5,14000,ocrbench_ocrbench_accuracy,0.55,
1128
- ≥5,14000,seedbench_seed_all,0.5454141189549749,
1129
- ≥5,14000,textvqa_val_exact_match,0.5173399999999999,0.006787096420087393
1130
- ≥5,15000,ai2d_exact_match,0.4740932642487047,0.008987066275159846
1131
- ≥5,15000,average,0.47568039073709784,
1132
- ≥5,15000,average_rank,3.0,
1133
- ≥5,15000,chartqa_relaxed_overall,0.602,0.00979166741164548
1134
- ≥5,15000,docvqa_val_anls,0.6649825816931088,0.006012202194059076
1135
- ≥5,15000,infovqa_val_anls,0.2659187859072639,0.007233849219121225
1136
- ≥5,15000,mme_total_score,1301.498799519808,
1137
- ≥5,15000,mmmu_val_mmmu_acc,0.30333,
1138
- ≥5,15000,mmstar_average,0.363574304462402,
1139
- ≥5,15000,ocrbench_ocrbench_accuracy,0.536,
1140
- ≥5,15000,seedbench_seed_all,0.5402445803224013,
1141
- ≥5,15000,textvqa_val_exact_match,0.53098,0.006774896882281907
1142
- ≥5,16000,ai2d_exact_match,0.47538860103626945,0.008988245555188545
1143
- ≥5,16000,average,0.48103362013771567,
1144
- ≥5,16000,average_rank,2.6,
1145
- ≥5,16000,chartqa_relaxed_overall,0.6172,0.009723347231923635
1146
- ≥5,16000,docvqa_val_anls,0.6661394800733964,0.006000339067695713
1147
- ≥5,16000,infovqa_val_anls,0.27200681388207976,0.007361243845813883
1148
- ≥5,16000,mme_total_score,1312.4185674269709,
1149
- ≥5,16000,mmmu_val_mmmu_acc,0.30667,
1150
- ≥5,16000,mmstar_average,0.352673072573432,
1151
- ≥5,16000,ocrbench_ocrbench_accuracy,0.553,
1152
- ≥5,16000,seedbench_seed_all,0.5483046136742635,
1153
- ≥5,16000,textvqa_val_exact_match,0.53792,0.0067618902203356104
1154
- ≥5,17000,ai2d_exact_match,0.4740932642487047,0.008987066275159846
1155
- ≥5,17000,average,0.4842246444979549,
1156
- ≥5,17000,average_rank,3.1,
1157
- ≥5,17000,chartqa_relaxed_overall,0.6252,0.009683361554563506
1158
- ≥5,17000,docvqa_val_anls,0.6727784028551866,0.005982986502554192
1159
- ≥5,17000,infovqa_val_anls,0.273461783643309,0.00736211121641681
1160
- ≥5,17000,mme_total_score,1256.561224489796,
1161
- ≥5,17000,mmmu_val_mmmu_acc,0.31889,
1162
- ≥5,17000,mmstar_average,0.35664172938975786,
1163
- ≥5,17000,ocrbench_ocrbench_accuracy,0.545,
1164
- ≥5,17000,seedbench_seed_all,0.549916620344636,
1165
- ≥5,17000,textvqa_val_exact_match,0.5420400000000001,0.006760567190239792
1166
- ≥5,18000,ai2d_exact_match,0.4802461139896373,0.008992128148477658
1167
- ≥5,18000,average,0.48392876207158253,
1168
- ≥5,18000,average_rank,2.9,
1169
- ≥5,18000,chartqa_relaxed_overall,0.6252,0.009683361554563506
1170
- ≥5,18000,docvqa_val_anls,0.68034033548242,0.005889534044935538
1171
- ≥5,18000,infovqa_val_anls,0.28015930560506613,0.007380855727131182
1172
- ≥5,18000,mme_total_score,1380.5266106442577,
1173
- ≥5,18000,mmmu_val_mmmu_acc,0.3,
1174
- ≥5,18000,mmstar_average,0.34877922919246646,
1175
- ≥5,18000,ocrbench_ocrbench_accuracy,0.549,
1176
- ≥5,18000,seedbench_seed_all,0.5529738743746526,
1177
- ≥5,18000,textvqa_val_exact_match,0.5386599999999999,0.0067648675941745775
1178
- ≥5,19000,ai2d_exact_match,0.4805699481865285,0.008992356706334513
1179
- ≥5,19000,average,0.49271643602329757,
1180
- ≥5,19000,average_rank,2.8,
1181
- ≥5,19000,chartqa_relaxed_overall,0.6248,0.009685427559111736
1182
- ≥5,19000,docvqa_val_anls,0.6825000217737053,0.005934471601355602
1183
- ≥5,19000,infovqa_val_anls,0.2841253071402532,0.007403930662950274
1184
- ≥5,19000,mme_total_score,1261.751700680272,
1185
- ≥5,19000,mmmu_val_mmmu_acc,0.32,
1186
- ≥5,19000,mmstar_average,0.3611420745688909,
1187
- ≥5,19000,ocrbench_ocrbench_accuracy,0.572,
1188
- ≥5,19000,seedbench_seed_all,0.5550305725403002,
1189
- ≥5,19000,textvqa_val_exact_match,0.5542799999999999,0.006739897741383979
1190
- ≥5,20000,ai2d_exact_match,0.4844559585492228,0.008994804366753555
1191
- ≥5,20000,average,0.49543136618963995,
1192
- ≥5,20000,average_rank,2.9,
1193
- ≥5,20000,chartqa_relaxed_overall,0.638,0.009613499245701268
1194
- ≥5,20000,docvqa_val_anls,0.688451623661496,0.005905200575549553
1195
- ≥5,20000,infovqa_val_anls,0.2789607789162199,0.007289443671361681
1196
- ≥5,20000,mme_total_score,1296.043617446979,
1197
- ≥5,20000,mmmu_val_mmmu_acc,0.3,
1198
- ≥5,20000,mmstar_average,0.3804272197382418,
1199
- ≥5,20000,ocrbench_ocrbench_accuracy,0.577,
1200
- ≥5,20000,seedbench_seed_all,0.5560867148415787,
1201
- ≥5,20000,textvqa_val_exact_match,0.5555,0.006734970078953051
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69acb8bc0b80b2c664d821b1c06d67af315e67d8a706cf9e5d351e4468392cc6
3
+ size 63236
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/content/assets/data/remove_ch.csv CHANGED
@@ -1,455 +1,3 @@
1
- run,step,metric,value,stderr
2
- Baseline,1000,ai2d_exact_match,0.2548575129533679,0.007843322436924496
3
- Baseline,1000,average,0.27120689295763617,
4
- Baseline,1000,average_rank,1.7,
5
- Baseline,1000,chartqa_relaxed_overall,0.3308,0.009411906161401973
6
- Baseline,1000,docvqa_val_anls,0.3528553494243383,0.005852289239342309
7
- Baseline,1000,infovqa_val_anls,0.17320578642581314,0.006297063452679795
8
- Baseline,1000,mme_total_score,977.4280712284914,
9
- Baseline,1000,mmmu_val_mmmu_acc,0.25222,
10
- Baseline,1000,mmstar_average,0.23215874078908072,
11
- Baseline,1000,ocrbench_ocrbench_accuracy,0.286,
12
- Baseline,1000,seedbench_seed_all,0.2563646470261256,
13
- Baseline,1000,textvqa_val_exact_match,0.3024,0.00628900296642181
14
- Baseline,2000,ai2d_exact_match,0.26295336787564766,0.007923526907377255
15
- Baseline,2000,average,0.3202068275596269,
16
- Baseline,2000,average_rank,1.5,
17
- Baseline,2000,chartqa_relaxed_overall,0.4688,0.009982508912777261
18
- Baseline,2000,docvqa_val_anls,0.4452261510942785,0.00614755494712251
19
- Baseline,2000,infovqa_val_anls,0.1820547866557169,0.006217861455795791
20
- Baseline,2000,mme_total_score,1049.3036214485794,
21
- Baseline,2000,mmmu_val_mmmu_acc,0.24556,
22
- Baseline,2000,mmstar_average,0.21305462434540698,
23
- Baseline,2000,ocrbench_ocrbench_accuracy,0.395,
24
- Baseline,2000,seedbench_seed_all,0.258532518065592,
25
- Baseline,2000,textvqa_val_exact_match,0.41068000000000005,0.006697862330024289
26
- Baseline,3000,ai2d_exact_match,0.25226683937823835,0.007816909588794397
27
- Baseline,3000,average,0.3507423834414229,
28
- Baseline,3000,average_rank,1.6,
29
- Baseline,3000,chartqa_relaxed_overall,0.5028,0.010001843767601082
30
- Baseline,3000,docvqa_val_anls,0.502653993831009,0.006267072346683124
31
- Baseline,3000,infovqa_val_anls,0.21728617578189535,0.006796941784959762
32
- Baseline,3000,mme_total_score,1170.2383953581434,
33
- Baseline,3000,mmmu_val_mmmu_acc,0.27556,
34
- Baseline,3000,mmstar_average,0.25432376938577683,
35
- Baseline,3000,ocrbench_ocrbench_accuracy,0.436,
36
- Baseline,3000,seedbench_seed_all,0.2792106725958866,
37
- Baseline,3000,textvqa_val_exact_match,0.43658,0.006766885462882726
38
- Baseline,4000,ai2d_exact_match,0.2645725388601036,0.007939149662089447
39
- Baseline,4000,average,0.36961781722974835,
40
- Baseline,4000,average_rank,1.6,
41
- Baseline,4000,chartqa_relaxed_overall,0.5312,0.009982508912777261
42
- Baseline,4000,docvqa_val_anls,0.5374434618615119,0.0062905728113059655
43
- Baseline,4000,infovqa_val_anls,0.2287924838861707,0.006994568698639919
44
- Baseline,4000,mme_total_score,1155.203781512605,
45
- Baseline,4000,mmmu_val_mmmu_acc,0.25556,
46
- Baseline,4000,mmstar_average,0.2575590188757354,
47
- Baseline,4000,ocrbench_ocrbench_accuracy,0.453,
48
- Baseline,4000,seedbench_seed_all,0.33913285158421347,
49
- Baseline,4000,textvqa_val_exact_match,0.4593,0.006791695475025738
50
- Baseline,5000,ai2d_exact_match,0.3125,0.008342439145556371
51
- Baseline,5000,average,0.3974627910380972,
52
- Baseline,5000,average_rank,1.6,
53
- Baseline,5000,chartqa_relaxed_overall,0.5488,0.00995424828018316
54
- Baseline,5000,docvqa_val_anls,0.552360266782429,0.006300308519952055
55
- Baseline,5000,infovqa_val_anls,0.23425555286643698,0.007002254622066442
56
- Baseline,5000,mme_total_score,1181.4653861544618,
57
- Baseline,5000,mmmu_val_mmmu_acc,0.26667,
58
- Baseline,5000,mmstar_average,0.29596648146165705,
59
- Baseline,5000,ocrbench_ocrbench_accuracy,0.462,
60
- Baseline,5000,seedbench_seed_all,0.43107281823235133,
61
- Baseline,5000,textvqa_val_exact_match,0.47354000000000007,0.0068172185364497985
62
- Baseline,6000,ai2d_exact_match,0.358160621761658,0.008629463221867162
63
- Baseline,6000,average,0.4161227404571003,
64
- Baseline,6000,average_rank,1.7,
65
- Baseline,6000,chartqa_relaxed_overall,0.5628,0.00992279440175477
66
- Baseline,6000,docvqa_val_anls,0.5747451497228876,0.00625495440870239
67
- Baseline,6000,infovqa_val_anls,0.22152017368968838,0.006604546680525351
68
- Baseline,6000,mme_total_score,1284.1648659463785,
69
- Baseline,6000,mmmu_val_mmmu_acc,0.27111,
70
- Baseline,6000,mmstar_average,0.2978489412854164,
71
- Baseline,6000,ocrbench_ocrbench_accuracy,0.495,
72
- Baseline,6000,seedbench_seed_all,0.4795997776542524,
73
- Baseline,6000,textvqa_val_exact_match,0.48432,0.006800535050670284
74
- Baseline,7000,ai2d_exact_match,0.3707901554404145,0.00869347755587734
75
- Baseline,7000,average,0.4291083177345374,
76
- Baseline,7000,average_rank,1.6,
77
- Baseline,7000,chartqa_relaxed_overall,0.5656,0.009915542506251351
78
- Baseline,7000,docvqa_val_anls,0.5940907049431567,0.006224236305767187
79
- Baseline,7000,infovqa_val_anls,0.2515675215816963,0.007105097396092786
80
- Baseline,7000,mme_total_score,1185.875650260104,
81
- Baseline,7000,mmmu_val_mmmu_acc,0.26556,
82
- Baseline,7000,mmstar_average,0.31372400960777047,
83
- Baseline,7000,ocrbench_ocrbench_accuracy,0.504,
84
- Baseline,7000,seedbench_seed_all,0.4964424680377988,
85
- Baseline,7000,textvqa_val_exact_match,0.5002,0.006794794025220267
86
- Baseline,8000,ai2d_exact_match,0.37759067357512954,0.008725299846043883
87
- Baseline,8000,average,0.43846759477995995,
88
- Baseline,8000,average_rank,1.8,
89
- Baseline,8000,chartqa_relaxed_overall,0.5832,0.009862556058385773
90
- Baseline,8000,docvqa_val_anls,0.6017336419437208,0.006231612198089698
91
- Baseline,8000,infovqa_val_anls,0.2449256624147254,0.006992518502948913
92
- Baseline,8000,mme_total_score,1199.2409963985594,
93
- Baseline,8000,mmmu_val_mmmu_acc,0.28111,
94
- Baseline,8000,mmstar_average,0.33512257186205047,
95
- Baseline,8000,ocrbench_ocrbench_accuracy,0.51,
96
- Baseline,8000,seedbench_seed_all,0.5024458032240133,
97
- Baseline,8000,textvqa_val_exact_match,0.51008,0.006796301690135059
98
- Baseline,9000,ai2d_exact_match,0.4067357512953368,0.008841214921078996
99
- Baseline,9000,average,0.4422510732201056,
100
- Baseline,9000,average_rank,1.8,
101
- Baseline,9000,chartqa_relaxed_overall,0.5912,0.009834211136815875
102
- Baseline,9000,docvqa_val_anls,0.6170968481662739,0.00617235763542544
103
- Baseline,9000,infovqa_val_anls,0.23537031288570615,0.00670318154156447
104
- Baseline,9000,mme_total_score,1231.5195078031213,
105
- Baseline,9000,mmmu_val_mmmu_acc,0.25889,
106
- Baseline,9000,mmstar_average,0.3216444898242951,
107
- Baseline,9000,ocrbench_ocrbench_accuracy,0.515,
108
- Baseline,9000,seedbench_seed_all,0.5120622568093385,
109
- Baseline,9000,textvqa_val_exact_match,0.52226,0.006792711289708482
110
- Baseline,10000,ai2d_exact_match,0.39993523316062174,0.008817096257082848
111
- Baseline,10000,average,0.4523875703250908,
112
- Baseline,10000,average_rank,1.7,
113
- Baseline,10000,chartqa_relaxed_overall,0.5996,0.00980154906867574
114
- Baseline,10000,docvqa_val_anls,0.6262613496433054,0.006147756371688175
115
- Baseline,10000,infovqa_val_anls,0.263290074230132,0.007186788766942786
116
- Baseline,10000,mme_total_score,1240.8218287314926,
117
- Baseline,10000,mmmu_val_mmmu_acc,0.28778,
118
- Baseline,10000,mmstar_average,0.32972717906018517,
119
- Baseline,10000,ocrbench_ocrbench_accuracy,0.517,
120
- Baseline,10000,seedbench_seed_all,0.5217342968315731,
121
- Baseline,10000,textvqa_val_exact_match,0.5261600000000001,0.006785774843600811
122
- Baseline,11000,ai2d_exact_match,0.422279792746114,0.008889771831066474
123
- Baseline,11000,average,0.4561398159525099,
124
- Baseline,11000,average_rank,1.7,
125
- Baseline,11000,chartqa_relaxed_overall,0.6104,0.009755142291143075
126
- Baseline,11000,docvqa_val_anls,0.6373130149166712,0.006128022584995044
127
- Baseline,11000,infovqa_val_anls,0.24419378339723755,0.006897644885887063
128
- Baseline,11000,mme_total_score,1322.9488795518205,
129
- Baseline,11000,mmmu_val_mmmu_acc,0.27778,
130
- Baseline,11000,mmstar_average,0.3298563439522548,
131
- Baseline,11000,ocrbench_ocrbench_accuracy,0.521,
132
- Baseline,11000,seedbench_seed_all,0.5237354085603113,
133
- Baseline,11000,textvqa_val_exact_match,0.5387,0.006770851562852138
134
- Baseline,12000,ai2d_exact_match,0.42001295336787564,0.008883255931688034
135
- Baseline,12000,average,0.4582751140055433,
136
- Baseline,12000,average_rank,1.7,
137
- Baseline,12000,chartqa_relaxed_overall,0.618,0.009719474639861454
138
- Baseline,12000,docvqa_val_anls,0.6393961983751871,0.0061228747388476674
139
- Baseline,12000,infovqa_val_anls,0.24798874058574302,0.006855374548993139
140
- Baseline,12000,mme_total_score,1225.6453581432572,
141
- Baseline,12000,mmmu_val_mmmu_acc,0.27889,
142
- Baseline,12000,mmstar_average,0.34010867846816534,
143
- Baseline,12000,ocrbench_ocrbench_accuracy,0.512,
144
- Baseline,12000,seedbench_seed_all,0.5350194552529183,
145
- Baseline,12000,textvqa_val_exact_match,0.5330600000000001,0.006777713092109446
146
- Baseline,13000,ai2d_exact_match,0.4375,0.008928571428571428
147
- Baseline,13000,average,0.4692868662590049,
148
- Baseline,13000,average_rank,1.4,
149
- Baseline,13000,chartqa_relaxed_overall,0.6148,0.00973479791861169
150
- Baseline,13000,docvqa_val_anls,0.6511374872549951,0.006086953065248391
151
- Baseline,13000,infovqa_val_anls,0.24465055100441893,0.006808432538374664
152
- Baseline,13000,mme_total_score,1281.7122849139657,
153
- Baseline,13000,mmmu_val_mmmu_acc,0.28222,
154
- Baseline,13000,mmstar_average,0.3453069542917521,
155
- Baseline,13000,ocrbench_ocrbench_accuracy,0.549,
156
- Baseline,13000,seedbench_seed_all,0.5442468037798777,
157
- Baseline,13000,textvqa_val_exact_match,0.55472,0.0067416788982325
158
- Baseline,14000,ai2d_exact_match,0.4572538860103627,0.00896620675297095
159
- Baseline,14000,average,0.47352486841689195,
160
- Baseline,14000,average_rank,1.3,
161
- Baseline,14000,chartqa_relaxed_overall,0.6172,0.009723347231923635
162
- Baseline,14000,docvqa_val_anls,0.6502269393708169,0.006057950730638126
163
- Baseline,14000,infovqa_val_anls,0.25805460837190913,0.007037735231659539
164
- Baseline,14000,mme_total_score,1309.1444577831132,
165
- Baseline,14000,mmmu_val_mmmu_acc,0.28111,
166
- Baseline,14000,mmstar_average,0.34575818188776586,
167
- Baseline,14000,ocrbench_ocrbench_accuracy,0.551,
168
- Baseline,14000,seedbench_seed_all,0.5483602001111729,
169
- Baseline,14000,textvqa_val_exact_match,0.55276,0.006751206724612103
170
- Baseline,15000,ai2d_exact_match,0.45045336787564766,0.008954861634252399
171
- Baseline,15000,average,0.47878665012878824,
172
- Baseline,15000,average_rank,1.2,
173
- Baseline,15000,chartqa_relaxed_overall,0.612,0.009747841205275417
174
- Baseline,15000,docvqa_val_anls,0.6621413031955148,0.006056838050222495
175
- Baseline,15000,infovqa_val_anls,0.2706898598157733,0.007200315730154543
176
- Baseline,15000,mme_total_score,1384.2171868747498,
177
- Baseline,15000,mmmu_val_mmmu_acc,0.30222,
178
- Baseline,15000,mmstar_average,0.35408135695920684,
179
- Baseline,15000,ocrbench_ocrbench_accuracy,0.558,
180
- Baseline,15000,seedbench_seed_all,0.5411339633129516,
181
- Baseline,15000,textvqa_val_exact_match,0.5583600000000001,0.0067279027203879065
182
- Baseline,16000,ai2d_exact_match,0.45077720207253885,0.008955440137395838
183
- Baseline,16000,average,0.47665128022935843,
184
- Baseline,16000,average_rank,1.5,
185
- Baseline,16000,chartqa_relaxed_overall,0.632,0.00964715642305132
186
- Baseline,16000,docvqa_val_anls,0.6709415729142987,0.005999818105621502
187
- Baseline,16000,infovqa_val_anls,0.26050032542402035,0.006997451875879188
188
- Baseline,16000,mme_total_score,1317.8491396558625,
189
- Baseline,16000,mmmu_val_mmmu_acc,0.27556,
190
- Baseline,16000,mmstar_average,0.33214333327093315,
191
- Baseline,16000,ocrbench_ocrbench_accuracy,0.56,
192
- Baseline,16000,seedbench_seed_all,0.5463590883824346,
193
- Baseline,16000,textvqa_val_exact_match,0.56158,0.006723854754867398
194
- Baseline,17000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
195
- Baseline,17000,average,0.4777141780162423,
196
- Baseline,17000,average_rank,1.2,
197
- Baseline,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
198
- Baseline,17000,docvqa_val_anls,0.6796338519136422,0.005948761388267941
199
- Baseline,17000,infovqa_val_anls,0.28070956072505215,0.007298333094144192
200
- Baseline,17000,mme_total_score,1381.9161664665867,
201
- Baseline,17000,mmmu_val_mmmu_acc,0.27667,
202
- Baseline,17000,mmstar_average,0.3370289492329521,
203
- Baseline,17000,ocrbench_ocrbench_accuracy,0.519,
204
- Baseline,17000,seedbench_seed_all,0.5510283490828238,
205
- Baseline,17000,textvqa_val_exact_match,0.56416,0.006724830373229479
206
- Baseline,18000,ai2d_exact_match,0.46567357512953367,0.008977921602780726
207
- Baseline,18000,average,0.4819834595278701,
208
- Baseline,18000,average_rank,1.1,
209
- Baseline,18000,chartqa_relaxed_overall,0.6376,0.009615793331418735
210
- Baseline,18000,docvqa_val_anls,0.6775884603912571,0.005972234236435759
211
- Baseline,18000,infovqa_val_anls,0.27154318420389256,0.007164903131667027
212
- Baseline,18000,mme_total_score,1336.922769107643,
213
- Baseline,18000,mmmu_val_mmmu_acc,0.28667,
214
- Baseline,18000,mmstar_average,0.34482796716566916,
215
- Baseline,18000,ocrbench_ocrbench_accuracy,0.533,
216
- Baseline,18000,seedbench_seed_all,0.5543079488604781,
217
- Baseline,18000,textvqa_val_exact_match,0.5666399999999999,0.006713392287599574
218
- Baseline,19000,ai2d_exact_match,0.4682642487046632,0.008981008686994101
219
- Baseline,19000,average,0.4899006713916878,
220
- Baseline,19000,chartqa_relaxed_overall,0.6444,0.009575809858898698
221
- Baseline,19000,docvqa_val_anls,0.678226526479947,0.005970619221588814
222
- Baseline,19000,infovqa_val_anls,0.26993847247278,0.0071348470764911525
223
- Baseline,19000,mme_total_score,1406.6628651460583,
224
- Baseline,19000,mmmu_val_mmmu_acc,0.28333,
225
- Baseline,19000,mmstar_average,0.356220913822775,
226
- Baseline,19000,ocrbench_ocrbench_accuracy,0.577,
227
- Baseline,19000,seedbench_seed_all,0.554585881045025,
228
- Baseline,19000,textvqa_val_exact_match,0.57714,0.0066918487914812905
229
- Baseline,20000,ai2d_exact_match,0.47571243523316065,0.00898853090258662
230
- Baseline,20000,average,0.4873169067639118,
231
- Baseline,20000,chartqa_relaxed_overall,0.6336,0.009638338810708618
232
- Baseline,20000,docvqa_val_anls,0.6895214454380043,0.005896462073053767
233
- Baseline,20000,infovqa_val_anls,0.2655657550458317,0.007033265532032538
234
- Baseline,20000,mme_total_score,1324.6738695478193,
235
- Baseline,20000,mmmu_val_mmmu_acc,0.30111,
236
- Baseline,20000,mmstar_average,0.33806766134497995,
237
- Baseline,20000,ocrbench_ocrbench_accuracy,0.555,
238
- Baseline,20000,seedbench_seed_all,0.5587548638132296,
239
- Baseline,20000,textvqa_val_exact_match,0.56852,0.006720151338087659
240
- Remove Multilingual Data,1000,ai2d_exact_match,0.2619818652849741,0.007914086941902855
241
- Remove Multilingual Data,1000,average,0.29340443385847137,
242
- Remove Multilingual Data,1000,average_rank,1.3,
243
- Remove Multilingual Data,1000,chartqa_relaxed_overall,0.3736,0.009677121197436144
244
- Remove Multilingual Data,1000,docvqa_val_anls,0.403140100303888,0.006111323163666132
245
- Remove Multilingual Data,1000,infovqa_val_anls,0.1764617576183696,0.006251319736392345
246
- Remove Multilingual Data,1000,mme_total_score,979.3045218087235,
247
- Remove Multilingual Data,1000,mmmu_val_mmmu_acc,0.25222,
248
- Remove Multilingual Data,1000,mmstar_average,0.2073057646207335,
249
- Remove Multilingual Data,1000,ocrbench_ocrbench_accuracy,0.333,
250
- Remove Multilingual Data,1000,seedbench_seed_all,0.2507504168982768,
251
- Remove Multilingual Data,1000,textvqa_val_exact_match,0.38218,0.006631325992355026
252
- Remove Multilingual Data,2000,ai2d_exact_match,0.25291450777202074,0.007823547213659585
253
- Remove Multilingual Data,2000,average,0.32254499165624334,
254
- Remove Multilingual Data,2000,average_rank,1.5,
255
- Remove Multilingual Data,2000,chartqa_relaxed_overall,0.4692,0.009983005968307607
256
- Remove Multilingual Data,2000,docvqa_val_anls,0.472590835723597,0.006255090657185791
257
- Remove Multilingual Data,2000,infovqa_val_anls,0.19402428600531574,0.006415305613638088
258
- Remove Multilingual Data,2000,mme_total_score,1067.5286114445778,
259
- Remove Multilingual Data,2000,mmmu_val_mmmu_acc,0.24444,
260
- Remove Multilingual Data,2000,mmstar_average,0.20544885849586278,
261
- Remove Multilingual Data,2000,ocrbench_ocrbench_accuracy,0.409,
262
- Remove Multilingual Data,2000,seedbench_seed_all,0.2555864369093941,
263
- Remove Multilingual Data,2000,textvqa_val_exact_match,0.3997,0.006677042652231296
264
- Remove Multilingual Data,3000,ai2d_exact_match,0.2658678756476684,0.00795154886571598
265
- Remove Multilingual Data,3000,average,0.35383248024337044,
266
- Remove Multilingual Data,3000,average_rank,1.4,
267
- Remove Multilingual Data,3000,chartqa_relaxed_overall,0.536,0.009976041728231964
268
- Remove Multilingual Data,3000,docvqa_val_anls,0.5115050780592246,0.006297134520533815
269
- Remove Multilingual Data,3000,infovqa_val_anls,0.1959317380528948,0.006353999153527862
270
- Remove Multilingual Data,3000,mme_total_score,1055.7074829931971,
271
- Remove Multilingual Data,3000,mmmu_val_mmmu_acc,0.26,
272
- Remove Multilingual Data,3000,mmstar_average,0.2325690534433309,
273
- Remove Multilingual Data,3000,ocrbench_ocrbench_accuracy,0.449,
274
- Remove Multilingual Data,3000,seedbench_seed_all,0.28943857698721515,
275
- Remove Multilingual Data,3000,textvqa_val_exact_match,0.44418,0.0067730052591185854
276
- Remove Multilingual Data,4000,ai2d_exact_match,0.2856217616580311,0.008130016747303466
277
- Remove Multilingual Data,4000,average,0.3775873253769421,
278
- Remove Multilingual Data,4000,average_rank,1.4,
279
- Remove Multilingual Data,4000,chartqa_relaxed_overall,0.55,0.009951864943131942
280
- Remove Multilingual Data,4000,docvqa_val_anls,0.5339851175847934,0.0062957385772197255
281
- Remove Multilingual Data,4000,infovqa_val_anls,0.20750676546327357,0.006369425500899887
282
- Remove Multilingual Data,4000,mme_total_score,1228.202280912365,
283
- Remove Multilingual Data,4000,mmmu_val_mmmu_acc,0.27111,
284
- Remove Multilingual Data,4000,mmstar_average,0.24655460164079995,
285
- Remove Multilingual Data,4000,ocrbench_ocrbench_accuracy,0.456,
286
- Remove Multilingual Data,4000,seedbench_seed_all,0.3898276820455809,
287
- Remove Multilingual Data,4000,textvqa_val_exact_match,0.45768000000000003,0.006781666588703993
288
- Remove Multilingual Data,5000,ai2d_exact_match,0.3121761658031088,0.008340079044408505
289
- Remove Multilingual Data,5000,average,0.3976192139479395,
290
- Remove Multilingual Data,5000,average_rank,1.4,
291
- Remove Multilingual Data,5000,chartqa_relaxed_overall,0.5684,0.009907968668564455
292
- Remove Multilingual Data,5000,docvqa_val_anls,0.5611339219828478,0.006260862186673622
293
- Remove Multilingual Data,5000,infovqa_val_anls,0.21913407408993218,0.006638320670102091
294
- Remove Multilingual Data,5000,mme_total_score,1219.2377951180472,
295
- Remove Multilingual Data,5000,mmmu_val_mmmu_acc,0.29444,
296
- Remove Multilingual Data,5000,mmstar_average,0.23556637343877926,
297
- Remove Multilingual Data,5000,ocrbench_ocrbench_accuracy,0.472,
298
- Remove Multilingual Data,5000,seedbench_seed_all,0.4443023902167871,
299
- Remove Multilingual Data,5000,textvqa_val_exact_match,0.47142,0.006807048104779351
300
- Remove Multilingual Data,6000,ai2d_exact_match,0.35200777202072536,0.008595926828224822
301
- Remove Multilingual Data,6000,average,0.42451996443270734,
302
- Remove Multilingual Data,6000,average_rank,1.3,
303
- Remove Multilingual Data,6000,chartqa_relaxed_overall,0.5744,0.009890651444389179
304
- Remove Multilingual Data,6000,docvqa_val_anls,0.5825552977560686,0.006257174245982806
305
- Remove Multilingual Data,6000,infovqa_val_anls,0.252828230577843,0.007149939162213116
306
- Remove Multilingual Data,6000,mme_total_score,1216.607643057223,
307
- Remove Multilingual Data,6000,mmmu_val_mmmu_acc,0.30222,
308
- Remove Multilingual Data,6000,mmstar_average,0.2807390632529032,
309
- Remove Multilingual Data,6000,ocrbench_ocrbench_accuracy,0.497,
310
- Remove Multilingual Data,6000,seedbench_seed_all,0.484769316286826,
311
- Remove Multilingual Data,6000,textvqa_val_exact_match,0.49416000000000004,0.006798707477504303
312
- Remove Multilingual Data,7000,ai2d_exact_match,0.3801813471502591,0.008736941116932581
313
- Remove Multilingual Data,7000,average,0.428085510128325,
314
- Remove Multilingual Data,7000,average_rank,1.4,
315
- Remove Multilingual Data,7000,chartqa_relaxed_overall,0.5796,0.009874438607593145
316
- Remove Multilingual Data,7000,docvqa_val_anls,0.5966369586509165,0.006224801729990067
317
- Remove Multilingual Data,7000,infovqa_val_anls,0.23354910759447625,0.006817906701297544
318
- Remove Multilingual Data,7000,mme_total_score,1188.1020408163265,
319
- Remove Multilingual Data,7000,mmmu_val_mmmu_acc,0.27556,
320
- Remove Multilingual Data,7000,mmstar_average,0.292518909276783,
321
- Remove Multilingual Data,7000,ocrbench_ocrbench_accuracy,0.503,
322
- Remove Multilingual Data,7000,seedbench_seed_all,0.48988326848249025,
323
- Remove Multilingual Data,7000,textvqa_val_exact_match,0.5018400000000001,0.006795274684043781
324
- Remove Multilingual Data,8000,ai2d_exact_match,0.3863341968911917,0.008763532923326706
325
- Remove Multilingual Data,8000,average,0.4413787447198958,
326
- Remove Multilingual Data,8000,average_rank,1.2,
327
- Remove Multilingual Data,8000,chartqa_relaxed_overall,0.5964,0.009814343815957088
328
- Remove Multilingual Data,8000,docvqa_val_anls,0.603351366738696,0.006235087701254087
329
- Remove Multilingual Data,8000,infovqa_val_anls,0.25307646024963104,0.007198626238671866
330
- Remove Multilingual Data,8000,mme_total_score,1261.5517206882753,
331
- Remove Multilingual Data,8000,mmmu_val_mmmu_acc,0.29556,
332
- Remove Multilingual Data,8000,mmstar_average,0.30595531673183934,
333
- Remove Multilingual Data,8000,ocrbench_ocrbench_accuracy,0.505,
334
- Remove Multilingual Data,8000,seedbench_seed_all,0.5124513618677042,
335
- Remove Multilingual Data,8000,textvqa_val_exact_match,0.51428,0.006792322389925977
336
- Remove Multilingual Data,9000,ai2d_exact_match,0.3908678756476684,0.008782181865213609
337
- Remove Multilingual Data,9000,average,0.4483393474436153,
338
- Remove Multilingual Data,9000,average_rank,1.2,
339
- Remove Multilingual Data,9000,chartqa_relaxed_overall,0.6008,0.00979663889573671
340
- Remove Multilingual Data,9000,docvqa_val_anls,0.6206417157518567,0.006160046717594884
341
- Remove Multilingual Data,9000,infovqa_val_anls,0.2517144366407357,0.007092352700671051
342
- Remove Multilingual Data,9000,mme_total_score,1270.4974989995999,
343
- Remove Multilingual Data,9000,mmmu_val_mmmu_acc,0.29333,
344
- Remove Multilingual Data,9000,mmstar_average,0.32657768650091523,
345
- Remove Multilingual Data,9000,ocrbench_ocrbench_accuracy,0.52,
346
- Remove Multilingual Data,9000,seedbench_seed_all,0.5163424124513619,
347
- Remove Multilingual Data,9000,textvqa_val_exact_match,0.51478,0.006772730933446224
348
- Remove Multilingual Data,10000,ai2d_exact_match,0.41450777202072536,0.008866630113019596
349
- Remove Multilingual Data,10000,average,0.45448389614950035,
350
- Remove Multilingual Data,10000,average_rank,1.3,
351
- Remove Multilingual Data,10000,chartqa_relaxed_overall,0.6068,0.009771166474772143
352
- Remove Multilingual Data,10000,docvqa_val_anls,0.6232449599819007,0.006177718712473361
353
- Remove Multilingual Data,10000,infovqa_val_anls,0.23737546748097776,0.006778926597473845
354
- Remove Multilingual Data,10000,mme_total_score,1276.3549419767905,
355
- Remove Multilingual Data,10000,mmmu_val_mmmu_acc,0.29889,
356
- Remove Multilingual Data,10000,mmstar_average,0.3130758097195978,
357
- Remove Multilingual Data,10000,ocrbench_ocrbench_accuracy,0.539,
358
- Remove Multilingual Data,10000,seedbench_seed_all,0.5219010561423013,
359
- Remove Multilingual Data,10000,textvqa_val_exact_match,0.53556,0.00676001751827386
360
- Remove Multilingual Data,11000,ai2d_exact_match,0.41904145077720206,0.008880404559123601
361
- Remove Multilingual Data,11000,average,0.4609227111862355,
362
- Remove Multilingual Data,11000,average_rank,1.3,
363
- Remove Multilingual Data,11000,chartqa_relaxed_overall,0.6108,0.00975332737879659
364
- Remove Multilingual Data,11000,docvqa_val_anls,0.6387481065492241,0.006094036395159673
365
- Remove Multilingual Data,11000,infovqa_val_anls,0.25052436731474453,0.006993658213921465
366
- Remove Multilingual Data,11000,mme_total_score,1258.2553021208482,
367
- Remove Multilingual Data,11000,mmmu_val_mmmu_acc,0.28,
368
- Remove Multilingual Data,11000,mmstar_average,0.3213557456291676,
369
- Remove Multilingual Data,11000,ocrbench_ocrbench_accuracy,0.561,
370
- Remove Multilingual Data,11000,seedbench_seed_all,0.526514730405781,
371
- Remove Multilingual Data,11000,textvqa_val_exact_match,0.54032,0.0067608876222200335
372
- Remove Multilingual Data,12000,ai2d_exact_match,0.41353626943005184,0.00886357792887845
373
- Remove Multilingual Data,12000,average,0.46149948562642984,
374
- Remove Multilingual Data,12000,average_rank,1.3,
375
- Remove Multilingual Data,12000,chartqa_relaxed_overall,0.622,0.009699692449425671
376
- Remove Multilingual Data,12000,docvqa_val_anls,0.6481870346272672,0.0060803752132680255
377
- Remove Multilingual Data,12000,infovqa_val_anls,0.25116762340113796,0.006993814336062128
378
- Remove Multilingual Data,12000,mme_total_score,1256.7357943177271,
379
- Remove Multilingual Data,12000,mmmu_val_mmmu_acc,0.28222,
380
- Remove Multilingual Data,12000,mmstar_average,0.311104865636332,
381
- Remove Multilingual Data,12000,ocrbench_ocrbench_accuracy,0.547,
382
- Remove Multilingual Data,12000,seedbench_seed_all,0.5312395775430795,
383
- Remove Multilingual Data,12000,textvqa_val_exact_match,0.54704,0.006750774938661079
384
- Remove Multilingual Data,13000,ai2d_exact_match,0.42810880829015546,0.008905646879422012
385
- Remove Multilingual Data,13000,average,0.4658949593838579,
386
- Remove Multilingual Data,13000,average_rank,1.6,
387
- Remove Multilingual Data,13000,chartqa_relaxed_overall,0.622,0.009699692449425671
388
- Remove Multilingual Data,13000,docvqa_val_anls,0.6461697403304425,0.006072036108570188
389
- Remove Multilingual Data,13000,infovqa_val_anls,0.2635164421127001,0.007102540516236264
390
- Remove Multilingual Data,13000,mme_total_score,1295.0039015606244,
391
- Remove Multilingual Data,13000,mmmu_val_mmmu_acc,0.29,
392
- Remove Multilingual Data,13000,mmstar_average,0.3296444797414335,
393
- Remove Multilingual Data,13000,ocrbench_ocrbench_accuracy,0.54,
394
- Remove Multilingual Data,13000,seedbench_seed_all,0.5312951639799889,
395
- Remove Multilingual Data,13000,textvqa_val_exact_match,0.54232,0.006771571040376891
396
- Remove Multilingual Data,14000,ai2d_exact_match,0.42487046632124353,0.008896983637113786
397
- Remove Multilingual Data,14000,average,0.46755416993970794,
398
- Remove Multilingual Data,14000,average_rank,1.7,
399
- Remove Multilingual Data,14000,chartqa_relaxed_overall,0.6256,0.009681288495793083
400
- Remove Multilingual Data,14000,docvqa_val_anls,0.6470833619171145,0.006119244473927763
401
- Remove Multilingual Data,14000,infovqa_val_anls,0.2541720455309047,0.007006172199083197
402
- Remove Multilingual Data,14000,mme_total_score,1262.1793717486994,
403
- Remove Multilingual Data,14000,mmmu_val_mmmu_acc,0.28556,
404
- Remove Multilingual Data,14000,mmstar_average,0.327544946405174,
405
- Remove Multilingual Data,14000,ocrbench_ocrbench_accuracy,0.559,
406
- Remove Multilingual Data,14000,seedbench_seed_all,0.5380767092829349,
407
- Remove Multilingual Data,14000,textvqa_val_exact_match,0.5460799999999999,0.006754587449305995
408
- Remove Multilingual Data,15000,ai2d_exact_match,0.42908031088082904,0.00890816984689523
409
- Remove Multilingual Data,15000,average,0.4720258172705174,
410
- Remove Multilingual Data,15000,average_rank,1.8,
411
- Remove Multilingual Data,15000,chartqa_relaxed_overall,0.626,0.009679208378267924
412
- Remove Multilingual Data,15000,docvqa_val_anls,0.655881547989144,0.006058079036611966
413
- Remove Multilingual Data,15000,infovqa_val_anls,0.2538472956751567,0.006929926842577286
414
- Remove Multilingual Data,15000,mme_total_score,1283.2800120048018,
415
- Remove Multilingual Data,15000,mmmu_val_mmmu_acc,0.29,
416
- Remove Multilingual Data,15000,mmstar_average,0.3309383426349411,
417
- Remove Multilingual Data,15000,ocrbench_ocrbench_accuracy,0.572,
418
- Remove Multilingual Data,15000,seedbench_seed_all,0.5407448582545858,
419
- Remove Multilingual Data,15000,textvqa_val_exact_match,0.54974,0.006738090742441116
420
- Remove Multilingual Data,16000,ai2d_exact_match,0.42940414507772023,0.008909003051055714
421
- Remove Multilingual Data,16000,average,0.476926180401357,
422
- Remove Multilingual Data,16000,average_rank,1.5,
423
- Remove Multilingual Data,16000,chartqa_relaxed_overall,0.626,0.009679208378267924
424
- Remove Multilingual Data,16000,docvqa_val_anls,0.6622394005833824,0.006046858134280091
425
- Remove Multilingual Data,16000,infovqa_val_anls,0.2633356312454137,0.007137388413784386
426
- Remove Multilingual Data,16000,mme_total_score,1328.4599839935972,
427
- Remove Multilingual Data,16000,mmmu_val_mmmu_acc,0.29556,
428
- Remove Multilingual Data,16000,mmstar_average,0.33932578522709744,
429
- Remove Multilingual Data,16000,ocrbench_ocrbench_accuracy,0.578,
430
- Remove Multilingual Data,16000,seedbench_seed_all,0.5431906614785992,
431
- Remove Multilingual Data,16000,textvqa_val_exact_match,0.55528,0.006733817132847886
432
- Remove Multilingual Data,17000,ai2d_exact_match,0.42940414507772023,0.008909003051055712
433
- Remove Multilingual Data,17000,average,0.4732087844936434,
434
- Remove Multilingual Data,17000,average_rank,1.8,
435
- Remove Multilingual Data,17000,chartqa_relaxed_overall,0.6264,0.009677121197436144
436
- Remove Multilingual Data,17000,docvqa_val_anls,0.661817176575324,0.0060368801840957114
437
- Remove Multilingual Data,17000,infovqa_val_anls,0.25584519300448166,0.007033162778192734
438
- Remove Multilingual Data,17000,mme_total_score,1270.766606642657,
439
- Remove Multilingual Data,17000,mmmu_val_mmmu_acc,0.28,
440
- Remove Multilingual Data,17000,mmstar_average,0.3233592606268431,
441
- Remove Multilingual Data,17000,ocrbench_ocrbench_accuracy,0.58,
442
- Remove Multilingual Data,17000,seedbench_seed_all,0.5439132851584213,
443
- Remove Multilingual Data,17000,textvqa_val_exact_match,0.5581400000000001,0.006731048171116916
444
- Remove Multilingual Data,18000,ai2d_exact_match,0.4368523316062176,0.008927095061184944
445
- Remove Multilingual Data,18000,average,0.4769341122300441,
446
- Remove Multilingual Data,18000,average_rank,1.9,
447
- Remove Multilingual Data,18000,chartqa_relaxed_overall,0.636,0.009624897685803465
448
- Remove Multilingual Data,18000,docvqa_val_anls,0.671397164123935,0.006004837667492473
449
- Remove Multilingual Data,18000,infovqa_val_anls,0.2570865428675732,0.007022334730795061
450
- Remove Multilingual Data,18000,mme_total_score,1330.2323929571828,
451
- Remove Multilingual Data,18000,mmmu_val_mmmu_acc,0.28444,
452
- Remove Multilingual Data,18000,mmstar_average,0.3272633338962395,
453
- Remove Multilingual Data,18000,ocrbench_ocrbench_accuracy,0.579,
454
- Remove Multilingual Data,18000,seedbench_seed_all,0.5457476375764313,
455
- Remove Multilingual Data,18000,textvqa_val_exact_match,0.55462,0.0067429981999808505
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869fc4724af7e9c868b6024f472f9ae0f6468b74ef61db101438f80610828abb
3
+ size 28837
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/content/assets/data/s25_ratings.csv CHANGED
@@ -1,1189 +1,3 @@
1
- run,step,metric,value,stderr
2
- ≥1,1000,ai2d_exact_match,0.48283678756476683,0.00899385068939683
3
- ≥1,1000,average,0.4841740613238066,
4
- ≥1,1000,average_rank,2.4,
5
- ≥1,1000,chartqa_relaxed_overall,0.6328,0.00964276190429159
6
- ≥1,1000,docvqa_val_anls,0.6709958484393396,0.006009113294340719
7
- ≥1,1000,infovqa_val_anls,0.2911610792718508,0.007480963558334323
8
- ≥1,1000,mme_total_score,1300.6441576630652,
9
- ≥1,1000,mmmu_val_mmmu_acc,0.28111,
10
- ≥1,1000,mmstar_average,0.34899099672724077,
11
- ≥1,1000,ocrbench_ocrbench_accuracy,0.53,
12
- ≥1,1000,seedbench_seed_all,0.5613118399110617,
13
- ≥1,1000,textvqa_val_exact_match,0.5583600000000001,0.006733787259646062
14
- ≥1,2000,ai2d_exact_match,0.4834844559585492,0.008994243503406855
15
- ≥1,2000,average,0.4870755750428875,
16
- ≥1,2000,average_rank,2.0,
17
- ≥1,2000,chartqa_relaxed_overall,0.6296,0.0096601689190934
18
- ≥1,2000,docvqa_val_anls,0.6827112292156415,0.005909694544631059
19
- ≥1,2000,infovqa_val_anls,0.26248215166111283,0.006999241957900095
20
- ≥1,2000,mme_total_score,1316.5322128851542,
21
- ≥1,2000,mmmu_val_mmmu_acc,0.29556,
22
- ≥1,2000,mmstar_average,0.351185684854186,
23
- ≥1,2000,ocrbench_ocrbench_accuracy,0.557,
24
- ≥1,2000,seedbench_seed_all,0.5579766536964981,
25
- ≥1,2000,textvqa_val_exact_match,0.5636800000000001,0.006720565803631728
26
- ≥1,3000,ai2d_exact_match,0.47085492227979275,0.008983852707691605
27
- ≥1,3000,average,0.48291385198510484,
28
- ≥1,3000,average_rank,2.7,
29
- ≥1,3000,chartqa_relaxed_overall,0.6416,0.00959252743718011
30
- ≥1,3000,docvqa_val_anls,0.680081009037435,0.005963713977526521
31
- ≥1,3000,infovqa_val_anls,0.2758757523314467,0.007145074435929658
32
- ≥1,3000,mme_total_score,1338.268607442977,
33
- ≥1,3000,mmmu_val_mmmu_acc,0.26889,
34
- ≥1,3000,mmstar_average,0.34908867626840856,
35
- ≥1,3000,ocrbench_ocrbench_accuracy,0.542,
36
- ≥1,3000,seedbench_seed_all,0.5577543079488605,
37
- ≥1,3000,textvqa_val_exact_match,0.56008,0.00674696843305253
38
- ≥1,4000,ai2d_exact_match,0.48218911917098445,0.008993442748995703
39
- ≥1,4000,average,0.49172515123492716,
40
- ≥1,4000,average_rank,2.3,
41
- ≥1,4000,chartqa_relaxed_overall,0.6488,0.009548816468986266
42
- ≥1,4000,docvqa_val_anls,0.6902890941626307,0.005912204920631156
43
- ≥1,4000,infovqa_val_anls,0.26986279043614175,0.007091114226807192
44
- ≥1,4000,mme_total_score,1322.6090436174468,
45
- ≥1,4000,mmmu_val_mmmu_acc,0.31,
46
- ≥1,4000,mmstar_average,0.35470222226954573,
47
- ≥1,4000,ocrbench_ocrbench_accuracy,0.542,
48
- ≥1,4000,seedbench_seed_all,0.5576431350750417,
49
- ≥1,4000,textvqa_val_exact_match,0.57004,0.006721660198430491
50
- ≥1,5000,ai2d_exact_match,0.48704663212435234,0.008996133680935945
51
- ≥1,5000,average,0.4922453953675835,
52
- ≥1,5000,average_rank,2.3,
53
- ≥1,5000,chartqa_relaxed_overall,0.6524,0.009526069199715017
54
- ≥1,5000,docvqa_val_anls,0.7021575420936199,0.005829944728253253
55
- ≥1,5000,infovqa_val_anls,0.2714850202382579,0.0071017460136769345
56
- ≥1,5000,mme_total_score,1372.0063025210084,
57
- ≥1,5000,mmmu_val_mmmu_acc,0.28444,
58
- ≥1,5000,mmstar_average,0.34918092027225467,
59
- ≥1,5000,ocrbench_ocrbench_accuracy,0.553,
60
- ≥1,5000,seedbench_seed_all,0.5571984435797666,
61
- ≥1,5000,textvqa_val_exact_match,0.5733,0.0066972526186883305
62
- ≥1,6000,ai2d_exact_match,0.4838082901554404,0.008994434238637761
63
- ≥1,6000,average,0.4949352825546263,
64
- ≥1,6000,average_rank,2.3,
65
- ≥1,6000,chartqa_relaxed_overall,0.6484,0.009551307082635064
66
- ≥1,6000,docvqa_val_anls,0.7034964362890477,0.00583650860725618
67
- ≥1,6000,infovqa_val_anls,0.2724245614355471,0.0071074877022118095
68
- ≥1,6000,mme_total_score,1406.1297519007603,
69
- ≥1,6000,mmmu_val_mmmu_acc,0.30333,
70
- ≥1,6000,mmstar_average,0.3537726186468994,
71
- ≥1,6000,ocrbench_ocrbench_accuracy,0.551,
72
- ≥1,6000,seedbench_seed_all,0.5621456364647026,
73
- ≥1,6000,textvqa_val_exact_match,0.57604,0.006696965995935035
74
- ≥1,7000,ai2d_exact_match,0.49158031088082904,0.008997878107766406
75
- ≥1,7000,average,0.5010900439307898,
76
- ≥1,7000,average_rank,1.9,
77
- ≥1,7000,chartqa_relaxed_overall,0.6564,0.009500090351500593
78
- ≥1,7000,docvqa_val_anls,0.7105997601562098,0.005781434620670767
79
- ≥1,7000,infovqa_val_anls,0.29338120425035286,0.007415977951206446
80
- ≥1,7000,mme_total_score,1362.5676270508204,
81
- ≥1,7000,mmmu_val_mmmu_acc,0.30778,
82
- ≥1,7000,mmstar_average,0.34667048751606516,
83
- ≥1,7000,ocrbench_ocrbench_accuracy,0.555,
84
- ≥1,7000,seedbench_seed_all,0.569538632573652,
85
- ≥1,7000,textvqa_val_exact_match,0.57886,0.006701104464206482
86
- ≥1,8000,ai2d_exact_match,0.48704663212435234,0.008996133680935945
87
- ≥1,8000,average,0.5012874693126343,
88
- ≥1,8000,average_rank,2.4,
89
- ≥1,8000,chartqa_relaxed_overall,0.66,0.009476070829586857
90
- ≥1,8000,docvqa_val_anls,0.7013710839567656,0.00584567154399218
91
- ≥1,8000,infovqa_val_anls,0.2843596286067672,0.00726326016667778
92
- ≥1,8000,mme_total_score,1366.6049419767905,
93
- ≥1,8000,mmmu_val_mmmu_acc,0.29778,
94
- ≥1,8000,mmstar_average,0.3726316801263804,
95
- ≥1,8000,ocrbench_ocrbench_accuracy,0.568,
96
- ≥1,8000,seedbench_seed_all,0.5647581989994441,
97
- ≥1,8000,textvqa_val_exact_match,0.5756399999999999,0.006701275960583923
98
- ≥1,9000,ai2d_exact_match,0.5080958549222798,0.008997974381217102
99
- ≥1,9000,average,0.5049424624827252,
100
- ≥1,9000,average_rank,1.9,
101
- ≥1,9000,chartqa_relaxed_overall,0.6644,0.009445885130487209
102
- ≥1,9000,docvqa_val_anls,0.7114743939854425,0.005784207378273765
103
- ≥1,9000,infovqa_val_anls,0.27927629692536604,0.007234508289873752
104
- ≥1,9000,mme_total_score,1385.721988795518,
105
- ≥1,9000,mmmu_val_mmmu_acc,0.30333,
106
- ≥1,9000,mmstar_average,0.35371044141416225,
107
- ≥1,9000,ocrbench_ocrbench_accuracy,0.572,
108
- ≥1,9000,seedbench_seed_all,0.5673151750972762,
109
- ≥1,9000,textvqa_val_exact_match,0.58488,0.006674247990391685
110
- ≥1,10000,ai2d_exact_match,0.5006476683937824,0.008999146569435552
111
- ≥1,10000,average,0.5082439013030791,
112
- ≥1,10000,average_rank,2.1,
113
- ≥1,10000,chartqa_relaxed_overall,0.66,0.009476070829586857
114
- ≥1,10000,docvqa_val_anls,0.7160888537676756,0.005756158349745215
115
- ≥1,10000,infovqa_val_anls,0.29920594326668903,0.0074179476099996864
116
- ≥1,10000,mme_total_score,1331.7510004001601,
117
- ≥1,10000,mmmu_val_mmmu_acc,0.31222,
118
- ≥1,10000,mmstar_average,0.34770435280317685,
119
- ≥1,10000,ocrbench_ocrbench_accuracy,0.572,
120
- ≥1,10000,seedbench_seed_all,0.5709282934963869,
121
- ≥1,10000,textvqa_val_exact_match,0.5954,0.006639803114330983
122
- ≥1,11000,ai2d_exact_match,0.506800518134715,0.008998321712163856
123
- ≥1,11000,average,0.5113045470128461,
124
- ≥1,11000,average_rank,2.4,
125
- ≥1,11000,chartqa_relaxed_overall,0.6648,0.009443095510537233
126
- ≥1,11000,docvqa_val_anls,0.7219007936057111,0.005738025679608452
127
- ≥1,11000,infovqa_val_anls,0.2919206859707748,0.007295238934448537
128
- ≥1,11000,mme_total_score,1423.2838135254103,
129
- ≥1,11000,mmmu_val_mmmu_acc,0.32,
130
- ≥1,11000,mmstar_average,0.34837257743331856,
131
- ≥1,11000,ocrbench_ocrbench_accuracy,0.584,
132
- ≥1,11000,seedbench_seed_all,0.567426347971095,
133
- ≥1,11000,textvqa_val_exact_match,0.5965199999999999,0.006637830223651069
134
- ≥1,12000,ai2d_exact_match,0.4957901554404145,0.0089988351333547
135
- ≥1,12000,average,0.5133063005116858,
136
- ≥1,12000,average_rank,2.0,
137
- ≥1,12000,chartqa_relaxed_overall,0.6752,0.00936787525721462
138
- ≥1,12000,docvqa_val_anls,0.7317458509080867,0.005677899397993261
139
- ≥1,12000,infovqa_val_anls,0.30244398410320705,0.0074372299260171675
140
- ≥1,12000,mme_total_score,1358.8711484593837,
141
- ≥1,12000,mmmu_val_mmmu_acc,0.30222,
142
- ≥1,12000,mmstar_average,0.36151764800560426,
143
- ≥1,12000,ocrbench_ocrbench_accuracy,0.571,
144
- ≥1,12000,seedbench_seed_all,0.5743190661478599,
145
- ≥1,12000,textvqa_val_exact_match,0.6055199999999998,0.006601107546780982
146
- ≥1,13000,ai2d_exact_match,0.5029145077720207,0.008999001233939133
147
- ≥1,13000,average,0.5113232076887448,
148
- ≥1,13000,average_rank,2.2,
149
- ≥1,13000,chartqa_relaxed_overall,0.6764,0.009358859508536295
150
- ≥1,13000,docvqa_val_anls,0.7299154645021083,0.005686391180628681
151
- ≥1,13000,infovqa_val_anls,0.28296895663700367,0.007106598521793854
152
- ≥1,13000,mme_total_score,1461.5425170068027,
153
- ≥1,13000,mmmu_val_mmmu_acc,0.28444,
154
- ≥1,13000,mmstar_average,0.3679555656349867,
155
- ≥1,13000,ocrbench_ocrbench_accuracy,0.575,
156
- ≥1,13000,seedbench_seed_all,0.5738743746525847,
157
- ≥1,13000,textvqa_val_exact_match,0.60844,0.006603822784953804
158
- ≥1,14000,ai2d_exact_match,0.508419689119171,0.00899787810776641
159
- ≥1,14000,average,0.5204248423941521,
160
- ≥1,14000,average_rank,1.5,
161
- ≥1,14000,chartqa_relaxed_overall,0.6748,0.009370864914387439
162
- ≥1,14000,docvqa_val_anls,0.7348023413497262,0.005658144612389036
163
- ≥1,14000,infovqa_val_anls,0.30339204212390886,0.007452040139655917
164
- ≥1,14000,mme_total_score,1421.6612645058024,
165
- ≥1,14000,mmmu_val_mmmu_acc,0.32333,
166
- ≥1,14000,mmstar_average,0.3578816768256025,
167
- ≥1,14000,ocrbench_ocrbench_accuracy,0.59,
168
- ≥1,14000,seedbench_seed_all,0.5760978321289605,
169
- ≥1,14000,textvqa_val_exact_match,0.6151,0.006568548330143662
170
- ≥1,15000,ai2d_exact_match,0.5123056994818653,0.008996428218289524
171
- ≥1,15000,average,0.518135626255078,
172
- ≥1,15000,average_rank,1.8,
173
- ≥1,15000,chartqa_relaxed_overall,0.6768,0.009355838641547569
174
- ≥1,15000,docvqa_val_anls,0.7406818231641893,0.00561534943093856
175
- ≥1,15000,infovqa_val_anls,0.2993680664172523,0.007344080406067735
176
- ≥1,15000,mme_total_score,1410.685474189676,
177
- ≥1,15000,mmmu_val_mmmu_acc,0.31778,
178
- ≥1,15000,mmstar_average,0.34818335740471335,
179
- ≥1,15000,ocrbench_ocrbench_accuracy,0.581,
180
- ≥1,15000,seedbench_seed_all,0.575041689827682,
181
- ≥1,15000,textvqa_val_exact_match,0.61206,0.006579602534644686
182
- ≥1,16000,ai2d_exact_match,0.5148963730569949,0.008995159373289019
183
- ≥1,16000,average,0.5188529848530237,
184
- ≥1,16000,average_rank,2.2,
185
- ≥1,16000,chartqa_relaxed_overall,0.6768,0.009355838641547569
186
- ≥1,16000,docvqa_val_anls,0.7381040832460759,0.005632273383411858
187
- ≥1,16000,infovqa_val_anls,0.30209162600532213,0.007372809699325085
188
- ≥1,16000,mme_total_score,1390.1362545018007,
189
- ≥1,16000,mmmu_val_mmmu_acc,0.31111,
190
- ≥1,16000,mmstar_average,0.35327018992913145,
191
- ≥1,16000,ocrbench_ocrbench_accuracy,0.581,
192
- ≥1,16000,seedbench_seed_all,0.5762645914396887,
193
- ≥1,16000,textvqa_val_exact_match,0.6161399999999999,0.006566896139347796
194
- ≥1,17000,ai2d_exact_match,0.5148963730569949,0.008995159373289019
195
- ≥1,17000,average,0.5197229023161958,
196
- ≥1,17000,average_rank,2.4,
197
- ≥1,17000,chartqa_relaxed_overall,0.6808,0.009325198535746702
198
- ≥1,17000,docvqa_val_anls,0.7415371461870564,0.005606416638789011
199
- ≥1,17000,infovqa_val_anls,0.31757741607819345,0.0075605614362149656
200
- ≥1,17000,mme_total_score,1349.7522008803521,
201
- ≥1,17000,mmmu_val_mmmu_acc,0.29556,
202
- ≥1,17000,mmstar_average,0.3467129398314668,
203
- ≥1,17000,ocrbench_ocrbench_accuracy,0.589,
204
- ≥1,17000,seedbench_seed_all,0.5760422456920511,
205
- ≥1,17000,textvqa_val_exact_match,0.6153799999999999,0.0065759668329423305
206
- ≥1,18000,ai2d_exact_match,0.5113341968911918,0.008996841687150462
207
- ≥1,18000,average,0.5217542622446647,
208
- ≥1,18000,average_rank,2.1,
209
- ≥1,18000,chartqa_relaxed_overall,0.686,0.00928418431696466
210
- ≥1,18000,docvqa_val_anls,0.7485976064804745,0.005545760483304357
211
- ≥1,18000,infovqa_val_anls,0.3079394168596966,0.007506515528281936
212
- ≥1,18000,mme_total_score,1386.236494597839,
213
- ≥1,18000,mmmu_val_mmmu_acc,0.30889,
214
- ≥1,18000,mmstar_average,0.36329690094894107,
215
- ≥1,18000,ocrbench_ocrbench_accuracy,0.58,
216
- ≥1,18000,seedbench_seed_all,0.5744302390216787,
217
- ≥1,18000,textvqa_val_exact_match,0.6153,0.006569673821646289
218
- ≥1,19000,ai2d_exact_match,0.5116580310880829,0.008996707642249475
219
- ≥1,19000,average,0.5243525940235553,
220
- ≥1,19000,average_rank,1.6,
221
- ≥1,19000,chartqa_relaxed_overall,0.6896,0.009254998541285659
222
- ≥1,19000,docvqa_val_anls,0.7410075109051968,0.005624845495160182
223
- ≥1,19000,infovqa_val_anls,0.31451986671246684,0.00754441993362511
224
- ≥1,19000,mme_total_score,1379.0539215686274,
225
- ≥1,19000,mmmu_val_mmmu_acc,0.30889,
226
- ≥1,19000,mmstar_average,0.36379458008546134,
227
- ≥1,19000,ocrbench_ocrbench_accuracy,0.594,
228
- ≥1,19000,seedbench_seed_all,0.5780433574207893,
229
- ≥1,19000,textvqa_val_exact_match,0.61766,0.006552511881896322
230
- ≥2,1000,ai2d_exact_match,0.47765544041450775,0.00899016344465196
231
- ≥2,1000,average,0.48208320918746633,
232
- ≥2,1000,average_rank,2.7,
233
- ≥2,1000,chartqa_relaxed_overall,0.626,0.009679208378267924
234
- ≥2,1000,docvqa_val_anls,0.6830886615719474,0.005941664313882304
235
- ≥2,1000,infovqa_val_anls,0.2636626226113445,0.007012099858086531
236
- ≥2,1000,mme_total_score,1394.7869147659064,
237
- ≥2,1000,mmmu_val_mmmu_acc,0.28111,
238
- ≥2,1000,mmstar_average,0.3621500124529322,
239
- ≥2,1000,ocrbench_ocrbench_accuracy,0.53,
240
- ≥2,1000,seedbench_seed_all,0.5518621456364647,
241
- ≥2,1000,textvqa_val_exact_match,0.5632199999999999,0.006735793977260649
242
- ≥2,2000,ai2d_exact_match,0.47506476683937826,0.00898795641911507
243
- ≥2,2000,average,0.48647523098478523,
244
- ≥2,2000,average_rank,2.4,
245
- ≥2,2000,chartqa_relaxed_overall,0.6392,0.00960657371300514
246
- ≥2,2000,docvqa_val_anls,0.6776161818000301,0.005964335785163625
247
- ≥2,2000,infovqa_val_anls,0.28064001553745443,0.007228333231022024
248
- ≥2,2000,mme_total_score,1262.5283113245298,
249
- ≥2,2000,mmmu_val_mmmu_acc,0.29556,
250
- ≥2,2000,mmstar_average,0.3433600502059375,
251
- ≥2,2000,ocrbench_ocrbench_accuracy,0.562,
252
- ≥2,2000,seedbench_seed_all,0.5489160644802669,
253
- ≥2,2000,textvqa_val_exact_match,0.55592,0.006741845534884587
254
- ≥2,3000,ai2d_exact_match,0.4854274611398964,0.00899533120652686
255
- ≥2,3000,average,0.4892979098475977,
256
- ≥2,3000,average_rank,2.0,
257
- ≥2,3000,chartqa_relaxed_overall,0.642,0.009590161024476605
258
- ≥2,3000,docvqa_val_anls,0.682810147307377,0.005940269120275799
259
- ≥2,3000,infovqa_val_anls,0.27552490540828095,0.007240182675336717
260
- ≥2,3000,mme_total_score,1310.3195278111243,
261
- ≥2,3000,mmmu_val_mmmu_acc,0.29667,
262
- ≥2,3000,mmstar_average,0.33383353302741087,
263
- ≥2,3000,ocrbench_ocrbench_accuracy,0.56,
264
- ≥2,3000,seedbench_seed_all,0.5592551417454141,
265
- ≥2,3000,textvqa_val_exact_match,0.56816,0.00671355771938026
266
- ≥2,4000,ai2d_exact_match,0.4838082901554404,0.008994434238637763
267
- ≥2,4000,average,0.49195026536834224,
268
- ≥2,4000,average_rank,2.2,
269
- ≥2,4000,chartqa_relaxed_overall,0.6428,0.009585406407993486
270
- ≥2,4000,docvqa_val_anls,0.6936982319965624,0.005883844142208432
271
- ≥2,4000,infovqa_val_anls,0.26951374340713585,0.007112166845409044
272
- ≥2,4000,mme_total_score,1301.329931972789,
273
- ≥2,4000,mmmu_val_mmmu_acc,0.30667,
274
- ≥2,4000,mmstar_average,0.34946626950413445,
275
- ≥2,4000,ocrbench_ocrbench_accuracy,0.547,
276
- ≥2,4000,seedbench_seed_all,0.5645358532518066,
277
- ≥2,4000,textvqa_val_exact_match,0.5700599999999999,0.006712416151142391
278
- ≥2,5000,ai2d_exact_match,0.4802461139896373,0.008992128148477658
279
- ≥2,5000,average,0.4911460216363542,
280
- ≥2,5000,average_rank,2.6,
281
- ≥2,5000,chartqa_relaxed_overall,0.6592,0.009481461028833927
282
- ≥2,5000,docvqa_val_anls,0.6952750329046061,0.005874374530558489
283
- ≥2,5000,infovqa_val_anls,0.2792676155726946,0.007321946399777712
284
- ≥2,5000,mme_total_score,1246.5271108443376,
285
- ≥2,5000,mmmu_val_mmmu_acc,0.30667,
286
- ≥2,5000,mmstar_average,0.3273375111929903,
287
- ≥2,5000,ocrbench_ocrbench_accuracy,0.544,
288
- ≥2,5000,seedbench_seed_all,0.5642579210672596,
289
- ≥2,5000,textvqa_val_exact_match,0.56406,0.006733849732986717
290
- ≥2,6000,ai2d_exact_match,0.47636010362694303,0.0089890902327936
291
- ≥2,6000,average,0.49370635223913606,
292
- ≥2,6000,average_rank,2.4,
293
- ≥2,6000,chartqa_relaxed_overall,0.6576,0.00949215130381674
294
- ≥2,6000,docvqa_val_anls,0.6979936603307108,0.005857650960456797
295
- ≥2,6000,infovqa_val_anls,0.2848576580974239,0.007220288614025636
296
- ≥2,6000,mme_total_score,1257.9977991196479,
297
- ≥2,6000,mmmu_val_mmmu_acc,0.28889,
298
- ≥2,6000,mmstar_average,0.3386087219715212,
299
- ≥2,6000,ocrbench_ocrbench_accuracy,0.555,
300
- ≥2,6000,seedbench_seed_all,0.5646470261256253,
301
- ≥2,6000,textvqa_val_exact_match,0.5794000000000001,0.0066913139768320015
302
- ≥2,7000,ai2d_exact_match,0.49125647668393785,0.008997778057794696
303
- ≥2,7000,average,0.49923190517534066,
304
- ≥2,7000,average_rank,2.4,
305
- ≥2,7000,chartqa_relaxed_overall,0.6564,0.009500090351500593
306
- ≥2,7000,docvqa_val_anls,0.7050049130392773,0.005832016517791021
307
- ≥2,7000,infovqa_val_anls,0.27630514531293887,0.007147131752819133
308
- ≥2,7000,mme_total_score,1298.6506602641057,
309
- ≥2,7000,mmmu_val_mmmu_acc,0.30667,
310
- ≥2,7000,mmstar_average,0.35103185667809866,
311
- ≥2,7000,ocrbench_ocrbench_accuracy,0.561,
312
- ≥2,7000,seedbench_seed_all,0.5657587548638132,
313
- ≥2,7000,textvqa_val_exact_match,0.5796600000000001,0.006695268643186835
314
- ≥2,8000,ai2d_exact_match,0.4948186528497409,0.008998670917263325
315
- ≥2,8000,average,0.5019054681854818,
316
- ≥2,8000,average_rank,1.7,
317
- ≥2,8000,chartqa_relaxed_overall,0.6528,0.009523504757028414
318
- ≥2,8000,docvqa_val_anls,0.7073923991601945,0.005811715016078567
319
- ≥2,8000,infovqa_val_anls,0.2893855968120429,0.007315932200378898
320
- ≥2,8000,mme_total_score,1294.7393957583033,
321
- ≥2,8000,mmmu_val_mmmu_acc,0.31444,
322
- ≥2,8000,mmstar_average,0.35566192560333365,
323
- ≥2,8000,ocrbench_ocrbench_accuracy,0.543,
324
- ≥2,8000,seedbench_seed_all,0.5711506392440244,
325
- ≥2,8000,textvqa_val_exact_match,0.5885,0.006652668757748281
326
- ≥2,9000,ai2d_exact_match,0.4961139896373057,0.008998882321332237
327
- ≥2,9000,average,0.5033958878673905,
328
- ≥2,9000,average_rank,1.8,
329
- ≥2,9000,chartqa_relaxed_overall,0.6652,0.009440298284094473
330
- ≥2,9000,docvqa_val_anls,0.706747911546142,0.005822953083156574
331
- ≥2,9000,infovqa_val_anls,0.2960318229790583,0.007315313753711981
332
- ≥2,9000,mme_total_score,1284.486194477791,
333
- ≥2,9000,mmmu_val_mmmu_acc,0.31111,
334
- ≥2,9000,mmstar_average,0.3461876713132692,
335
- ≥2,9000,ocrbench_ocrbench_accuracy,0.551,
336
- ≥2,9000,seedbench_seed_all,0.5688715953307393,
337
- ≥2,9000,textvqa_val_exact_match,0.5893,0.006649446971666576
338
- ≥2,10000,ai2d_exact_match,0.4954663212435233,0.008998784170060763
339
- ≥2,10000,average,0.5062630509259689,
340
- ≥2,10000,average_rank,2.5,
341
- ≥2,10000,chartqa_relaxed_overall,0.668,0.009420504145710235
342
- ≥2,10000,docvqa_val_anls,0.722875937910498,0.005715570269767272
343
- ≥2,10000,infovqa_val_anls,0.28155653174519985,0.007182472403759747
344
- ≥2,10000,mme_total_score,1304.360544217687,
345
- ≥2,10000,mmmu_val_mmmu_acc,0.31556,
346
- ≥2,10000,mmstar_average,0.34845583808486047,
347
- ≥2,10000,ocrbench_ocrbench_accuracy,0.564,
348
- ≥2,10000,seedbench_seed_all,0.5670928293496387,
349
- ≥2,10000,textvqa_val_exact_match,0.59336,0.006650836699676301
350
- ≥2,11000,ai2d_exact_match,0.5093911917098446,0.008997566627779879
351
- ≥2,11000,average,0.5121996275740728,
352
- ≥2,11000,average_rank,2.1,
353
- ≥2,11000,chartqa_relaxed_overall,0.6692,0.009411906161401973
354
- ≥2,11000,docvqa_val_anls,0.7205703696519083,0.005737270521428796
355
- ≥2,11000,infovqa_val_anls,0.30697732217578644,0.007486340094072884
356
- ≥2,11000,mme_total_score,1312.018607442977,
357
- ≥2,11000,mmmu_val_mmmu_acc,0.30889,
358
- ≥2,11000,mmstar_average,0.34270221710271187,
359
- ≥2,11000,ocrbench_ocrbench_accuracy,0.574,
360
- ≥2,11000,seedbench_seed_all,0.5739855475264035,
361
- ≥2,11000,textvqa_val_exact_match,0.6040800000000001,0.00661203558088616
362
- ≥2,12000,ai2d_exact_match,0.5123056994818653,0.008996428218289528
363
- ≥2,12000,average,0.5150951619345675,
364
- ≥2,12000,average_rank,2.3,
365
- ≥2,12000,chartqa_relaxed_overall,0.6672,0.00942619781683542
366
- ≥2,12000,docvqa_val_anls,0.726550362704052,0.005691891264118933
367
- ≥2,12000,infovqa_val_anls,0.3008889889078986,0.007362325835960529
368
- ≥2,12000,mme_total_score,1224.6687675070027,
369
- ≥2,12000,mmmu_val_mmmu_acc,0.31444,
370
- ≥2,12000,mmstar_average,0.35781468591706916,
371
- ≥2,12000,ocrbench_ocrbench_accuracy,0.58,
372
- ≥2,12000,seedbench_seed_all,0.5740967204002223,
373
- ≥2,12000,textvqa_val_exact_match,0.60256,0.006618961505423797
374
- ≥2,13000,ai2d_exact_match,0.5080958549222798,0.0089979743812171
375
- ≥2,13000,average,0.5180586542380377,
376
- ≥2,13000,average_rank,1.4,
377
- ≥2,13000,chartqa_relaxed_overall,0.6752,0.00936787525721462
378
- ≥2,13000,docvqa_val_anls,0.726059208019786,0.0056904102427854444
379
- ≥2,13000,infovqa_val_anls,0.3067653345076983,0.007414171368476549
380
- ≥2,13000,mme_total_score,1241.2817126850741,
381
- ≥2,13000,mmmu_val_mmmu_acc,0.31778,
382
- ≥2,13000,mmstar_average,0.35994731281597653,
383
- ≥2,13000,ocrbench_ocrbench_accuracy,0.582,
384
- ≥2,13000,seedbench_seed_all,0.5763201778765981,
385
- ≥2,13000,textvqa_val_exact_match,0.61036,0.006605638574142127
386
- ≥2,14000,ai2d_exact_match,0.5055051813471503,0.008998608627616667
387
- ≥2,14000,average,0.5187199474947337,
388
- ≥2,14000,average_rank,2.1,
389
- ≥2,14000,chartqa_relaxed_overall,0.6788,0.00934061683451043
390
- ≥2,14000,docvqa_val_anls,0.7306315173289623,0.005670445587318404
391
- ≥2,14000,infovqa_val_anls,0.30084936045159133,0.007340699586893536
392
- ≥2,14000,mme_total_score,1266.9314725890356,
393
- ≥2,14000,mmmu_val_mmmu_acc,0.32,
394
- ≥2,14000,mmstar_average,0.360779371604499,
395
- ≥2,14000,ocrbench_ocrbench_accuracy,0.587,
396
- ≥2,14000,seedbench_seed_all,0.5733740967204002,
397
- ≥2,14000,textvqa_val_exact_match,0.61154,0.006582281592745273
398
- ≥2,15000,ai2d_exact_match,0.5077720207253886,0.008998066878268323
399
- ≥2,15000,average,0.5182417002827931,
400
- ≥2,15000,average_rank,2.2,
401
- ≥2,15000,chartqa_relaxed_overall,0.6732,0.009382745779746297
402
- ≥2,15000,docvqa_val_anls,0.7366238053330653,0.005647248266865468
403
- ≥2,15000,infovqa_val_anls,0.30893362163842225,0.007385953320794889
404
- ≥2,15000,mme_total_score,1280.3160264105643,
405
- ≥2,15000,mmmu_val_mmmu_acc,0.31778,
406
- ≥2,15000,mmstar_average,0.3597603073218589,
407
- ≥2,15000,ocrbench_ocrbench_accuracy,0.571,
408
- ≥2,15000,seedbench_seed_all,0.5739855475264035,
409
- ≥2,15000,textvqa_val_exact_match,0.61512,0.006574049037248568
410
- ≥2,16000,ai2d_exact_match,0.5055051813471503,0.008998608627616667
411
- ≥2,16000,average,0.5226694963682967,
412
- ≥2,16000,average_rank,1.9,
413
- ≥2,16000,chartqa_relaxed_overall,0.6844,0.009296947310365735
414
- ≥2,16000,docvqa_val_anls,0.7369050997741022,0.00564381681657765
415
- ≥2,16000,infovqa_val_anls,0.2990672453595873,0.007260058695111045
416
- ≥2,16000,mme_total_score,1231.8950580232092,
417
- ≥2,16000,mmmu_val_mmmu_acc,0.32333,
418
- ≥2,16000,mmstar_average,0.3660943054808571,
419
- ≥2,16000,ocrbench_ocrbench_accuracy,0.601,
420
- ≥2,16000,seedbench_seed_all,0.5785436353529739,
421
- ≥2,16000,textvqa_val_exact_match,0.6091799999999999,0.006589463538554954
422
- ≥2,17000,ai2d_exact_match,0.5097150259067358,0.008997455247470535
423
- ≥2,17000,average,0.5231030271400094,
424
- ≥2,17000,average_rank,1.5,
425
- ≥2,17000,chartqa_relaxed_overall,0.6844,0.009296947310365735
426
- ≥2,17000,docvqa_val_anls,0.7407178352725541,0.005609117579860497
427
- ≥2,17000,infovqa_val_anls,0.30677928223689904,0.007423923972542159
428
- ≥2,17000,mme_total_score,1251.8118247298921,
429
- ≥2,17000,mmmu_val_mmmu_acc,0.31333,
430
- ≥2,17000,mmstar_average,0.35755470618019386,
431
- ≥2,17000,ocrbench_ocrbench_accuracy,0.595,
432
- ≥2,17000,seedbench_seed_all,0.5787103946637021,
433
- ≥2,17000,textvqa_val_exact_match,0.6217199999999999,0.006547657801423109
434
- ≥2,18000,ai2d_exact_match,0.5129533678756477,0.008996133680935945
435
- ≥2,18000,average,0.520551210243477,
436
- ≥2,18000,average_rank,2.1,
437
- ≥2,18000,chartqa_relaxed_overall,0.6796,0.009334473148259746
438
- ≥2,18000,docvqa_val_anls,0.7420992559479452,0.005605162069925204
439
- ≥2,18000,infovqa_val_anls,0.30026388587258485,0.007302705356586967
440
- ≥2,18000,mme_total_score,1243.8207282913165,
441
- ≥2,18000,mmmu_val_mmmu_acc,0.31111,
442
- ≥2,18000,mmstar_average,0.3520362724339696,
443
- ≥2,18000,ocrbench_ocrbench_accuracy,0.591,
444
- ≥2,18000,seedbench_seed_all,0.576598110061145,
445
- ≥2,18000,textvqa_val_exact_match,0.6193,0.006553540400299342
446
- ≥2,19000,ai2d_exact_match,0.508419689119171,0.008997878107766411
447
- ≥2,19000,average,0.523370364263479,
448
- ≥2,19000,average_rank,2.1,
449
- ≥2,19000,chartqa_relaxed_overall,0.6852,0.009290581788240476
450
- ≥2,19000,docvqa_val_anls,0.7378793056289451,0.005630284657853331
451
- ≥2,19000,infovqa_val_anls,0.29852452208029057,0.007300069652856512
452
- ≥2,19000,mme_total_score,1273.484593837535,
453
- ≥2,19000,mmmu_val_mmmu_acc,0.31778,
454
- ≥2,19000,mmstar_average,0.3583181328603031,
455
- ≥2,19000,ocrbench_ocrbench_accuracy,0.609,
456
- ≥2,19000,seedbench_seed_all,0.5769316286826014,
457
- ≥2,19000,textvqa_val_exact_match,0.6182799999999999,0.0065560479462046795
458
- ≥2,20000,ai2d_exact_match,0.5132772020725389,0.008995980744276042
459
- ≥2,20000,average,0.5252790448062622,
460
- ≥2,20000,average_rank,1.1,
461
- ≥2,20000,chartqa_relaxed_overall,0.6808,0.009325198535746702
462
- ≥2,20000,docvqa_val_anls,0.7417425674578729,0.0056064333517934105
463
- ≥2,20000,infovqa_val_anls,0.3091382953917658,0.007408396253875713
464
- ≥2,20000,mme_total_score,1276.3417366946778,
465
- ≥2,20000,mmmu_val_mmmu_acc,0.31778,
466
- ≥2,20000,mmstar_average,0.35941177079666153,
467
- ≥2,20000,ocrbench_ocrbench_accuracy,0.607,
468
- ≥2,20000,seedbench_seed_all,0.5788215675375209,
469
- ≥2,20000,textvqa_val_exact_match,0.6195400000000001,0.0065546800414733606
470
- ≥3,1000,ai2d_exact_match,0.46696891191709844,0.008979495543032526
471
- ≥3,1000,average,0.4819077497875202,
472
- ≥3,1000,average_rank,2.6,
473
- ≥3,1000,chartqa_relaxed_overall,0.6376,0.009615793331418735
474
- ≥3,1000,docvqa_val_anls,0.6765375416572318,0.00595906808496784
475
- ≥3,1000,infovqa_val_anls,0.28562874655210324,0.007377482443151623
476
- ≥3,1000,mme_total_score,1210.921368547419,
477
- ≥3,1000,mmmu_val_mmmu_acc,0.28556,
478
- ≥3,1000,mmstar_average,0.342259005993489,
479
- ≥3,1000,ocrbench_ocrbench_accuracy,0.534,
480
- ≥3,1000,seedbench_seed_all,0.5559755419677599,
481
- ≥3,1000,textvqa_val_exact_match,0.5526399999999999,0.006746058696867995
482
- ≥3,2000,ai2d_exact_match,0.4685880829015544,0.008981377477192708
483
- ≥3,2000,average,0.48620065133730717,
484
- ≥3,2000,average_rank,2.0,
485
- ≥3,2000,chartqa_relaxed_overall,0.6356,0.009627155802808046
486
- ≥3,2000,docvqa_val_anls,0.6718354763369633,0.005996528203070324
487
- ≥3,2000,infovqa_val_anls,0.26419815798743335,0.006939135175774486
488
- ≥3,2000,mme_total_score,1264.654161664666,
489
- ≥3,2000,mmmu_val_mmmu_acc,0.30333,
490
- ≥3,2000,mmstar_average,0.3562263182394967,
491
- ≥3,2000,ocrbench_ocrbench_accuracy,0.551,
492
- ≥3,2000,seedbench_seed_all,0.5580878265703169,
493
- ≥3,2000,textvqa_val_exact_match,0.56694,0.0067100232609457085
494
- ≥3,3000,ai2d_exact_match,0.4838082901554404,0.008994434238637763
495
- ≥3,3000,average,0.48597261570869915,
496
- ≥3,3000,average_rank,3.0,
497
- ≥3,3000,chartqa_relaxed_overall,0.6316,0.009649342979082627
498
- ≥3,3000,docvqa_val_anls,0.6746316657514325,0.005965125654000594
499
- ≥3,3000,infovqa_val_anls,0.26946459224600977,0.007089931445596614
500
- ≥3,3000,mme_total_score,1247.7741096438576,
501
- ≥3,3000,mmmu_val_mmmu_acc,0.28556,
502
- ≥3,3000,mmstar_average,0.3458825563160156,
503
- ≥3,3000,ocrbench_ocrbench_accuracy,0.562,
504
- ≥3,3000,seedbench_seed_all,0.5555864369093941,
505
- ≥3,3000,textvqa_val_exact_match,0.56522,0.006727876573231477
506
- ≥3,4000,ai2d_exact_match,0.48575129533678757,0.008995499260034972
507
- ≥3,4000,average,0.49355357269641903,
508
- ≥3,4000,average_rank,2.2,
509
- ≥3,4000,chartqa_relaxed_overall,0.6548,0.009510571191350932
510
- ≥3,4000,docvqa_val_anls,0.6853328262496681,0.0059320222320751875
511
- ≥3,4000,infovqa_val_anls,0.2850385340966683,0.007361799302921674
512
- ≥3,4000,mme_total_score,1288.7305922368948,
513
- ≥3,4000,mmmu_val_mmmu_acc,0.30111,
514
- ≥3,4000,mmstar_average,0.357958492470139,
515
- ≥3,4000,ocrbench_ocrbench_accuracy,0.541,
516
- ≥3,4000,seedbench_seed_all,0.5598110061145081,
517
- ≥3,4000,textvqa_val_exact_match,0.57118,0.006705227329084893
518
- ≥3,5000,ai2d_exact_match,0.4727979274611399,0.008985826352357517
519
- ≥3,5000,average,0.4915808423458039,
520
- ≥3,5000,average_rank,2.6,
521
- ≥3,5000,chartqa_relaxed_overall,0.6516,0.009531175862679805
522
- ≥3,5000,docvqa_val_anls,0.6805544343770252,0.005954062592926349
523
- ≥3,5000,infovqa_val_anls,0.2790745100628044,0.007226853744230138
524
- ≥3,5000,mme_total_score,1234.2862144857945,
525
- ≥3,5000,mmmu_val_mmmu_acc,0.30889,
526
- ≥3,5000,mmstar_average,0.3515137442307206,
527
- ≥3,5000,ocrbench_ocrbench_accuracy,0.548,
528
- ≥3,5000,seedbench_seed_all,0.5665369649805447,
529
- ≥3,5000,textvqa_val_exact_match,0.56526,0.006737603842695726
530
- ≥3,6000,ai2d_exact_match,0.4834844559585492,0.008994243503406857
531
- ≥3,6000,average,0.4916502418219912,
532
- ≥3,6000,average_rank,2.8,
533
- ≥3,6000,chartqa_relaxed_overall,0.6504,0.009538780390203614
534
- ≥3,6000,docvqa_val_anls,0.6884045774843457,0.005915343845415068
535
- ≥3,6000,infovqa_val_anls,0.27942328823789453,0.007164390448746867
536
- ≥3,6000,mme_total_score,1169.1683673469388,
537
- ≥3,6000,mmmu_val_mmmu_acc,0.28333,
538
- ≥3,6000,mmstar_average,0.3409248964069589,
539
- ≥3,6000,ocrbench_ocrbench_accuracy,0.564,
540
- ≥3,6000,seedbench_seed_all,0.5649249583101723,
541
- ≥3,6000,textvqa_val_exact_match,0.5699599999999999,0.006704305275108255
542
- ≥3,7000,ai2d_exact_match,0.49158031088082904,0.008997878107766406
543
- ≥3,7000,average,0.498429728288751,
544
- ≥3,7000,average_rank,2.5,
545
- ≥3,7000,chartqa_relaxed_overall,0.6468,0.009561196085649289
546
- ≥3,7000,docvqa_val_anls,0.6934235036732116,0.005908575911274035
547
- ≥3,7000,infovqa_val_anls,0.29038240983122426,0.0073217194111741745
548
- ≥3,7000,mme_total_score,1180.5045018007202,
549
- ≥3,7000,mmmu_val_mmmu_acc,0.31111,
550
- ≥3,7000,mmstar_average,0.3501487176509592,
551
- ≥3,7000,ocrbench_ocrbench_accuracy,0.562,
552
- ≥3,7000,seedbench_seed_all,0.5647026125625347,
553
- ≥3,7000,textvqa_val_exact_match,0.57572,0.00668387845238326
554
- ≥3,8000,ai2d_exact_match,0.5048575129533679,0.008998729431386472
555
- ≥3,8000,average,0.4984949624992469,
556
- ≥3,8000,average_rank,2.8,
557
- ≥3,8000,chartqa_relaxed_overall,0.6472,0.009558734841217527
558
- ≥3,8000,docvqa_val_anls,0.7000334929155309,0.005878854074791644
559
- ≥3,8000,infovqa_val_anls,0.286719889854365,0.0073233352192073635
560
- ≥3,8000,mme_total_score,1136.111644657863,
561
- ≥3,8000,mmmu_val_mmmu_acc,0.28778,
562
- ≥3,8000,mmstar_average,0.33112430039975294,
563
- ≥3,8000,ocrbench_ocrbench_accuracy,0.578,
564
- ≥3,8000,seedbench_seed_all,0.5710394663702056,
565
- ≥3,8000,textvqa_val_exact_match,0.5797000000000001,0.006692483833971778
566
- ≥3,9000,ai2d_exact_match,0.4944948186528497,0.00899860862761667
567
- ≥3,9000,average,0.5022809828687513,
568
- ≥3,9000,average_rank,2.8,
569
- ≥3,9000,chartqa_relaxed_overall,0.6648,0.009443095510537233
570
- ≥3,9000,docvqa_val_anls,0.7066412322864666,0.005811056629671494
571
- ≥3,9000,infovqa_val_anls,0.2915189250095514,0.007376511883779376
572
- ≥3,9000,mme_total_score,1097.9659863945578,
573
- ≥3,9000,mmmu_val_mmmu_acc,0.3,
574
- ≥3,9000,mmstar_average,0.34971925063698756,
575
- ≥3,9000,ocrbench_ocrbench_accuracy,0.565,
576
- ≥3,9000,seedbench_seed_all,0.5663146192329072,
577
- ≥3,9000,textvqa_val_exact_match,0.58204,0.006677395090979731
578
- ≥3,10000,ai2d_exact_match,0.49287564766839376,0.008998240543632312
579
- ≥3,10000,average,0.5094325810245673,
580
- ≥3,10000,average_rank,2.2,
581
- ≥3,10000,chartqa_relaxed_overall,0.6704,0.009403239035659185
582
- ≥3,10000,docvqa_val_anls,0.7142047579734908,0.005771728801461397
583
- ≥3,10000,infovqa_val_anls,0.2964737261567996,0.007512514632225057
584
- ≥3,10000,mme_total_score,1149.6209483793518,
585
- ≥3,10000,mmmu_val_mmmu_acc,0.30778,
586
- ≥3,10000,mmstar_average,0.3527466682951291,
587
- ≥3,10000,ocrbench_ocrbench_accuracy,0.577,
588
- ≥3,10000,seedbench_seed_all,0.5703724291272929,
589
- ≥3,10000,textvqa_val_exact_match,0.6030399999999999,0.006618920886575133
590
- ≥3,11000,ai2d_exact_match,0.506800518134715,0.008998321712163861
591
- ≥3,11000,average,0.5127105840130626,
592
- ≥3,11000,average_rank,2.3,
593
- ≥3,11000,chartqa_relaxed_overall,0.6676,0.009423354808471266
594
- ≥3,11000,docvqa_val_anls,0.7155651550295605,0.005774638250173171
595
- ≥3,11000,infovqa_val_anls,0.2960078107648859,0.007491292300444957
596
- ≥3,11000,mme_total_score,1091.2908163265306,
597
- ≥3,11000,mmmu_val_mmmu_acc,0.31,
598
- ≥3,11000,mmstar_average,0.3487291874190849,
599
- ≥3,11000,ocrbench_ocrbench_accuracy,0.597,
600
- ≥3,11000,seedbench_seed_all,0.5746525847693162,
601
- ≥3,11000,textvqa_val_exact_match,0.59804,0.006635181746369987
602
- ≥3,12000,ai2d_exact_match,0.5045336787564767,0.008998784170060779
603
- ≥3,12000,average,0.5136574673989756,
604
- ≥3,12000,average_rank,2.5,
605
- ≥3,12000,chartqa_relaxed_overall,0.6648,0.009443095510537233
606
- ≥3,12000,docvqa_val_anls,0.7173866974813923,0.005773853880330729
607
- ≥3,12000,infovqa_val_anls,0.31948469442993455,0.007793312195447671
608
- ≥3,12000,mme_total_score,1082.547619047619,
609
- ≥3,12000,mmmu_val_mmmu_acc,0.29889,
610
- ≥3,12000,mmstar_average,0.3472872054060228,
611
- ≥3,12000,ocrbench_ocrbench_accuracy,0.593,
612
- ≥3,12000,seedbench_seed_all,0.5748749305169538,
613
- ≥3,12000,textvqa_val_exact_match,0.6026600000000001,0.006626535072978538
614
- ≥3,13000,ai2d_exact_match,0.4996761658031088,0.008999152231809674
615
- ≥3,13000,average,0.5115591424915379,
616
- ≥3,13000,average_rank,3.0,
617
- ≥3,13000,chartqa_relaxed_overall,0.668,0.009420504145710235
618
- ≥3,13000,docvqa_val_anls,0.7201586562486062,0.005765862770757432
619
- ≥3,13000,infovqa_val_anls,0.30087605763050673,0.007444543350447085
620
- ≥3,13000,mme_total_score,1142.0209083633454,
621
- ≥3,13000,mmmu_val_mmmu_acc,0.31333,
622
- ≥3,13000,mmstar_average,0.35413412647702824,
623
- ≥3,13000,ocrbench_ocrbench_accuracy,0.568,
624
- ≥3,13000,seedbench_seed_all,0.5750972762645914,
625
- ≥3,13000,textvqa_val_exact_match,0.60476,0.0066167835724745445
626
- ≥3,14000,ai2d_exact_match,0.5051813471502591,0.008998670917263325
627
- ≥3,14000,average,0.512283584996583,
628
- ≥3,14000,average_rank,2.9,
629
- ≥3,14000,chartqa_relaxed_overall,0.6748,0.009370864914387439
630
- ≥3,14000,docvqa_val_anls,0.7235575236423071,0.0057268410738261786
631
- ≥3,14000,infovqa_val_anls,0.30893243437607226,0.007712373578271492
632
- ≥3,14000,mme_total_score,1159.9943977591035,
633
- ≥3,14000,mmmu_val_mmmu_acc,0.29667,
634
- ≥3,14000,mmstar_average,0.3421543616905478,
635
- ≥3,14000,ocrbench_ocrbench_accuracy,0.576,
636
- ≥3,14000,seedbench_seed_all,0.5778765981100611,
637
- ≥3,14000,textvqa_val_exact_match,0.6053799999999999,0.006612545370071516
638
- ≥3,15000,ai2d_exact_match,0.501619170984456,0.00899910693271464
639
- ≥3,15000,average,0.5157692661333466,
640
- ≥3,15000,average_rank,2.6,
641
- ≥3,15000,chartqa_relaxed_overall,0.6836,0.009303280948921504
642
- ≥3,15000,docvqa_val_anls,0.7289675184474169,0.005688711489562826
643
- ≥3,15000,infovqa_val_anls,0.31447779168584217,0.0076280570930290885
644
- ≥3,15000,mme_total_score,1129.2125850340135,
645
- ≥3,15000,mmmu_val_mmmu_acc,0.31222,
646
- ≥3,15000,mmstar_average,0.35035142103070877,
647
- ≥3,15000,ocrbench_ocrbench_accuracy,0.563,
648
- ≥3,15000,seedbench_seed_all,0.5774874930516953,
649
- ≥3,15000,textvqa_val_exact_match,0.6102,0.006593260666562748
650
- ≥3,16000,ai2d_exact_match,0.506800518134715,0.00899832171216386
651
- ≥3,16000,average,0.5182958246289815,
652
- ≥3,16000,average_rank,2.5,
653
- ≥3,16000,chartqa_relaxed_overall,0.674,0.009376820884924869
654
- ≥3,16000,docvqa_val_anls,0.7332718536740643,0.005664165532854214
655
- ≥3,16000,infovqa_val_anls,0.3097055695251213,0.007564531791761635
656
- ≥3,16000,mme_total_score,1158.8010204081631,
657
- ≥3,16000,mmmu_val_mmmu_acc,0.30889,
658
- ≥3,16000,mmstar_average,0.3535555364692335,
659
- ≥3,16000,ocrbench_ocrbench_accuracy,0.588,
660
- ≥3,16000,seedbench_seed_all,0.5780989438576987,
661
- ≥3,16000,textvqa_val_exact_match,0.61234,0.006584482968555135
662
- ≥3,17000,ai2d_exact_match,0.4990284974093264,0.008999137132137064
663
- ≥3,17000,average,0.517538300624539,
664
- ≥3,17000,average_rank,2.8,
665
- ≥3,17000,chartqa_relaxed_overall,0.6736,0.009379787213112317
666
- ≥3,17000,docvqa_val_anls,0.7343487873475517,0.005650745093023672
667
- ≥3,17000,infovqa_val_anls,0.30023060019445785,0.007383738588396597
668
- ≥3,17000,mme_total_score,1158.095238095238,
669
- ≥3,17000,mmmu_val_mmmu_acc,0.31222,
670
- ≥3,17000,mmstar_average,0.3493043581903593,
671
- ≥3,17000,ocrbench_ocrbench_accuracy,0.594,
672
- ≥3,17000,seedbench_seed_all,0.5784324624791551,
673
- ≥3,17000,textvqa_val_exact_match,0.61668,0.0065583044906102304
674
- ≥3,18000,ai2d_exact_match,0.5058290155440415,0.008998542562369287
675
- ≥3,18000,average,0.5182210734972332,
676
- ≥3,18000,average_rank,2.5,
677
- ≥3,18000,chartqa_relaxed_overall,0.674,0.009376820884924869
678
- ≥3,18000,docvqa_val_anls,0.7287326909630594,0.005700735629180951
679
- ≥3,18000,infovqa_val_anls,0.30100700787702633,0.007386740457934267
680
- ≥3,18000,mme_total_score,1175.5579231692677,
681
- ≥3,18000,mmmu_val_mmmu_acc,0.32,
682
- ≥3,18000,mmstar_average,0.34714462691309605,
683
- ≥3,18000,ocrbench_ocrbench_accuracy,0.6,
684
- ≥3,18000,seedbench_seed_all,0.5773763201778765,
685
- ≥3,18000,textvqa_val_exact_match,0.6099,0.006589801445917723
686
- ≥3,19000,ai2d_exact_match,0.5045336787564767,0.008998784170060777
687
- ≥3,19000,average,0.5187824665863345,
688
- ≥3,19000,average_rank,2.7,
689
- ≥3,19000,chartqa_relaxed_overall,0.6768,0.009355838641547569
690
- ≥3,19000,docvqa_val_anls,0.7340665543774125,0.005662673189593881
691
- ≥3,19000,infovqa_val_anls,0.3094998838176309,0.007498739242965892
692
- ≥3,19000,mme_total_score,1173.1207482993198,
693
- ≥3,19000,mmmu_val_mmmu_acc,0.30444,
694
- ≥3,19000,mmstar_average,0.34505224352615843,
695
- ≥3,19000,ocrbench_ocrbench_accuracy,0.597,
696
- ≥3,19000,seedbench_seed_all,0.5777098387993329,
697
- ≥3,19000,textvqa_val_exact_match,0.6199399999999999,0.0065535844523310115
698
- ≥3,20000,ai2d_exact_match,0.4944948186528497,0.008998608627616674
699
- ≥3,20000,average,0.5158935311436484,
700
- ≥3,20000,average_rank,2.2,
701
- ≥3,20000,chartqa_relaxed_overall,0.6788,0.00934061683451043
702
- ≥3,20000,docvqa_val_anls,0.7330651042103438,0.0056772111451400455
703
- ≥3,20000,infovqa_val_anls,0.2964558374276726,0.007412691037826716
704
- ≥3,20000,mme_total_score,1203.7891156462586,
705
- ≥3,20000,mmmu_val_mmmu_acc,0.31556,
706
- ≥3,20000,mmstar_average,0.3448737131648378,
707
- ≥3,20000,ocrbench_ocrbench_accuracy,0.592,
708
- ≥3,20000,seedbench_seed_all,0.5741523068371317,
709
- ≥3,20000,textvqa_val_exact_match,0.6136400000000001,0.006578650759020563
710
- ≥4,1000,ai2d_exact_match,0.46599740932642486,0.008978320789223164
711
- ≥4,1000,average,0.4810433130994131,
712
- ≥4,1000,average_rank,3.0,
713
- ≥4,1000,chartqa_relaxed_overall,0.6364,0.009622632385247222
714
- ≥4,1000,docvqa_val_anls,0.6731681544556957,0.005980246808815758
715
- ≥4,1000,infovqa_val_anls,0.273064875980351,0.007121239402495689
716
- ≥4,1000,mme_total_score,1069.875850340136,
717
- ≥4,1000,mmmu_val_mmmu_acc,0.28889,
718
- ≥4,1000,mmstar_average,0.35232408630345313,
719
- ≥4,1000,ocrbench_ocrbench_accuracy,0.54,
720
- ≥4,1000,seedbench_seed_all,0.5455252918287937,
721
- ≥4,1000,textvqa_val_exact_match,0.5540200000000001,0.006743431077169729
722
- ≥4,2000,ai2d_exact_match,0.4579015544041451,0.00896719935987288
723
- ≥4,2000,average,0.4733427752805117,
724
- ≥4,2000,average_rank,4.1,
725
- ≥4,2000,chartqa_relaxed_overall,0.6368,0.009620359896064799
726
- ≥4,2000,docvqa_val_anls,0.6685623057181342,0.006022846398992095
727
- ≥4,2000,infovqa_val_anls,0.2586347697028306,0.006939507684848232
728
- ≥4,2000,mme_total_score,1037.0391156462586,
729
- ≥4,2000,mmmu_val_mmmu_acc,0.27778,
730
- ≥4,2000,mmstar_average,0.3426833682664769,
731
- ≥4,2000,ocrbench_ocrbench_accuracy,0.517,
732
- ≥4,2000,seedbench_seed_all,0.5533629794330184,
733
- ≥4,2000,textvqa_val_exact_match,0.5473600000000001,0.006769325729654826
734
- ≥4,3000,ai2d_exact_match,0.4724740932642487,0.008985506893308395
735
- ≥4,3000,average,0.48486620292260835,
736
- ≥4,3000,average_rank,3.1,
737
- ≥4,3000,chartqa_relaxed_overall,0.648,0.009553790345406665
738
- ≥4,3000,docvqa_val_anls,0.6797920414745026,0.0059259219910189455
739
- ≥4,3000,infovqa_val_anls,0.25291991664683544,0.0068990348571168
740
- ≥4,3000,mme_total_score,989.6139455782312,
741
- ≥4,3000,mmmu_val_mmmu_acc,0.31889,
742
- ≥4,3000,mmstar_average,0.359381486980145,
743
- ≥4,3000,ocrbench_ocrbench_accuracy,0.528,
744
- ≥4,3000,seedbench_seed_all,0.5529182879377432,
745
- ≥4,3000,textvqa_val_exact_match,0.55142,0.006751052663282407
746
- ≥4,4000,ai2d_exact_match,0.48704663212435234,0.008996133680935945
747
- ≥4,4000,average,0.4833844903828087,
748
- ≥4,4000,average_rank,3.6,
749
- ≥4,4000,chartqa_relaxed_overall,0.634,0.00963611653607192
750
- ≥4,4000,docvqa_val_anls,0.6872369707367743,0.005902275856072045
751
- ≥4,4000,infovqa_val_anls,0.26951247528968925,0.007084476663871501
752
- ≥4,4000,mme_total_score,943.8639455782313,
753
- ≥4,4000,mmmu_val_mmmu_acc,0.28556,
754
- ≥4,4000,mmstar_average,0.3561252135601649,
755
- ≥4,4000,ocrbench_ocrbench_accuracy,0.525,
756
- ≥4,4000,seedbench_seed_all,0.5544191217342969,
757
- ≥4,4000,textvqa_val_exact_match,0.55156,0.006755726552211068
758
- ≥4,5000,ai2d_exact_match,0.4944948186528497,0.008998608627616672
759
- ≥4,5000,average,0.4902778679880179,
760
- ≥4,5000,average_rank,3.2,
761
- ≥4,5000,chartqa_relaxed_overall,0.6524,0.009526069199715017
762
- ≥4,5000,docvqa_val_anls,0.6838821393578449,0.005934519981948664
763
- ≥4,5000,infovqa_val_anls,0.2885173111410286,0.007387917761485684
764
- ≥4,5000,mme_total_score,877.7568027210884,
765
- ≥4,5000,mmmu_val_mmmu_acc,0.28222,
766
- ≥4,5000,mmstar_average,0.3491170485770135,
767
- ≥4,5000,ocrbench_ocrbench_accuracy,0.543,
768
- ≥4,5000,seedbench_seed_all,0.5610894941634241,
769
- ≥4,5000,textvqa_val_exact_match,0.55778,0.006740043023304169
770
- ≥4,6000,ai2d_exact_match,0.47830310880829013,0.008990677331728418
771
- ≥4,6000,average,0.49160704402561856,
772
- ≥4,6000,average_rank,3.2,
773
- ≥4,6000,chartqa_relaxed_overall,0.6524,0.009526069199715017
774
- ≥4,6000,docvqa_val_anls,0.6895610098990497,0.005895883993977457
775
- ≥4,6000,infovqa_val_anls,0.29445466931250164,0.007468796422091737
776
- ≥4,6000,mme_total_score,959.8639455782312,
777
- ≥4,6000,mmmu_val_mmmu_acc,0.29889,
778
- ≥4,6000,mmstar_average,0.33644817130133137,
779
- ≥4,6000,ocrbench_ocrbench_accuracy,0.56,
780
- ≥4,6000,seedbench_seed_all,0.5555864369093941,
781
- ≥4,6000,textvqa_val_exact_match,0.5588199999999999,0.006728260950578821
782
- ≥4,7000,ai2d_exact_match,0.5006476683937824,0.008999146569435549
783
- ≥4,7000,average,0.4896016595164798,
784
- ≥4,7000,average_rank,3.4,
785
- ≥4,7000,chartqa_relaxed_overall,0.6572,0.009494805133851454
786
- ≥4,7000,docvqa_val_anls,0.6893686651094205,0.0058969034940001145
787
- ≥4,7000,infovqa_val_anls,0.2859893612299588,0.00729316403263038
788
- ≥4,7000,mme_total_score,927.2312925170069,
789
- ≥4,7000,mmmu_val_mmmu_acc,0.29222,
790
- ≥4,7000,mmstar_average,0.3472936989473972,
791
- ≥4,7000,ocrbench_ocrbench_accuracy,0.519,
792
- ≥4,7000,seedbench_seed_all,0.5559755419677599,
793
- ≥4,7000,textvqa_val_exact_match,0.55872,0.0067301301064875444
794
- ≥4,8000,ai2d_exact_match,0.4731217616580311,0.008986142019669732
795
- ≥4,8000,average,0.492078815307747,
796
- ≥4,8000,average_rank,3.5,
797
- ≥4,8000,chartqa_relaxed_overall,0.6676,0.009423354808471266
798
- ≥4,8000,docvqa_val_anls,0.6925495561792242,0.005900020554879468
799
- ≥4,8000,infovqa_val_anls,0.2810222429209379,0.007207972787105912
800
- ≥4,8000,mme_total_score,848.2908163265306,
801
- ≥4,8000,mmmu_val_mmmu_acc,0.31333,
802
- ≥4,8000,mmstar_average,0.350192703081569,
803
- ≥4,8000,ocrbench_ocrbench_accuracy,0.529,
804
- ≥4,8000,seedbench_seed_all,0.5595330739299611,
805
- ≥4,8000,textvqa_val_exact_match,0.56236,0.006739267736625781
806
- ≥4,9000,ai2d_exact_match,0.48737046632124353,0.0089962828388782
807
- ≥4,9000,average,0.49234565866208857,
808
- ≥4,9000,average_rank,4.1,
809
- ≥4,9000,chartqa_relaxed_overall,0.6608,0.009470650520873179
810
- ≥4,9000,docvqa_val_anls,0.6999407172900073,0.0058399608509493465
811
- ≥4,9000,infovqa_val_anls,0.28057597856713984,0.0072085582760555555
812
- ≥4,9000,mme_total_score,971.6003401360543,
813
- ≥4,9000,mmmu_val_mmmu_acc,0.28111,
814
- ≥4,9000,mmstar_average,0.3444424817337138,
815
- ≥4,9000,ocrbench_ocrbench_accuracy,0.545,
816
- ≥4,9000,seedbench_seed_all,0.5603112840466926,
817
- ≥4,9000,textvqa_val_exact_match,0.5715600000000001,0.006710949310502175
818
- ≥4,10000,ai2d_exact_match,0.5009715025906736,0.008999137132137068
819
- ≥4,10000,average,0.5030450627246211,
820
- ≥4,10000,average_rank,3.3,
821
- ≥4,10000,chartqa_relaxed_overall,0.666,0.009434680984649817
822
- ≥4,10000,docvqa_val_anls,0.7128440324276674,0.005793211438464534
823
- ≥4,10000,infovqa_val_anls,0.28379375750066616,0.007201019014370097
824
- ≥4,10000,mme_total_score,823.7772108843537,
825
- ≥4,10000,mmmu_val_mmmu_acc,0.30444,
826
- ≥4,10000,mmstar_average,0.35617504910097153,
827
- ≥4,10000,ocrbench_ocrbench_accuracy,0.563,
828
- ≥4,10000,seedbench_seed_all,0.562201222901612,
829
- ≥4,10000,textvqa_val_exact_match,0.57798,0.00669581889824864
830
- ≥4,11000,ai2d_exact_match,0.4899611398963731,0.008997340090107678
831
- ≥4,11000,average,0.5043945508574572,
832
- ≥4,11000,average_rank,3.7,
833
- ≥4,11000,chartqa_relaxed_overall,0.6684,0.009417645821601513
834
- ≥4,11000,docvqa_val_anls,0.718360308980877,0.00573640855634517
835
- ≥4,11000,infovqa_val_anls,0.3061911172660032,0.007586892248142986
836
- ≥4,11000,mme_total_score,913.9846938775511,
837
- ≥4,11000,mmmu_val_mmmu_acc,0.30444,
838
- ≥4,11000,mmstar_average,0.3441847617795319,
839
- ≥4,11000,ocrbench_ocrbench_accuracy,0.572,
840
- ≥4,11000,seedbench_seed_all,0.5605336297943302,
841
- ≥4,11000,textvqa_val_exact_match,0.5754799999999999,0.006700024775058468
842
- ≥4,12000,ai2d_exact_match,0.48737046632124353,0.0089962828388782
843
- ≥4,12000,average,0.5040020270755444,
844
- ≥4,12000,average_rank,3.7,
845
- ≥4,12000,chartqa_relaxed_overall,0.6708,0.009400334595970852
846
- ≥4,12000,docvqa_val_anls,0.7119962267424205,0.0057890771916119035
847
- ≥4,12000,infovqa_val_anls,0.29271378410211696,0.007308133874246768
848
- ≥4,12000,mme_total_score,857.7363945578231,
849
- ≥4,12000,mmmu_val_mmmu_acc,0.31333,
850
- ≥4,12000,mmstar_average,0.3366375608443022,
851
- ≥4,12000,ocrbench_ocrbench_accuracy,0.578,
852
- ≥4,12000,seedbench_seed_all,0.5663702056698166,
853
- ≥4,12000,textvqa_val_exact_match,0.5788,0.006686093984573812
854
- ≥4,13000,ai2d_exact_match,0.5029145077720207,0.008999001233939135
855
- ≥4,13000,average,0.5025324527027837,
856
- ≥4,13000,average_rank,3.8,
857
- ≥4,13000,chartqa_relaxed_overall,0.6736,0.009379787213112317
858
- ≥4,13000,docvqa_val_anls,0.7115068932890629,0.0057865061972425
859
- ≥4,13000,infovqa_val_anls,0.28657766964072817,0.007222563686487699
860
- ≥4,13000,mme_total_score,912.2363945578231,
861
- ≥4,13000,mmmu_val_mmmu_acc,0.30222,
862
- ≥4,13000,mmstar_average,0.35323329267271303,
863
- ≥4,13000,ocrbench_ocrbench_accuracy,0.548,
864
- ≥4,13000,seedbench_seed_all,0.5634797109505281,
865
- ≥4,13000,textvqa_val_exact_match,0.58126,0.006685319826323647
866
- ≥4,14000,ai2d_exact_match,0.5029145077720207,0.008999001233939133
867
- ≥4,14000,average,0.5048464815785578,
868
- ≥4,14000,average_rank,3.7,
869
- ≥4,14000,chartqa_relaxed_overall,0.6836,0.009303280948921504
870
- ≥4,14000,docvqa_val_anls,0.7158797575412708,0.005776895411277372
871
- ≥4,14000,infovqa_val_anls,0.2977244895971059,0.007409958547797003
872
- ≥4,14000,mme_total_score,863.687074829932,
873
- ≥4,14000,mmmu_val_mmmu_acc,0.30111,
874
- ≥4,14000,mmstar_average,0.33994823410485003,
875
- ≥4,14000,ocrbench_ocrbench_accuracy,0.562,
876
- ≥4,14000,seedbench_seed_all,0.5584213451917732,
877
- ≥4,14000,textvqa_val_exact_match,0.58202,0.0066807687023343965
878
- ≥4,15000,ai2d_exact_match,0.5123056994818653,0.008996428218289531
879
- ≥4,15000,average,0.5109092566320045,
880
- ≥4,15000,average_rank,3.5,
881
- ≥4,15000,chartqa_relaxed_overall,0.6712,0.009397422445513864
882
- ≥4,15000,docvqa_val_anls,0.7188356324043049,0.005760252125758746
883
- ≥4,15000,infovqa_val_anls,0.31301984081498224,0.007566633771439808
884
- ≥4,15000,mme_total_score,910.8588435374149,
885
- ≥4,15000,mmmu_val_mmmu_acc,0.31333,
886
- ≥4,15000,mmstar_average,0.3405171175316349,
887
- ≥4,15000,ocrbench_ocrbench_accuracy,0.57,
888
- ≥4,15000,seedbench_seed_all,0.5630350194552529,
889
- ≥4,15000,textvqa_val_exact_match,0.59594,0.006638698497713893
890
- ≥4,16000,ai2d_exact_match,0.5035621761658031,0.008998925734053562
891
- ≥4,16000,average,0.5129618260818141,
892
- ≥4,16000,average_rank,3.5,
893
- ≥4,16000,chartqa_relaxed_overall,0.6816,0.00931897598051042
894
- ≥4,16000,docvqa_val_anls,0.721094250093947,0.005753477697941139
895
- ≥4,16000,infovqa_val_anls,0.3169075222245947,0.007639057821423446
896
- ≥4,16000,mme_total_score,900.3299319727892,
897
- ≥4,16000,mmmu_val_mmmu_acc,0.30222,
898
- ≥4,16000,mmstar_average,0.34176931782507797,
899
- ≥4,16000,ocrbench_ocrbench_accuracy,0.588,
900
- ≥4,16000,seedbench_seed_all,0.5657031684269038,
901
- ≥4,16000,textvqa_val_exact_match,0.5958,0.006635034041762488
902
- ≥4,17000,ai2d_exact_match,0.49190414507772023,0.008997974381217109
903
- ≥4,17000,average,0.5093728538878098,
904
- ≥4,17000,average_rank,3.7,
905
- ≥4,17000,chartqa_relaxed_overall,0.68,0.009331389496316869
906
- ≥4,17000,docvqa_val_anls,0.7210491309814,0.005753367994292813
907
- ≥4,17000,infovqa_val_anls,0.3201561983029552,0.007662267005009952
908
- ≥4,17000,mme_total_score,877.8401360544218,
909
- ≥4,17000,mmmu_val_mmmu_acc,0.30778,
910
- ≥4,17000,mmstar_average,0.3348906353085911,
911
- ≥4,17000,ocrbench_ocrbench_accuracy,0.573,
912
- ≥4,17000,seedbench_seed_all,0.564035575319622,
913
- ≥4,17000,textvqa_val_exact_match,0.59154,0.006655985735352941
914
- ≥4,18000,ai2d_exact_match,0.49028497409326427,0.008997455247470554
915
- ≥4,18000,average,0.5099416307525485,
916
- ≥4,18000,average_rank,3.7,
917
- ≥4,18000,chartqa_relaxed_overall,0.6788,0.00934061683451043
918
- ≥4,18000,docvqa_val_anls,0.7282528158071215,0.00570007403218014
919
- ≥4,18000,infovqa_val_anls,0.3087200968720397,0.007513490264469946
920
- ≥4,18000,mme_total_score,929.9506802721088,
921
- ≥4,18000,mmmu_val_mmmu_acc,0.30111,
922
- ≥4,18000,mmstar_average,0.342890936748704,
923
- ≥4,18000,ocrbench_ocrbench_accuracy,0.585,
924
- ≥4,18000,seedbench_seed_all,0.5645358532518066,
925
- ≥4,18000,textvqa_val_exact_match,0.5898800000000001,0.006662761859703513
926
- ≥4,19000,ai2d_exact_match,0.49417098445595853,0.008998542562369278
927
- ≥4,19000,average,0.5124245876024062,
928
- ≥4,19000,average_rank,3.7,
929
- ≥4,19000,chartqa_relaxed_overall,0.6752,0.00936787525721462
930
- ≥4,19000,docvqa_val_anls,0.7321651331177514,0.005674418458926489
931
- ≥4,19000,infovqa_val_anls,0.3128382816486564,0.007545062449451713
932
- ≥4,19000,mme_total_score,920.5612244897959,
933
- ≥4,19000,mmmu_val_mmmu_acc,0.31444,
934
- ≥4,19000,mmstar_average,0.3381960053749425,
935
- ≥4,19000,ocrbench_ocrbench_accuracy,0.581,
936
- ≥4,19000,seedbench_seed_all,0.5635908838243469,
937
- ≥4,19000,textvqa_val_exact_match,0.60022,0.0066236821295251325
938
- ≥4,20000,ai2d_exact_match,0.4993523316062176,0.008999146569435543
939
- ≥4,20000,average,0.5097536365259775,
940
- ≥4,20000,average_rank,2.9,
941
- ≥4,20000,chartqa_relaxed_overall,0.6788,0.00934061683451043
942
- ≥4,20000,docvqa_val_anls,0.7257805691640822,0.005714530309266441
943
- ≥4,20000,infovqa_val_anls,0.3115295213783156,0.007581035362425172
944
- ≥4,20000,mme_total_score,936.8911564625851,
945
- ≥4,20000,mmmu_val_mmmu_acc,0.29333,
946
- ≥4,20000,mmstar_average,0.342179144828651,
947
- ≥4,20000,ocrbench_ocrbench_accuracy,0.572,
948
- ≥4,20000,seedbench_seed_all,0.5640911617565314,
949
- ≥4,20000,textvqa_val_exact_match,0.6007199999999999,0.00662859592800733
950
- ≥5,1000,ai2d_exact_match,0.46275906735751293,0.008974157783087492
951
- ≥5,1000,average,0.46601067306382465,
952
- ≥5,1000,average_rank,4.3,
953
- ≥5,1000,chartqa_relaxed_overall,0.586,0.009852940280589808
954
- ≥5,1000,docvqa_val_anls,0.6587979311295683,0.006033428065938081
955
- ≥5,1000,infovqa_val_anls,0.26573226652787757,0.007027770857338852
956
- ≥5,1000,mme_total_score,1141.8704481792718,
957
- ≥5,1000,mmmu_val_mmmu_acc,0.29111,
958
- ≥5,1000,mmstar_average,0.3326633517590184,
959
- ≥5,1000,ocrbench_ocrbench_accuracy,0.512,
960
- ≥5,1000,seedbench_seed_all,0.5481934408004447,
961
- ≥5,1000,textvqa_val_exact_match,0.53684,0.0067933638823904985
962
- ≥5,2000,ai2d_exact_match,0.46729274611398963,0.008979879527453428
963
- ≥5,2000,average,0.46843615619784085,
964
- ≥5,2000,average_rank,4.5,
965
- ≥5,2000,chartqa_relaxed_overall,0.6232,0.009693621125059844
966
- ≥5,2000,docvqa_val_anls,0.6576303662245503,0.0060380542666198
967
- ≥5,2000,infovqa_val_anls,0.2544768002153279,0.006980921578600097
968
- ≥5,2000,mme_total_score,1121.454081632653,
969
- ≥5,2000,mmmu_val_mmmu_acc,0.28333,
970
- ≥5,2000,mmstar_average,0.3471972386408189,
971
- ≥5,2000,ocrbench_ocrbench_accuracy,0.517,
972
- ≥5,2000,seedbench_seed_all,0.544858254585881,
973
- ≥5,2000,textvqa_val_exact_match,0.52094,0.006790900275023118
974
- ≥5,3000,ai2d_exact_match,0.405440414507772,0.00883675667187808
975
- ≥5,3000,average,0.46118026257153605,
976
- ≥5,3000,average_rank,4.2,
977
- ≥5,3000,chartqa_relaxed_overall,0.6156,0.009731008838409575
978
- ≥5,3000,docvqa_val_anls,0.6431483265654762,0.0060571462869005105
979
- ≥5,3000,infovqa_val_anls,0.25688718356638174,0.007171420821325129
980
- ≥5,3000,mme_total_score,1082.7074829931973,
981
- ≥5,3000,mmmu_val_mmmu_acc,0.29778,
982
- ≥5,3000,mmstar_average,0.3516979671312099,
983
- ≥5,3000,ocrbench_ocrbench_accuracy,0.521,
984
- ≥5,3000,seedbench_seed_all,0.547248471372985,
985
- ≥5,3000,textvqa_val_exact_match,0.51182,0.006815757362882421
986
- ≥5,4000,ai2d_exact_match,0.4491580310880829,0.008952509302111547
987
- ≥5,4000,average,0.4646276743863569,
988
- ≥5,4000,average_rank,4.7,
989
- ≥5,4000,chartqa_relaxed_overall,0.626,0.009679208378267924
990
- ≥5,4000,docvqa_val_anls,0.6457409563970327,0.006096190550822001
991
- ≥5,4000,infovqa_val_anls,0.2657314142312884,0.007188343779485259
992
- ≥5,4000,mme_total_score,1068.4183673469388,
993
- ≥5,4000,mmmu_val_mmmu_acc,0.30333,
994
- ≥5,4000,mmstar_average,0.33033606075691685,
995
- ≥5,4000,ocrbench_ocrbench_accuracy,0.501,
996
- ≥5,4000,seedbench_seed_all,0.546692607003891,
997
- ≥5,4000,textvqa_val_exact_match,0.5136599999999999,0.006800789000270868
998
- ≥5,5000,ai2d_exact_match,0.4630829015544041,0.008974591204222938
999
- ≥5,5000,average,0.47175640838182836,
1000
- ≥5,5000,average_rank,4.3,
1001
- ≥5,5000,chartqa_relaxed_overall,0.6016,0.009793331391099473
1002
- ≥5,5000,docvqa_val_anls,0.6583943642704193,0.006028435004183156
1003
- ≥5,5000,infovqa_val_anls,0.28445442343834715,0.007395809557151278
1004
- ≥5,5000,mme_total_score,1063.6232492997199,
1005
- ≥5,5000,mmmu_val_mmmu_acc,0.30111,
1006
- ≥5,5000,mmstar_average,0.34898828745177285,
1007
- ≥5,5000,ocrbench_ocrbench_accuracy,0.524,
1008
- ≥5,5000,seedbench_seed_all,0.5438576987215119,
1009
- ≥5,5000,textvqa_val_exact_match,0.52032,0.006801255099919928
1010
- ≥5,6000,ai2d_exact_match,0.41936528497409326,0.008881358943343104
1011
- ≥5,6000,average,0.4607787848869989,
1012
- ≥5,6000,average_rank,4.3,
1013
- ≥5,6000,chartqa_relaxed_overall,0.5688,0.009906860368095493
1014
- ≥5,6000,docvqa_val_anls,0.6530464526768891,0.006064278476677726
1015
- ≥5,6000,infovqa_val_anls,0.2838075612518576,0.007411753553258339
1016
- ≥5,6000,mme_total_score,1102.3075230092036,
1017
- ≥5,6000,mmmu_val_mmmu_acc,0.30222,
1018
- ≥5,6000,mmstar_average,0.3384709546298998,
1019
- ≥5,6000,ocrbench_ocrbench_accuracy,0.514,
1020
- ≥5,6000,seedbench_seed_all,0.5458588104502501,
1021
- ≥5,6000,textvqa_val_exact_match,0.52144,0.006795447071398616
1022
- ≥5,7000,ai2d_exact_match,0.44689119170984454,0.008948245073044946
1023
- ≥5,7000,average,0.46361553646961884,
1024
- ≥5,7000,average_rank,4.8,
1025
- ≥5,7000,chartqa_relaxed_overall,0.596,0.009815912634917984
1026
- ≥5,7000,docvqa_val_anls,0.6473018376832792,0.00607167873881633
1027
- ≥5,7000,infovqa_val_anls,0.2701993608610082,0.007205660851186524
1028
- ≥5,7000,mme_total_score,1018.4163665466186,
1029
- ≥5,7000,mmmu_val_mmmu_acc,0.30556,
1030
- ≥5,7000,mmstar_average,0.33545236293074815,
1031
- ≥5,7000,ocrbench_ocrbench_accuracy,0.512,
1032
- ≥5,7000,seedbench_seed_all,0.5431350750416898,
1033
- ≥5,7000,textvqa_val_exact_match,0.516,0.006822412261202951
1034
- ≥5,8000,ai2d_exact_match,0.4488341968911917,0.008951911635408226
1035
- ≥5,8000,average,0.4668616879585074,
1036
- ≥5,8000,average_rank,4.6,
1037
- ≥5,8000,chartqa_relaxed_overall,0.6072,0.00976941352263433
1038
- ≥5,8000,docvqa_val_anls,0.6519934800658986,0.006080604378776126
1039
- ≥5,8000,infovqa_val_anls,0.2785842294592336,0.0074156607313128845
1040
- ≥5,8000,mme_total_score,1057.0833333333333,
1041
- ≥5,8000,mmmu_val_mmmu_acc,0.30333,
1042
- ≥5,8000,mmstar_average,0.3378731184509322,
1043
- ≥5,8000,ocrbench_ocrbench_accuracy,0.518,
1044
- ≥5,8000,seedbench_seed_all,0.5403001667593107,
1045
- ≥5,8000,textvqa_val_exact_match,0.51564,0.006799847473666819
1046
- ≥5,9000,ai2d_exact_match,0.39345854922279794,0.008792480650628204
1047
- ≥5,9000,average,0.459912532971243,
1048
- ≥5,9000,average_rank,4.4,
1049
- ≥5,9000,chartqa_relaxed_overall,0.6084,0.00976411343463736
1050
- ≥5,9000,docvqa_val_anls,0.6541887939771373,0.006063084097609983
1051
- ≥5,9000,infovqa_val_anls,0.27276949319611876,0.007319733478874126
1052
- ≥5,9000,mme_total_score,1123.0184073629453,
1053
- ≥5,9000,mmmu_val_mmmu_acc,0.32333,
1054
- ≥5,9000,mmstar_average,0.3247860715180074,
1055
- ≥5,9000,ocrbench_ocrbench_accuracy,0.509,
1056
- ≥5,9000,seedbench_seed_all,0.5397998888271262,
1057
- ≥5,9000,textvqa_val_exact_match,0.51348,0.006813467735926963
1058
- ≥5,10000,ai2d_exact_match,0.4326424870466321,0.008917121282993509
1059
- ≥5,10000,average,0.46134428795967075,
1060
- ≥5,10000,average_rank,4.9,
1061
- ≥5,10000,chartqa_relaxed_overall,0.6072,0.00976941352263433
1062
- ≥5,10000,docvqa_val_anls,0.651687815510166,0.006071913532526164
1063
- ≥5,10000,infovqa_val_anls,0.27997237091892013,0.007395864137910542
1064
- ≥5,10000,mme_total_score,1022.3228291316527,
1065
- ≥5,10000,mmmu_val_mmmu_acc,0.28889,
1066
- ≥5,10000,mmstar_average,0.329809486810568,
1067
- ≥5,10000,ocrbench_ocrbench_accuracy,0.511,
1068
- ≥5,10000,seedbench_seed_all,0.5375764313507504,
1069
- ≥5,10000,textvqa_val_exact_match,0.51332,0.006823388252580171
1070
- ≥5,11000,ai2d_exact_match,0.4268134715025907,0.008902228386480452
1071
- ≥5,11000,average,0.46104097512732234,
1072
- ≥5,11000,average_rank,4.5,
1073
- ≥5,11000,chartqa_relaxed_overall,0.6012,0.0097949885513097
1074
- ≥5,11000,docvqa_val_anls,0.644837445168982,0.006085623472495874
1075
- ≥5,11000,infovqa_val_anls,0.2640855729780956,0.007198720155523597
1076
- ≥5,11000,mme_total_score,1039.019507803121,
1077
- ≥5,11000,mmmu_val_mmmu_acc,0.30889,
1078
- ≥5,11000,mmstar_average,0.3483796516991238,
1079
- ≥5,11000,ocrbench_ocrbench_accuracy,0.509,
1080
- ≥5,11000,seedbench_seed_all,0.5367426347971095,
1081
- ≥5,11000,textvqa_val_exact_match,0.50942,0.00682319308775463
1082
- ≥5,12000,ai2d_exact_match,0.3944300518134715,0.008796275864065532
1083
- ≥5,12000,average,0.4536626915651331,
1084
- ≥5,12000,average_rank,4.5,
1085
- ≥5,12000,chartqa_relaxed_overall,0.5772,0.009882060820012199
1086
- ≥5,12000,docvqa_val_anls,0.6559090016447592,0.00604562177320508
1087
- ≥5,12000,infovqa_val_anls,0.2673016323091914,0.0072722156919221015
1088
- ≥5,12000,mme_total_score,1023.3735494197679,
1089
- ≥5,12000,mmmu_val_mmmu_acc,0.31778,
1090
- ≥5,12000,mmstar_average,0.3313831269791424,
1091
- ≥5,12000,ocrbench_ocrbench_accuracy,0.505,
1092
- ≥5,12000,seedbench_seed_all,0.5327404113396331,
1093
- ≥5,12000,textvqa_val_exact_match,0.50122,0.006832030272732221
1094
- ≥5,13000,ai2d_exact_match,0.40867875647668395,0.00884778289870742
1095
- ≥5,13000,average,0.45776989353761316,
1096
- ≥5,13000,average_rank,4.6,
1097
- ≥5,13000,chartqa_relaxed_overall,0.5908,0.009835692163550793
1098
- ≥5,13000,docvqa_val_anls,0.6503688245286325,0.0060676446684505315
1099
- ≥5,13000,infovqa_val_anls,0.2636657235502622,0.007162177374827191
1100
- ≥5,13000,mme_total_score,1002.4256702681073,
1101
- ≥5,13000,mmmu_val_mmmu_acc,0.31556,
1102
- ≥5,13000,mmstar_average,0.3443129801956691,
1103
- ≥5,13000,ocrbench_ocrbench_accuracy,0.512,
1104
- ≥5,13000,seedbench_seed_all,0.5329627570872707,
1105
- ≥5,13000,textvqa_val_exact_match,0.50158,0.006823401826251807
1106
- ≥5,14000,ai2d_exact_match,0.41483160621761656,0.008867639612484149
1107
- ≥5,14000,average,0.45268439675941724,
1108
- ≥5,14000,average_rank,4.8,
1109
- ≥5,14000,chartqa_relaxed_overall,0.588,0.009845871036662436
1110
- ≥5,14000,docvqa_val_anls,0.6498549577427524,0.006073551423686328
1111
- ≥5,14000,infovqa_val_anls,0.2661623211050356,0.00731739457874179
1112
- ≥5,14000,mme_total_score,1034.9393757503,
1113
- ≥5,14000,mmmu_val_mmmu_acc,0.3,
1114
- ≥5,14000,mmstar_average,0.3342054606442816,
1115
- ≥5,14000,ocrbench_ocrbench_accuracy,0.494,
1116
- ≥5,14000,seedbench_seed_all,0.5294052251250695,
1117
- ≥5,14000,textvqa_val_exact_match,0.4977,0.006830920457365827
1118
- ≥5,15000,ai2d_exact_match,0.42001295336787564,0.008883255931688048
1119
- ≥5,15000,average,0.4570450291018434,
1120
- ≥5,15000,average_rank,4.9,
1121
- ≥5,15000,chartqa_relaxed_overall,0.59,0.009838634025503496
1122
- ≥5,15000,docvqa_val_anls,0.6475057079650752,0.006081599544786637
1123
- ≥5,15000,infovqa_val_anls,0.26732840510253686,0.007267222145742162
1124
- ≥5,15000,mme_total_score,1033.4811924769908,
1125
- ≥5,15000,mmmu_val_mmmu_acc,0.30667,
1126
- ≥5,15000,mmstar_average,0.33017343172346,
1127
- ≥5,15000,ocrbench_ocrbench_accuracy,0.516,
1128
- ≥5,15000,seedbench_seed_all,0.5345747637576431,
1129
- ≥5,15000,textvqa_val_exact_match,0.5011399999999999,0.006833438318727342
1130
- ≥5,16000,ai2d_exact_match,0.41353626943005184,0.008863577928878446
1131
- ≥5,16000,average,0.45298319741394405,
1132
- ≥5,16000,average_rank,4.9,
1133
- ≥5,16000,chartqa_relaxed_overall,0.5928,0.00982821965366181
1134
- ≥5,16000,docvqa_val_anls,0.6444827949953511,0.006083163064354419
1135
- ≥5,16000,infovqa_val_anls,0.27176255535031313,0.0073933278275316846
1136
- ≥5,16000,mme_total_score,1004.6780712284915,
1137
- ≥5,16000,mmmu_val_mmmu_acc,0.30111,
1138
- ≥5,16000,mmstar_average,0.32864449435945237,
1139
- ≥5,16000,ocrbench_ocrbench_accuracy,0.502,
1140
- ≥5,16000,seedbench_seed_all,0.526792662590328,
1141
- ≥5,16000,textvqa_val_exact_match,0.49572000000000005,0.006835033273947625
1142
- ≥5,17000,ai2d_exact_match,0.4112694300518135,0.008856317823411107
1143
- ≥5,17000,average,0.4529560838437233,
1144
- ≥5,17000,average_rank,4.6,
1145
- ≥5,17000,chartqa_relaxed_overall,0.5876,0.009847298295140926
1146
- ≥5,17000,docvqa_val_anls,0.6389774022522821,0.00612389508858012
1147
- ≥5,17000,infovqa_val_anls,0.2806511079053113,0.007508796510654168
1148
- ≥5,17000,mme_total_score,995.327831132453,
1149
- ≥5,17000,mmmu_val_mmmu_acc,0.31333,
1150
- ≥5,17000,mmstar_average,0.33458844306670454,
1151
- ≥5,17000,ocrbench_ocrbench_accuracy,0.496,
1152
- ≥5,17000,seedbench_seed_all,0.5230683713173986,
1153
- ≥5,17000,textvqa_val_exact_match,0.49112,0.006832742230852753
1154
- ≥5,18000,ai2d_exact_match,0.41936528497409326,0.008881358943343104
1155
- ≥5,18000,average,0.4506952703715631,
1156
- ≥5,18000,average_rank,4.6,
1157
- ≥5,18000,chartqa_relaxed_overall,0.5752,0.009888230116554488
1158
- ≥5,18000,docvqa_val_anls,0.6393690836463973,0.006115883377355433
1159
- ≥5,18000,infovqa_val_anls,0.26588334023973736,0.007337010225614936
1160
- ≥5,18000,mme_total_score,989.2097839135654,
1161
- ≥5,18000,mmmu_val_mmmu_acc,0.31333,
1162
- ≥5,18000,mmstar_average,0.32322974671841465,
1163
- ≥5,18000,ocrbench_ocrbench_accuracy,0.498,
1164
- ≥5,18000,seedbench_seed_all,0.5279599777654252,
1165
- ≥5,18000,textvqa_val_exact_match,0.49391999999999997,0.006830895911063903
1166
- ≥5,19000,ai2d_exact_match,0.3954015544041451,0.008800034697838395
1167
- ≥5,19000,average,0.44423744725800945,
1168
- ≥5,19000,average_rank,4.9,
1169
- ≥5,19000,chartqa_relaxed_overall,0.5744,0.009890651444389179
1170
- ≥5,19000,docvqa_val_anls,0.6275859067200067,0.006146304949422434
1171
- ≥5,19000,infovqa_val_anls,0.27001013621966435,0.00741081345045112
1172
- ≥5,19000,mme_total_score,1012.671468587435,
1173
- ≥5,19000,mmmu_val_mmmu_acc,0.30222,
1174
- ≥5,19000,mmstar_average,0.33172139573813564,
1175
- ≥5,19000,ocrbench_ocrbench_accuracy,0.489,
1176
- ≥5,19000,seedbench_seed_all,0.5244580322401334,
1177
- ≥5,19000,textvqa_val_exact_match,0.48334000000000005,0.006839754771120511
1178
- ≥5,20000,ai2d_exact_match,0.3950777202072539,0.00879878579254534
1179
- ≥5,20000,average,0.44700580037620813,
1180
- ≥5,20000,average_rank,3.8,
1181
- ≥5,20000,chartqa_relaxed_overall,0.5824,0.009865243291986469
1182
- ≥5,20000,docvqa_val_anls,0.635044358086249,0.006123826440768213
1183
- ≥5,20000,infovqa_val_anls,0.2648967410637257,0.0073547743128100345
1184
- ≥5,20000,mme_total_score,1015.2638055222089,
1185
- ≥5,20000,mmmu_val_mmmu_acc,0.31111,
1186
- ≥5,20000,mmstar_average,0.33540590765288064,
1187
- ≥5,20000,ocrbench_ocrbench_accuracy,0.485,
1188
- ≥5,20000,seedbench_seed_all,0.5234574763757643,
1189
- ≥5,20000,textvqa_val_exact_match,0.49065999999999993,0.0068247980522276805
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca22654a0302da0ca335420b0a89cd770cea560b11f2a9f9f25927877d7ed231
3
+ size 61626
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/content/assets/data/ss_vs_s1.csv CHANGED
@@ -1,481 +1,3 @@
1
- run,step,metric,value,stderr
2
- Single Stage,1000,ai2d_exact_match,0.2548575129533679,0.007843322436924496
3
- Single Stage,1000,average,0.27120689295763617,
4
- Single Stage,1000,average_rank,2.0,
5
- Single Stage,1000,chartqa_relaxed_overall,0.3308,0.009411906161401973
6
- Single Stage,1000,docvqa_val_anls,0.3528553494243383,0.005852289239342309
7
- Single Stage,1000,infovqa_val_anls,0.17320578642581314,0.006297063452679795
8
- Single Stage,1000,mme_total_score,977.4280712284914,
9
- Single Stage,1000,mmmu_val_mmmu_acc,0.25222,
10
- Single Stage,1000,mmstar_average,0.23215874078908072,
11
- Single Stage,1000,ocrbench_ocrbench_accuracy,0.286,
12
- Single Stage,1000,seedbench_seed_all,0.2563646470261256,
13
- Single Stage,1000,textvqa_val_exact_match,0.3024,0.00628900296642181
14
- Single Stage,2000,ai2d_exact_match,0.26295336787564766,0.007923526907377255
15
- Single Stage,2000,average,0.3202068275596269,
16
- Single Stage,2000,average_rank,1.8,
17
- Single Stage,2000,chartqa_relaxed_overall,0.4688,0.009982508912777261
18
- Single Stage,2000,docvqa_val_anls,0.4452261510942785,0.00614755494712251
19
- Single Stage,2000,infovqa_val_anls,0.1820547866557169,0.006217861455795791
20
- Single Stage,2000,mme_total_score,1049.3036214485794,
21
- Single Stage,2000,mmmu_val_mmmu_acc,0.24556,
22
- Single Stage,2000,mmstar_average,0.21305462434540698,
23
- Single Stage,2000,ocrbench_ocrbench_accuracy,0.395,
24
- Single Stage,2000,seedbench_seed_all,0.258532518065592,
25
- Single Stage,2000,textvqa_val_exact_match,0.41068000000000005,0.006697862330024289
26
- Single Stage,3000,ai2d_exact_match,0.25226683937823835,0.007816909588794397
27
- Single Stage,3000,average,0.3507423834414229,
28
- Single Stage,3000,average_rank,1.7,
29
- Single Stage,3000,chartqa_relaxed_overall,0.5028,0.010001843767601082
30
- Single Stage,3000,docvqa_val_anls,0.502653993831009,0.006267072346683124
31
- Single Stage,3000,infovqa_val_anls,0.21728617578189535,0.006796941784959762
32
- Single Stage,3000,mme_total_score,1170.2383953581434,
33
- Single Stage,3000,mmmu_val_mmmu_acc,0.27556,
34
- Single Stage,3000,mmstar_average,0.25432376938577683,
35
- Single Stage,3000,ocrbench_ocrbench_accuracy,0.436,
36
- Single Stage,3000,seedbench_seed_all,0.2792106725958866,
37
- Single Stage,3000,textvqa_val_exact_match,0.43658,0.006766885462882726
38
- Single Stage,4000,ai2d_exact_match,0.2645725388601036,0.007939149662089447
39
- Single Stage,4000,average,0.36961781722974835,
40
- Single Stage,4000,average_rank,1.8,
41
- Single Stage,4000,chartqa_relaxed_overall,0.5312,0.009982508912777261
42
- Single Stage,4000,docvqa_val_anls,0.5374434618615119,0.0062905728113059655
43
- Single Stage,4000,infovqa_val_anls,0.2287924838861707,0.006994568698639919
44
- Single Stage,4000,mme_total_score,1155.203781512605,
45
- Single Stage,4000,mmmu_val_mmmu_acc,0.25556,
46
- Single Stage,4000,mmstar_average,0.2575590188757354,
47
- Single Stage,4000,ocrbench_ocrbench_accuracy,0.453,
48
- Single Stage,4000,seedbench_seed_all,0.33913285158421347,
49
- Single Stage,4000,textvqa_val_exact_match,0.4593,0.006791695475025738
50
- Single Stage,5000,ai2d_exact_match,0.3125,0.008342439145556371
51
- Single Stage,5000,average,0.3974627910380972,
52
- Single Stage,5000,average_rank,1.8,
53
- Single Stage,5000,chartqa_relaxed_overall,0.5488,0.00995424828018316
54
- Single Stage,5000,docvqa_val_anls,0.552360266782429,0.006300308519952055
55
- Single Stage,5000,infovqa_val_anls,0.23425555286643698,0.007002254622066442
56
- Single Stage,5000,mme_total_score,1181.4653861544618,
57
- Single Stage,5000,mmmu_val_mmmu_acc,0.26667,
58
- Single Stage,5000,mmstar_average,0.29596648146165705,
59
- Single Stage,5000,ocrbench_ocrbench_accuracy,0.462,
60
- Single Stage,5000,seedbench_seed_all,0.43107281823235133,
61
- Single Stage,5000,textvqa_val_exact_match,0.47354000000000007,0.0068172185364497985
62
- Single Stage,6000,ai2d_exact_match,0.358160621761658,0.008629463221867162
63
- Single Stage,6000,average,0.4161227404571003,
64
- Single Stage,6000,average_rank,1.6,
65
- Single Stage,6000,chartqa_relaxed_overall,0.5628,0.00992279440175477
66
- Single Stage,6000,docvqa_val_anls,0.5747451497228876,0.00625495440870239
67
- Single Stage,6000,infovqa_val_anls,0.22152017368968838,0.006604546680525351
68
- Single Stage,6000,mme_total_score,1284.1648659463785,
69
- Single Stage,6000,mmmu_val_mmmu_acc,0.27111,
70
- Single Stage,6000,mmstar_average,0.2978489412854164,
71
- Single Stage,6000,ocrbench_ocrbench_accuracy,0.495,
72
- Single Stage,6000,seedbench_seed_all,0.4795997776542524,
73
- Single Stage,6000,textvqa_val_exact_match,0.48432,0.006800535050670284
74
- Single Stage,7000,ai2d_exact_match,0.3707901554404145,0.00869347755587734
75
- Single Stage,7000,average,0.4291083177345374,
76
- Single Stage,7000,average_rank,1.6,
77
- Single Stage,7000,chartqa_relaxed_overall,0.5656,0.009915542506251351
78
- Single Stage,7000,docvqa_val_anls,0.5940907049431567,0.006224236305767187
79
- Single Stage,7000,infovqa_val_anls,0.2515675215816963,0.007105097396092786
80
- Single Stage,7000,mme_total_score,1185.875650260104,
81
- Single Stage,7000,mmmu_val_mmmu_acc,0.26556,
82
- Single Stage,7000,mmstar_average,0.31372400960777047,
83
- Single Stage,7000,ocrbench_ocrbench_accuracy,0.504,
84
- Single Stage,7000,seedbench_seed_all,0.4964424680377988,
85
- Single Stage,7000,textvqa_val_exact_match,0.5002,0.006794794025220267
86
- Single Stage,8000,ai2d_exact_match,0.37759067357512954,0.008725299846043883
87
- Single Stage,8000,average,0.43846759477995995,
88
- Single Stage,8000,average_rank,1.5,
89
- Single Stage,8000,chartqa_relaxed_overall,0.5832,0.009862556058385773
90
- Single Stage,8000,docvqa_val_anls,0.6017336419437208,0.006231612198089698
91
- Single Stage,8000,infovqa_val_anls,0.2449256624147254,0.006992518502948913
92
- Single Stage,8000,mme_total_score,1199.2409963985594,
93
- Single Stage,8000,mmmu_val_mmmu_acc,0.28111,
94
- Single Stage,8000,mmstar_average,0.33512257186205047,
95
- Single Stage,8000,ocrbench_ocrbench_accuracy,0.51,
96
- Single Stage,8000,seedbench_seed_all,0.5024458032240133,
97
- Single Stage,8000,textvqa_val_exact_match,0.51008,0.006796301690135059
98
- Single Stage,9000,ai2d_exact_match,0.4067357512953368,0.008841214921078996
99
- Single Stage,9000,average,0.4422510732201056,
100
- Single Stage,9000,average_rank,1.6,
101
- Single Stage,9000,chartqa_relaxed_overall,0.5912,0.009834211136815875
102
- Single Stage,9000,docvqa_val_anls,0.6170968481662739,0.00617235763542544
103
- Single Stage,9000,infovqa_val_anls,0.23537031288570615,0.00670318154156447
104
- Single Stage,9000,mme_total_score,1231.5195078031213,
105
- Single Stage,9000,mmmu_val_mmmu_acc,0.25889,
106
- Single Stage,9000,mmstar_average,0.3216444898242951,
107
- Single Stage,9000,ocrbench_ocrbench_accuracy,0.515,
108
- Single Stage,9000,seedbench_seed_all,0.5120622568093385,
109
- Single Stage,9000,textvqa_val_exact_match,0.52226,0.006792711289708482
110
- Single Stage,10000,ai2d_exact_match,0.39993523316062174,0.008817096257082848
111
- Single Stage,10000,average,0.4523875703250908,
112
- Single Stage,10000,average_rank,1.3,
113
- Single Stage,10000,chartqa_relaxed_overall,0.5996,0.00980154906867574
114
- Single Stage,10000,docvqa_val_anls,0.6262613496433054,0.006147756371688175
115
- Single Stage,10000,infovqa_val_anls,0.263290074230132,0.007186788766942786
116
- Single Stage,10000,mme_total_score,1240.8218287314926,
117
- Single Stage,10000,mmmu_val_mmmu_acc,0.28778,
118
- Single Stage,10000,mmstar_average,0.32972717906018517,
119
- Single Stage,10000,ocrbench_ocrbench_accuracy,0.517,
120
- Single Stage,10000,seedbench_seed_all,0.5217342968315731,
121
- Single Stage,10000,textvqa_val_exact_match,0.5261600000000001,0.006785774843600811
122
- Single Stage,11000,ai2d_exact_match,0.422279792746114,0.008889771831066474
123
- Single Stage,11000,average,0.4561398159525099,
124
- Single Stage,11000,average_rank,1.2,
125
- Single Stage,11000,chartqa_relaxed_overall,0.6104,0.009755142291143075
126
- Single Stage,11000,docvqa_val_anls,0.6373130149166712,0.006128022584995044
127
- Single Stage,11000,infovqa_val_anls,0.24419378339723755,0.006897644885887063
128
- Single Stage,11000,mme_total_score,1322.9488795518205,
129
- Single Stage,11000,mmmu_val_mmmu_acc,0.27778,
130
- Single Stage,11000,mmstar_average,0.3298563439522548,
131
- Single Stage,11000,ocrbench_ocrbench_accuracy,0.521,
132
- Single Stage,11000,seedbench_seed_all,0.5237354085603113,
133
- Single Stage,11000,textvqa_val_exact_match,0.5387,0.006770851562852138
134
- Single Stage,12000,ai2d_exact_match,0.42001295336787564,0.008883255931688034
135
- Single Stage,12000,average,0.4582751140055433,
136
- Single Stage,12000,average_rank,1.4,
137
- Single Stage,12000,chartqa_relaxed_overall,0.618,0.009719474639861454
138
- Single Stage,12000,docvqa_val_anls,0.6393961983751871,0.0061228747388476674
139
- Single Stage,12000,infovqa_val_anls,0.24798874058574302,0.006855374548993139
140
- Single Stage,12000,mme_total_score,1225.6453581432572,
141
- Single Stage,12000,mmmu_val_mmmu_acc,0.27889,
142
- Single Stage,12000,mmstar_average,0.34010867846816534,
143
- Single Stage,12000,ocrbench_ocrbench_accuracy,0.512,
144
- Single Stage,12000,seedbench_seed_all,0.5350194552529183,
145
- Single Stage,12000,textvqa_val_exact_match,0.5330600000000001,0.006777713092109446
146
- Single Stage,13000,ai2d_exact_match,0.4375,0.008928571428571428
147
- Single Stage,13000,average,0.4692868662590049,
148
- Single Stage,13000,average_rank,1.2,
149
- Single Stage,13000,chartqa_relaxed_overall,0.6148,0.00973479791861169
150
- Single Stage,13000,docvqa_val_anls,0.6511374872549951,0.006086953065248391
151
- Single Stage,13000,infovqa_val_anls,0.24465055100441893,0.006808432538374664
152
- Single Stage,13000,mme_total_score,1281.7122849139657,
153
- Single Stage,13000,mmmu_val_mmmu_acc,0.28222,
154
- Single Stage,13000,mmstar_average,0.3453069542917521,
155
- Single Stage,13000,ocrbench_ocrbench_accuracy,0.549,
156
- Single Stage,13000,seedbench_seed_all,0.5442468037798777,
157
- Single Stage,13000,textvqa_val_exact_match,0.55472,0.0067416788982325
158
- Single Stage,14000,ai2d_exact_match,0.4572538860103627,0.00896620675297095
159
- Single Stage,14000,average,0.47352486841689195,
160
- Single Stage,14000,average_rank,1.4,
161
- Single Stage,14000,chartqa_relaxed_overall,0.6172,0.009723347231923635
162
- Single Stage,14000,docvqa_val_anls,0.6502269393708169,0.006057950730638126
163
- Single Stage,14000,infovqa_val_anls,0.25805460837190913,0.007037735231659539
164
- Single Stage,14000,mme_total_score,1309.1444577831132,
165
- Single Stage,14000,mmmu_val_mmmu_acc,0.28111,
166
- Single Stage,14000,mmstar_average,0.34575818188776586,
167
- Single Stage,14000,ocrbench_ocrbench_accuracy,0.551,
168
- Single Stage,14000,seedbench_seed_all,0.5483602001111729,
169
- Single Stage,14000,textvqa_val_exact_match,0.55276,0.006751206724612103
170
- Single Stage,15000,ai2d_exact_match,0.45045336787564766,0.008954861634252399
171
- Single Stage,15000,average,0.47878665012878824,
172
- Single Stage,15000,average_rank,1.2,
173
- Single Stage,15000,chartqa_relaxed_overall,0.612,0.009747841205275417
174
- Single Stage,15000,docvqa_val_anls,0.6621413031955148,0.006056838050222495
175
- Single Stage,15000,infovqa_val_anls,0.2706898598157733,0.007200315730154543
176
- Single Stage,15000,mme_total_score,1384.2171868747498,
177
- Single Stage,15000,mmmu_val_mmmu_acc,0.30222,
178
- Single Stage,15000,mmstar_average,0.35408135695920684,
179
- Single Stage,15000,ocrbench_ocrbench_accuracy,0.558,
180
- Single Stage,15000,seedbench_seed_all,0.5411339633129516,
181
- Single Stage,15000,textvqa_val_exact_match,0.5583600000000001,0.0067279027203879065
182
- Single Stage,16000,ai2d_exact_match,0.45077720207253885,0.008955440137395838
183
- Single Stage,16000,average,0.47665128022935843,
184
- Single Stage,16000,average_rank,1.3,
185
- Single Stage,16000,chartqa_relaxed_overall,0.632,0.00964715642305132
186
- Single Stage,16000,docvqa_val_anls,0.6709415729142987,0.005999818105621502
187
- Single Stage,16000,infovqa_val_anls,0.26050032542402035,0.006997451875879188
188
- Single Stage,16000,mme_total_score,1317.8491396558625,
189
- Single Stage,16000,mmmu_val_mmmu_acc,0.27556,
190
- Single Stage,16000,mmstar_average,0.33214333327093315,
191
- Single Stage,16000,ocrbench_ocrbench_accuracy,0.56,
192
- Single Stage,16000,seedbench_seed_all,0.5463590883824346,
193
- Single Stage,16000,textvqa_val_exact_match,0.56158,0.006723854754867398
194
- Single Stage,17000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
195
- Single Stage,17000,average,0.4777141780162423,
196
- Single Stage,17000,average_rank,1.3,
197
- Single Stage,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
198
- Single Stage,17000,docvqa_val_anls,0.6796338519136422,0.005948761388267941
199
- Single Stage,17000,infovqa_val_anls,0.28070956072505215,0.007298333094144192
200
- Single Stage,17000,mme_total_score,1381.9161664665867,
201
- Single Stage,17000,mmmu_val_mmmu_acc,0.27667,
202
- Single Stage,17000,mmstar_average,0.3370289492329521,
203
- Single Stage,17000,ocrbench_ocrbench_accuracy,0.519,
204
- Single Stage,17000,seedbench_seed_all,0.5510283490828238,
205
- Single Stage,17000,textvqa_val_exact_match,0.56416,0.006724830373229479
206
- Single Stage,18000,ai2d_exact_match,0.46567357512953367,0.008977921602780726
207
- Single Stage,18000,average,0.4819834595278701,
208
- Single Stage,18000,average_rank,1.3,
209
- Single Stage,18000,chartqa_relaxed_overall,0.6376,0.009615793331418735
210
- Single Stage,18000,docvqa_val_anls,0.6775884603912571,0.005972234236435759
211
- Single Stage,18000,infovqa_val_anls,0.27154318420389256,0.007164903131667027
212
- Single Stage,18000,mme_total_score,1336.922769107643,
213
- Single Stage,18000,mmmu_val_mmmu_acc,0.28667,
214
- Single Stage,18000,mmstar_average,0.34482796716566916,
215
- Single Stage,18000,ocrbench_ocrbench_accuracy,0.533,
216
- Single Stage,18000,seedbench_seed_all,0.5543079488604781,
217
- Single Stage,18000,textvqa_val_exact_match,0.5666399999999999,0.006713392287599574
218
- Single Stage,19000,ai2d_exact_match,0.4682642487046632,0.008981008686994101
219
- Single Stage,19000,average,0.4899006713916878,
220
- Single Stage,19000,average_rank,1.1,
221
- Single Stage,19000,chartqa_relaxed_overall,0.6444,0.009575809858898698
222
- Single Stage,19000,docvqa_val_anls,0.678226526479947,0.005970619221588814
223
- Single Stage,19000,infovqa_val_anls,0.26993847247278,0.0071348470764911525
224
- Single Stage,19000,mme_total_score,1406.6628651460583,
225
- Single Stage,19000,mmmu_val_mmmu_acc,0.28333,
226
- Single Stage,19000,mmstar_average,0.356220913822775,
227
- Single Stage,19000,ocrbench_ocrbench_accuracy,0.577,
228
- Single Stage,19000,seedbench_seed_all,0.554585881045025,
229
- Single Stage,19000,textvqa_val_exact_match,0.57714,0.0066918487914812905
230
- Single Stage,20000,ai2d_exact_match,0.47571243523316065,0.00898853090258662
231
- Single Stage,20000,average,0.4873169067639118,
232
- Single Stage,20000,average_rank,1.2,
233
- Single Stage,20000,chartqa_relaxed_overall,0.6336,0.009638338810708618
234
- Single Stage,20000,docvqa_val_anls,0.6895214454380043,0.005896462073053767
235
- Single Stage,20000,infovqa_val_anls,0.2655657550458317,0.007033265532032538
236
- Single Stage,20000,mme_total_score,1324.6738695478193,
237
- Single Stage,20000,mmmu_val_mmmu_acc,0.30111,
238
- Single Stage,20000,mmstar_average,0.33806766134497995,
239
- Single Stage,20000,ocrbench_ocrbench_accuracy,0.555,
240
- Single Stage,20000,seedbench_seed_all,0.5587548638132296,
241
- Single Stage,20000,textvqa_val_exact_match,0.56852,0.006720151338087659
242
- Two Stage,1000,ai2d_exact_match,0.25906735751295334,0.007885466610693084
243
- Two Stage,1000,average,0.31368848609084204,
244
- Two Stage,1000,average_rank,1.0,
245
- Two Stage,1000,chartqa_relaxed_overall,0.4436,0.009938164963872337
246
- Two Stage,1000,docvqa_val_anls,0.42857906272393714,0.00617017051120098
247
- Two Stage,1000,infovqa_val_anls,0.19144447578161194,0.006593728313201272
248
- Two Stage,1000,mme_total_score,998.7869147659063,
249
- Two Stage,1000,mmmu_val_mmmu_acc,0.25889,
250
- Two Stage,1000,mmstar_average,0.2467637945300377,
251
- Two Stage,1000,ocrbench_ocrbench_accuracy,0.368,
252
- Two Stage,1000,seedbench_seed_all,0.25703168426903833,
253
- Two Stage,1000,textvqa_val_exact_match,0.36982,0.006597131039140386
254
- Two Stage,2000,ai2d_exact_match,0.26327720207253885,0.007926662492947052
255
- Two Stage,2000,average,0.3358130433652279,
256
- Two Stage,2000,average_rank,1.2,
257
- Two Stage,2000,chartqa_relaxed_overall,0.4992,0.010001987797631107
258
- Two Stage,2000,docvqa_val_anls,0.4932752040405314,0.006286364089099095
259
- Two Stage,2000,infovqa_val_anls,0.19095428252193772,0.006391194919224349
260
- Two Stage,2000,mme_total_score,1062.8957583033214,
261
- Two Stage,2000,mmmu_val_mmmu_acc,0.23333,
262
- Two Stage,2000,mmstar_average,0.22051867830573926,
263
- Two Stage,2000,ocrbench_ocrbench_accuracy,0.435,
264
- Two Stage,2000,seedbench_seed_all,0.2556420233463035,
265
- Two Stage,2000,textvqa_val_exact_match,0.43112,0.006756288819146318
266
- Two Stage,3000,ai2d_exact_match,0.2655440414507772,0.007948457289013515
267
- Two Stage,3000,average,0.3636919255920759,
268
- Two Stage,3000,average_rank,1.3,
269
- Two Stage,3000,chartqa_relaxed_overall,0.5348,0.009977745545085072
270
- Two Stage,3000,docvqa_val_anls,0.5283823835512687,0.006261305725762883
271
- Two Stage,3000,infovqa_val_anls,0.2064005153919739,0.00660395026420985
272
- Two Stage,3000,mme_total_score,1152.5195078031213,
273
- Two Stage,3000,mmmu_val_mmmu_acc,0.26667,
274
- Two Stage,3000,mmstar_average,0.26072557614922737,
275
- Two Stage,3000,ocrbench_ocrbench_accuracy,0.455,
276
- Two Stage,3000,seedbench_seed_all,0.29666481378543635,
277
- Two Stage,3000,textvqa_val_exact_match,0.45903999999999995,0.006792178031860127
278
- Two Stage,4000,ai2d_exact_match,0.30343264248704666,0.008274550183857863
279
- Two Stage,4000,average,0.386738207804619,
280
- Two Stage,4000,average_rank,1.2,
281
- Two Stage,4000,chartqa_relaxed_overall,0.5464,0.00995883966107287
282
- Two Stage,4000,docvqa_val_anls,0.5513347609587042,0.006295149714671814
283
- Two Stage,4000,infovqa_val_anls,0.209061566918142,0.006630816594060217
284
- Two Stage,4000,mme_total_score,1092.9095638255303,
285
- Two Stage,4000,mmmu_val_mmmu_acc,0.26889,
286
- Two Stage,4000,mmstar_average,0.26686799048357046,
287
- Two Stage,4000,ocrbench_ocrbench_accuracy,0.477,
288
- Two Stage,4000,seedbench_seed_all,0.38643690939410785,
289
- Two Stage,4000,textvqa_val_exact_match,0.47121999999999997,0.006809171409434235
290
- Two Stage,5000,ai2d_exact_match,0.34617875647668395,0.008562713351618975
291
- Two Stage,5000,average,0.41048271276999254,
292
- Two Stage,5000,average_rank,1.2,
293
- Two Stage,5000,chartqa_relaxed_overall,0.5568,0.009937253322797029
294
- Two Stage,5000,docvqa_val_anls,0.5616928036954175,0.006281333847375657
295
- Two Stage,5000,infovqa_val_anls,0.21417615930558564,0.006470237976804916
296
- Two Stage,5000,mme_total_score,1113.2024809923969,
297
- Two Stage,5000,mmmu_val_mmmu_acc,0.28889,
298
- Two Stage,5000,mmstar_average,0.3048769900603613,
299
- Two Stage,5000,ocrbench_ocrbench_accuracy,0.501,
300
- Two Stage,5000,seedbench_seed_all,0.4454697053918844,
301
- Two Stage,5000,textvqa_val_exact_match,0.47525999999999996,0.006811465752181289
302
- Two Stage,6000,ai2d_exact_match,0.3853626943005181,0.008759432661868542
303
- Two Stage,6000,average,0.4256324408073156,
304
- Two Stage,6000,average_rank,1.4,
305
- Two Stage,6000,chartqa_relaxed_overall,0.574,0.009891852177211218
306
- Two Stage,6000,docvqa_val_anls,0.5959624206334873,0.006223948314975518
307
- Two Stage,6000,infovqa_val_anls,0.21910870056052556,0.00650522330852698
308
- Two Stage,6000,mme_total_score,1166.5228091236495,
309
- Two Stage,6000,mmmu_val_mmmu_acc,0.28333,
310
- Two Stage,6000,mmstar_average,0.28797389940888596,
311
- Two Stage,6000,ocrbench_ocrbench_accuracy,0.512,
312
- Two Stage,6000,seedbench_seed_all,0.4776542523624236,
313
- Two Stage,6000,textvqa_val_exact_match,0.4953,0.006792791061270795
314
- Two Stage,7000,ai2d_exact_match,0.3915155440414508,0.008784780895708935
315
- Two Stage,7000,average,0.4301306852910006,
316
- Two Stage,7000,average_rank,1.4,
317
- Two Stage,7000,chartqa_relaxed_overall,0.5776,0.009880807059104824
318
- Two Stage,7000,docvqa_val_anls,0.5986163103423551,0.0062031909815058375
319
- Two Stage,7000,infovqa_val_anls,0.22133856274121264,0.006604073748499083
320
- Two Stage,7000,mme_total_score,1191.3954581832734,
321
- Two Stage,7000,mmmu_val_mmmu_acc,0.28667,
322
- Two Stage,7000,mmstar_average,0.2999043663917079,
323
- Two Stage,7000,ocrbench_ocrbench_accuracy,0.501,
324
- Two Stage,7000,seedbench_seed_all,0.48449138410227904,
325
- Two Stage,7000,textvqa_val_exact_match,0.51004,0.006807782962299279
326
- Two Stage,8000,ai2d_exact_match,0.4106217616580311,0.008854207883828033
327
- Two Stage,8000,average,0.4460743520389214,
328
- Two Stage,8000,average_rank,1.5,
329
- Two Stage,8000,chartqa_relaxed_overall,0.6044,0.009781540134915584
330
- Two Stage,8000,docvqa_val_anls,0.6026263625222106,0.006221681650022778
331
- Two Stage,8000,infovqa_val_anls,0.25653488200256863,0.007114496312902602
332
- Two Stage,8000,mme_total_score,1122.452581032413,
333
- Two Stage,8000,mmmu_val_mmmu_acc,0.30556,
334
- Two Stage,8000,mmstar_average,0.3287554228678711,
335
- Two Stage,8000,ocrbench_ocrbench_accuracy,0.502,
336
- Two Stage,8000,seedbench_seed_all,0.4953307392996109,
337
- Two Stage,8000,textvqa_val_exact_match,0.5088400000000001,0.006790286627123755
338
- Two Stage,9000,ai2d_exact_match,0.40900259067357514,0.00884886365109852
339
- Two Stage,9000,average,0.4448373661618862,
340
- Two Stage,9000,average_rank,1.4,
341
- Two Stage,9000,chartqa_relaxed_overall,0.602,0.00979166741164548
342
- Two Stage,9000,docvqa_val_anls,0.6230206474600885,0.006150742264825986
343
- Two Stage,9000,infovqa_val_anls,0.22695214706156083,0.0066522293148095326
344
- Two Stage,9000,mme_total_score,1123.2771108443376,
345
- Two Stage,9000,mmmu_val_mmmu_acc,0.28444,
346
- Two Stage,9000,mmstar_average,0.31337399530900006,
347
- Two Stage,9000,ocrbench_ocrbench_accuracy,0.516,
348
- Two Stage,9000,seedbench_seed_all,0.5044469149527515,
349
- Two Stage,9000,textvqa_val_exact_match,0.5243,0.006775919466531711
350
- Two Stage,10000,ai2d_exact_match,0.4167746113989637,0.008873613803189363
351
- Two Stage,10000,average,0.45019708387432694,
352
- Two Stage,10000,average_rank,1.7,
353
- Two Stage,10000,chartqa_relaxed_overall,0.6008,0.00979663889573671
354
- Two Stage,10000,docvqa_val_anls,0.625559493523932,0.006163808988970625
355
- Two Stage,10000,infovqa_val_anls,0.2484394159425024,0.006960467307383163
356
- Two Stage,10000,mme_total_score,1175.7940176070429,
357
- Two Stage,10000,mmmu_val_mmmu_acc,0.28444,
358
- Two Stage,10000,mmstar_average,0.3201372990396749,
359
- Two Stage,10000,ocrbench_ocrbench_accuracy,0.523,
360
- Two Stage,10000,seedbench_seed_all,0.5092829349638688,
361
- Two Stage,10000,textvqa_val_exact_match,0.52334,0.006775531746371587
362
- Two Stage,11000,ai2d_exact_match,0.4219559585492228,0.008888852746011196
363
- Two Stage,11000,average,0.4544831873326875,
364
- Two Stage,11000,average_rank,1.8,
365
- Two Stage,11000,chartqa_relaxed_overall,0.6128,0.009744149186940382
366
- Two Stage,11000,docvqa_val_anls,0.6332812103643084,0.006140691371662128
367
- Two Stage,11000,infovqa_val_anls,0.23863681037743975,0.006726839163261667
368
- Two Stage,11000,mme_total_score,1205.7752100840335,
369
- Two Stage,11000,mmmu_val_mmmu_acc,0.27667,
370
- Two Stage,11000,mmstar_average,0.3207287756303977,
371
- Two Stage,11000,ocrbench_ocrbench_accuracy,0.542,
372
- Two Stage,11000,seedbench_seed_all,0.5166759310728183,
373
- Two Stage,11000,textvqa_val_exact_match,0.5276,0.006779501480792346
374
- Two Stage,12000,ai2d_exact_match,0.43005181347150256,0.00891065778843896
375
- Two Stage,12000,average,0.4603231834457321,
376
- Two Stage,12000,average_rank,1.6,
377
- Two Stage,12000,chartqa_relaxed_overall,0.612,0.009747841205275417
378
- Two Stage,12000,docvqa_val_anls,0.6395985301346107,0.006113052714689484
379
- Two Stage,12000,infovqa_val_anls,0.2439170659215255,0.006865310277271596
380
- Two Stage,12000,mme_total_score,1157.484293717487,
381
- Two Stage,12000,mmmu_val_mmmu_acc,0.29556,
382
- Two Stage,12000,mmstar_average,0.33444157500257155,
383
- Two Stage,12000,ocrbench_ocrbench_accuracy,0.539,
384
- Two Stage,12000,seedbench_seed_all,0.5193996664813786,
385
- Two Stage,12000,textvqa_val_exact_match,0.52894,0.006785904875622425
386
- Two Stage,13000,ai2d_exact_match,0.4339378238341969,0.00892025987527176
387
- Two Stage,13000,average,0.46490664749620997,
388
- Two Stage,13000,average_rank,1.8,
389
- Two Stage,13000,chartqa_relaxed_overall,0.6224,0.009697675699134625
390
- Two Stage,13000,docvqa_val_anls,0.6462803017356844,0.0061027748005307945
391
- Two Stage,13000,infovqa_val_anls,0.24426636134362278,0.006797247018813037
392
- Two Stage,13000,mme_total_score,1191.0042016806724,
393
- Two Stage,13000,mmmu_val_mmmu_acc,0.3,
394
- Two Stage,13000,mmstar_average,0.33993002648901727,
395
- Two Stage,13000,ocrbench_ocrbench_accuracy,0.545,
396
- Two Stage,13000,seedbench_seed_all,0.5175653140633686,
397
- Two Stage,13000,textvqa_val_exact_match,0.5347799999999999,0.0067635803775740536
398
- Two Stage,14000,ai2d_exact_match,0.44332901554404147,0.008941163900483138
399
- Two Stage,14000,average,0.47155104399726233,
400
- Two Stage,14000,average_rank,1.6,
401
- Two Stage,14000,chartqa_relaxed_overall,0.6268,0.009675026948726469
402
- Two Stage,14000,docvqa_val_anls,0.6586021078894133,0.006060927182389954
403
- Two Stage,14000,infovqa_val_anls,0.2553127836308732,0.0069494972189920795
404
- Two Stage,14000,mme_total_score,1219.156662665066,
405
- Two Stage,14000,mmmu_val_mmmu_acc,0.30444,
406
- Two Stage,14000,mmstar_average,0.32252187023399065,
407
- Two Stage,14000,ocrbench_ocrbench_accuracy,0.564,
408
- Two Stage,14000,seedbench_seed_all,0.5245136186770428,
409
- Two Stage,14000,textvqa_val_exact_match,0.54444,0.006760159556655915
410
- Two Stage,15000,ai2d_exact_match,0.44527202072538863,0.008945084019331405
411
- Two Stage,15000,average,0.47506404899487137,
412
- Two Stage,15000,average_rank,1.8,
413
- Two Stage,15000,chartqa_relaxed_overall,0.628,0.009668701749325345
414
- Two Stage,15000,docvqa_val_anls,0.6614266719753668,0.006055793707421594
415
- Two Stage,15000,infovqa_val_anls,0.25669760055121127,0.006992050333066725
416
- Two Stage,15000,mme_total_score,1198.7210884353742,
417
- Two Stage,15000,mmmu_val_mmmu_acc,0.31222,
418
- Two Stage,15000,mmstar_average,0.34599838005318234,
419
- Two Stage,15000,ocrbench_ocrbench_accuracy,0.553,
420
- Two Stage,15000,seedbench_seed_all,0.5271817676486937,
421
- Two Stage,15000,textvqa_val_exact_match,0.5457799999999999,0.006751174267547695
422
- Two Stage,16000,ai2d_exact_match,0.452720207253886,0.008958830742136086
423
- Two Stage,16000,average,0.4756900312291722,
424
- Two Stage,16000,average_rank,1.7,
425
- Two Stage,16000,chartqa_relaxed_overall,0.6228,0.009695651925812239
426
- Two Stage,16000,docvqa_val_anls,0.6636227651335681,0.006049765989250173
427
- Two Stage,16000,infovqa_val_anls,0.2545981800588258,0.0069034382302033005
428
- Two Stage,16000,mme_total_score,1211.0271108443376,
429
- Two Stage,16000,mmmu_val_mmmu_acc,0.30778,
430
- Two Stage,16000,mmstar_average,0.3441840591332238,
431
- Two Stage,16000,ocrbench_ocrbench_accuracy,0.558,
432
- Two Stage,16000,seedbench_seed_all,0.5251250694830462,
433
- Two Stage,16000,textvqa_val_exact_match,0.55238,0.006735691577574321
434
- Two Stage,17000,ai2d_exact_match,0.45142487046632124,0.008956585653027465
435
- Two Stage,17000,average,0.478877157951835,
436
- Two Stage,17000,average_rank,1.7,
437
- Two Stage,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
438
- Two Stage,17000,docvqa_val_anls,0.6682822523143818,0.006027291004964481
439
- Two Stage,17000,infovqa_val_anls,0.2566899031113292,0.006984361605936137
440
- Two Stage,17000,mme_total_score,1157.7550020008005,
441
- Two Stage,17000,mmmu_val_mmmu_acc,0.31556,
442
- Two Stage,17000,mmstar_average,0.3413821094043331,
443
- Two Stage,17000,ocrbench_ocrbench_accuracy,0.563,
444
- Two Stage,17000,seedbench_seed_all,0.5275152862701501,
445
- Two Stage,17000,textvqa_val_exact_match,0.55404,0.006743665997528143
446
- Two Stage,18000,ai2d_exact_match,0.45077720207253885,0.008955440137395842
447
- Two Stage,18000,average,0.48011960096968553,
448
- Two Stage,18000,average_rank,1.7,
449
- Two Stage,18000,chartqa_relaxed_overall,0.6324,0.00964496273307725
450
- Two Stage,18000,docvqa_val_anls,0.6669938909662756,0.006030949772272312
451
- Two Stage,18000,infovqa_val_anls,0.26114082779542375,0.006997258882360672
452
- Two Stage,18000,mme_total_score,1199.3700480192078,
453
- Two Stage,18000,mmmu_val_mmmu_acc,0.30222,
454
- Two Stage,18000,mmstar_average,0.34746272024423847,
455
- Two Stage,18000,ocrbench_ocrbench_accuracy,0.579,
456
- Two Stage,18000,seedbench_seed_all,0.5271817676486937,
457
- Two Stage,18000,textvqa_val_exact_match,0.5539,0.0067478933611137175
458
- Two Stage,19000,ai2d_exact_match,0.44559585492227977,0.00894572391435784
459
- Two Stage,19000,average,0.48026929849849115,
460
- Two Stage,19000,average_rank,1.9,
461
- Two Stage,19000,chartqa_relaxed_overall,0.6372,0.00961808021316077
462
- Two Stage,19000,docvqa_val_anls,0.6688318561206944,0.006022351017420005
463
- Two Stage,19000,infovqa_val_anls,0.2646354907091152,0.007027671735260141
464
- Two Stage,19000,mme_total_score,1170.1806722689075,
465
- Two Stage,19000,mmmu_val_mmmu_acc,0.29778,
466
- Two Stage,19000,mmstar_average,0.35086201891999,
467
- Two Stage,19000,ocrbench_ocrbench_accuracy,0.574,
468
- Two Stage,19000,seedbench_seed_all,0.5292384658143413,
469
- Two Stage,19000,textvqa_val_exact_match,0.55428,0.006746127657232224
470
- Two Stage,20000,ai2d_exact_match,0.44721502590673573,0.008948865761421001
471
- Two Stage,20000,average,0.4807284005437735,
472
- Two Stage,20000,average_rank,1.8,
473
- Two Stage,20000,chartqa_relaxed_overall,0.632,0.00964715642305132
474
- Two Stage,20000,docvqa_val_anls,0.6696120046502304,0.0060246464192922275
475
- Two Stage,20000,infovqa_val_anls,0.2643335615077466,0.007024758501317731
476
- Two Stage,20000,mme_total_score,1187.4589835934376,
477
- Two Stage,20000,mmmu_val_mmmu_acc,0.29778,
478
- Two Stage,20000,mmstar_average,0.34891710287927624,
479
- Two Stage,20000,ocrbench_ocrbench_accuracy,0.582,
480
- Two Stage,20000,seedbench_seed_all,0.5282379099499722,
481
- Two Stage,20000,textvqa_val_exact_match,0.5564600000000001,0.006728915911338792
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f076631fcad76129ed8cab03c72a61965b465e1f3e7fa8dc68b7c7a9275616b
3
+ size 28041
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/env.d.ts CHANGED
@@ -1 +1,13 @@
1
- /// <reference path="../.astro/types.d.ts" />
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ /// <reference path="../.astro/types.d.ts" />
2
+ /// <reference types="astro/client" />
3
+ /// <reference types="vite/client" />
4
+
5
+ interface ImportMetaEnv {
6
+ readonly PUBLIC_TABLE_OF_CONTENT_AUTO_COLLAPSE?: string | boolean;
7
+ // Back-compat
8
+ readonly PUBLIC_TOC_AUTO_COLLAPSE?: string | boolean;
9
+ }
10
+
11
+ interface ImportMeta {
12
+ readonly env: ImportMetaEnv;
13
+ }
app/src/pages/index.astro CHANGED
@@ -4,6 +4,7 @@ import Hero from '../components/Hero.astro';
4
  import Footer from '../components/Footer.astro';
5
  import ThemeToggle from '../components/ThemeToggle.astro';
6
  import Seo from '../components/Seo.astro';
 
7
  // Default OG image served from public/
8
  const ogDefaultUrl = '/thumb.jpg';
9
  import 'katex/dist/katex.min.css';
@@ -17,11 +18,78 @@ const docTitleHtml = (articleFM?.title ?? 'Untitled article')
17
  .replace(/\n/g, '<br/>');
18
  const subtitle = articleFM?.subtitle ?? '';
19
  const description = articleFM?.description ?? '';
20
- const authors = articleFM?.authors ?? [];
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  const published = articleFM?.published ?? undefined;
22
  const tags = articleFM?.tags ?? [];
23
- // Prefer ogImage from frontmatter if provided
24
- const fmOg = articleFM?.ogImage as string | undefined;
25
  const imageAbs: string = fmOg && fmOg.startsWith('http')
26
  ? fmOg
27
  : (Astro.site ? new URL((fmOg ?? ogDefaultUrl), Astro.site).toString() : (fmOg ?? ogDefaultUrl));
@@ -42,20 +110,27 @@ const extractYear = (val: string | undefined): number | undefined => {
42
  };
43
 
44
  const year = extractYear(published);
45
- const citationAuthorsText = authors.join(', ');
46
  const citationText = `${citationAuthorsText}${year ? ` (${year})` : ''}. "${titleFlat}".`;
47
 
48
- const authorsBib = authors.join(' and ');
49
- const keyAuthor = (authors[0] || 'article').split(/\s+/).slice(-1)[0].toLowerCase();
50
  const keyTitle = titleFlat.toLowerCase().replace(/[^a-z0-9]+/g, '_').replace(/^_|_$/g, '').slice(0, 24);
51
  const bibKey = `${keyAuthor}${year ?? ''}_${keyTitle}`;
52
- const bibtex = `@misc{${bibKey},\n title={${titleFlat}},\n author={${authorsBib}},\n ${year ? `year={${year}}` : ''}\n}`;
 
 
 
 
 
 
 
53
  ---
54
- <html lang="en" data-theme="light">
55
  <head>
56
  <meta charset="utf-8" />
57
  <meta name="viewport" content="width=device-width, initial-scale=1" />
58
- <Seo title={docTitle} description={description} authors={authors} published={published} tags={tags} image={imageAbs} />
59
  <script is:inline>
60
  (() => {
61
  try {
@@ -66,215 +141,27 @@ const bibtex = `@misc{${bibKey},\n title={${titleFlat}},\n author={${authorsBi
66
  } catch {}
67
  })();
68
  </script>
 
69
 
70
  <!-- TO MANAGE PROPERLY -->
71
  <script src="https://cdn.plot.ly/plotly-3.0.0.min.js" charset="utf-8"></script>
72
  <script src="https://cdn.jsdelivr.net/npm/d3@7/dist/d3.min.js"></script>
73
- <script type="module" src="https://gradio.s3-us-west-2.amazonaws.com/4.4.0/gradio.js"> </script>
 
74
  </head>
75
  <body>
76
  <ThemeToggle />
77
- <Hero title={docTitleHtml} titleRaw={docTitle} description={subtitle} authors={articleFM?.authors} affiliation={articleFM?.affiliation} published={articleFM?.published} />
78
 
79
  <section class="content-grid">
80
- <aside class="toc">
81
- <div class="title">Table of Contents</div>
82
- <div id="article-toc-placeholder"></div>
83
- </aside>
84
- <details class="toc-mobile">
85
- <summary>Table of Contents</summary>
86
- <div id="article-toc-mobile-placeholder"></div>
87
- </details>
88
  <main>
89
  <Article />
90
- <style is:inline>
91
- /* Inline tweak for details blocks used in MDX */
92
- details { background: var(--code-bg) !important; border: 1px solid var(--border-color) !important; border-radius: 6px; margin: 1em 0; padding: .5em .75em; }
93
- </style>
94
  </main>
95
  </section>
96
 
97
- <Footer citationText={citationText} bibtex={bibtex} />
98
-
99
- <!-- Medium-like image zoom (lightbox) -->
100
- <script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/medium-zoom.min.js"></script>
101
- <script>
102
- // Initialize zoom on img[data-zoomable]; wait for script & content; close on scroll like Medium
103
- (() => {
104
- /** @type {any} */
105
- let zoomInstance = null;
106
-
107
- /** @param {() => void} cb */
108
- const ensureMediumZoomReady = (cb) => {
109
- // @ts-ignore mediumZoom injected globally by external script
110
- if (window.mediumZoom) return cb();
111
- // @ts-ignore mediumZoom injected globally by external script
112
- const retry = () => (window.mediumZoom ? cb() : setTimeout(retry, 30));
113
- retry();
114
- };
115
-
116
- /** @returns {HTMLElement[]} */
117
- const collectTargets = () => Array.from(document.querySelectorAll('section.content-grid main img[data-zoomable]'));
118
-
119
- const initOrUpdateZoom = () => {
120
- const isDark = document.documentElement.getAttribute('data-theme') === 'dark';
121
- const background = isDark ? 'rgba(0,0,0,.9)' : 'rgba(0,0,0,.85)';
122
- const targets = collectTargets();
123
- if (!targets.length) return;
124
-
125
- if (!zoomInstance) {
126
- // @ts-ignore medium-zoom injected globally by external script
127
- zoomInstance = window.mediumZoom(targets, { background, margin: 24, scrollOffset: 0 });
128
-
129
- let onScrollLike;
130
- const attachCloseOnScroll = () => {
131
- if (onScrollLike) return;
132
- // @ts-ignore medium-zoom instance has close()
133
- onScrollLike = () => { zoomInstance && zoomInstance.close(); };
134
- window.addEventListener('wheel', onScrollLike, { passive: true });
135
- window.addEventListener('touchmove', onScrollLike, { passive: true });
136
- window.addEventListener('scroll', onScrollLike, { passive: true });
137
- };
138
- const detachCloseOnScroll = () => {
139
- if (!onScrollLike) return;
140
- window.removeEventListener('wheel', onScrollLike);
141
- window.removeEventListener('touchmove', onScrollLike);
142
- window.removeEventListener('scroll', onScrollLike);
143
- onScrollLike = null;
144
- };
145
- // @ts-ignore medium-zoom instance has on()
146
- zoomInstance.on('open', attachCloseOnScroll);
147
- // @ts-ignore medium-zoom instance has on()
148
- zoomInstance.on('close', detachCloseOnScroll);
149
-
150
- const themeObserver = new MutationObserver(() => {
151
- const dark = document.documentElement.getAttribute('data-theme') === 'dark';
152
- // @ts-ignore medium-zoom instance has update()
153
- zoomInstance && zoomInstance.update({ background: dark ? 'rgba(0,0,0,.9)' : 'rgba(0,0,0,.85)' });
154
- });
155
- themeObserver.observe(document.documentElement, { attributes: true, attributeFilter: ['data-theme'] });
156
- } else {
157
- // @ts-ignore medium-zoom instance has attach()/update()
158
- zoomInstance.attach(targets);
159
- // @ts-ignore medium-zoom instance has update()
160
- zoomInstance.update({ background });
161
- }
162
- };
163
-
164
- const bootstrap = () => ensureMediumZoomReady(() => {
165
- initOrUpdateZoom();
166
- setTimeout(initOrUpdateZoom, 0);
167
- const main = document.querySelector('section.content-grid main');
168
- if (main) {
169
- const mo = new MutationObserver(() => initOrUpdateZoom());
170
- mo.observe(main, { childList: true, subtree: true });
171
- }
172
- });
173
-
174
- if (document.readyState === 'complete') bootstrap();
175
- else window.addEventListener('load', bootstrap, { once: true });
176
- })();
177
- </script>
178
-
179
-
180
- <script>
181
- // Add a small download button to img[data-downloadable]
182
- (() => {
183
- const SELECTOR = 'section.content-grid main img[data-downloadable]';
184
-
185
- /**
186
- * @param {HTMLImageElement} img
187
- */
188
- const injectDownloadButton = (img) => {
189
- if (!img || img.dataset.__dlInjected) return;
190
- const parentFigure = img.closest('figure');
191
- const parent = img.parentElement;
192
- if (!parent) return;
193
- img.dataset.__dlInjected = '1';
194
-
195
- // Wrap the image in a positioned inline-block so the button is on the image
196
- const wrapper = document.createElement('span');
197
- wrapper.className = 'img-dl-wrap';
198
- parent.insertBefore(wrapper, img);
199
- wrapper.appendChild(img);
200
- if (parentFigure && !parentFigure.classList.contains('has-dl-btn')) {
201
- parentFigure.classList.add('has-dl-btn');
202
- }
203
-
204
- // Determine download href and filename
205
- const pickHrefAndName = () => {
206
- const current = img.currentSrc || img.src || '';
207
- let href = img.getAttribute('data-download-src') || current;
208
- // Derive filename from the original source when possible
209
- const deriveName = () => {
210
- try {
211
- const u = new URL(current, location.href);
212
- // Prefer original href param if provided by Astro image service
213
- const rawHref = u.searchParams.get('href');
214
- const candidate = rawHref ? decodeURIComponent(rawHref) : u.pathname;
215
- const last = String(candidate).split('/').pop() || '';
216
- // Strip query/hash and any appended transform suffixes after extension
217
- const base = last.split('?')[0].split('#')[0];
218
- const m = base.match(/^(.+?\.(?:png|jpe?g|webp|avif|gif|svg))(?:[._-].*)?$/i);
219
- if (m && m[1]) return m[1];
220
- // If extension missing, fallback to base as-is
221
- return base || 'image';
222
- } catch {
223
- return 'image';
224
- }
225
- };
226
- const name = img.getAttribute('data-download-name') || deriveName();
227
- return { href, name };
228
- };
229
 
230
- const { href, name } = pickHrefAndName();
231
- const a = document.createElement('a');
232
- a.className = 'button button--ghost img-dl-btn';
233
- a.href = href;
234
- if (name) a.download = name;
235
- a.setAttribute('aria-label', 'Download image');
236
- a.setAttribute('title', name ? `Download ${name}` : 'Download image');
237
- a.innerHTML = '<svg viewBox="0 0 24 24" aria-hidden="true" focusable="false"><path d="M12 16c-.26 0-.52-.11-.71-.29l-5-5a1 1 0 0 1 1.42-1.42L11 12.59V4a1 1 0 1 1 2 0v8.59l3.29-3.3a1 1 0 1 1 1.42 1.42l-5 5c-.19.18-.45.29-.71.29zM5 20a1 1 0 1 1 0-2h14a1 1 0 1 1 0 2H5z"/></svg>';
238
-
239
- // Ensure href/name match currentSrc right before navigation
240
- a.addEventListener('click', async (ev) => {
241
- try {
242
- ev.preventDefault();
243
- const picked = pickHrefAndName();
244
- const res = await fetch(picked.href, { credentials: 'same-origin' });
245
- const blob = await res.blob();
246
- const objectUrl = URL.createObjectURL(blob);
247
- const tmp = document.createElement('a');
248
- tmp.href = objectUrl;
249
- tmp.download = picked.name || 'image';
250
- document.body.appendChild(tmp);
251
- tmp.click();
252
- setTimeout(() => { URL.revokeObjectURL(objectUrl); tmp.remove(); }, 1000);
253
- } catch {
254
- // Fallback to native behavior if fetch fails
255
- }
256
- });
257
-
258
- // Append inside wrapper so positioning is relative to the image box
259
- wrapper.appendChild(a);
260
- };
261
-
262
- const scan = () => {
263
- document.querySelectorAll(SELECTOR).forEach((el) => injectDownloadButton(el));
264
- };
265
-
266
- const bootstrap = () => {
267
- scan();
268
- const main = document.querySelector('section.content-grid main');
269
- if (!main) return;
270
- const mo = new MutationObserver(() => scan());
271
- mo.observe(main, { childList: true, subtree: true, attributes: true, attributeFilter: ['src'] });
272
- };
273
-
274
- if (document.readyState === 'complete') bootstrap();
275
- else window.addEventListener('load', bootstrap, { once: true });
276
- })();
277
- </script>
278
 
279
  <script>
280
  // Open external links in a new tab; keep internal anchors in-page
@@ -320,119 +207,7 @@ const bibtex = `@misc{${bibKey},\n title={${titleFlat}},\n author={${authorsBi
320
  });
321
  </script>
322
 
323
- <script>
324
- // Build TOC from article headings (h2/h3/h4) and render into the sticky aside
325
- const buildTOC = () => {
326
- const holder = document.getElementById('article-toc-placeholder');
327
- const holderMobile = document.getElementById('article-toc-mobile-placeholder');
328
- // Always rebuild TOC to avoid stale entries
329
- if (holder) holder.innerHTML = '';
330
- if (holderMobile) holderMobile.innerHTML = '';
331
- const articleRoot = document.querySelector('section.content-grid main');
332
- if (!articleRoot) return;
333
- const headings = articleRoot.querySelectorAll('h2, h3, h4');
334
- if (!headings.length) return;
335
-
336
- // Filter out headings that should not appear in TOC
337
- const normalize = (s) => String(s || '')
338
- .toLowerCase()
339
- .replace(/[^a-z0-9]+/g, ' ')
340
- .trim();
341
- const isTocLabel = (s) => /^(table\s+of\s+contents?)$|^toc$/i.test(String(s || '').replace(/[^a-zA-Z0-9]+/g, ' ').trim());
342
- const shouldSkip = (h) => {
343
- const t = h.textContent || '';
344
- const id = String(h.id || '');
345
- const slug = normalize(t).replace(/\s+/g, '_');
346
- if (isTocLabel(t)) return true;
347
- if (isTocLabel(id.replace(/[_-]+/g, ' '))) return true;
348
- if (isTocLabel(slug.replace(/[_-]+/g, ' '))) return true;
349
- return false;
350
- };
351
- const headingsArr = Array.from(headings).filter(h => !shouldSkip(h));
352
- if (!headingsArr.length) return;
353
-
354
- // Ensure unique ids for headings (deduplicate duplicates)
355
- const usedIds = new Set<string>();
356
- const slugify = (s: string) => String(s || '')
357
- .toLowerCase()
358
- .trim()
359
- .replace(/\s+/g, '_')
360
- .replace(/[^a-z0-9_\-]/g, '');
361
- headingsArr.forEach((h) => {
362
- let id = (h.id || '').trim();
363
- if (!id) {
364
- const base = slugify(h.textContent || '');
365
- id = base || 'section';
366
- }
367
- let candidate = id;
368
- let n = 2;
369
- while (usedIds.has(candidate)) {
370
- candidate = `${id}-${n++}`;
371
- }
372
- if (h.id !== candidate) h.id = candidate;
373
- usedIds.add(candidate);
374
- });
375
-
376
- const nav = document.createElement('nav');
377
- let ulStack = [document.createElement('ul')];
378
- nav.appendChild(ulStack[0]);
379
-
380
- const levelOf = (tag) => tag === 'H2' ? 2 : tag === 'H3' ? 3 : 4;
381
- let prev = 2;
382
- headingsArr.forEach((h) => {
383
- const lvl = levelOf(h.tagName);
384
- // adjust depth
385
- while (lvl > prev) { const ul = document.createElement('ul'); ulStack[ulStack.length-1].lastElementChild?.appendChild(ul); ulStack.push(ul); prev++; }
386
- while (lvl < prev) { ulStack.pop(); prev--; }
387
- const li = document.createElement('li');
388
- const a = document.createElement('a');
389
- a.href = '#' + h.id; a.textContent = h.textContent; a.target = '_self';
390
- li.appendChild(a);
391
- ulStack[ulStack.length-1].appendChild(li);
392
- });
393
-
394
- if (holder) holder.appendChild(nav);
395
- if (holderMobile) holderMobile.appendChild(nav.cloneNode(true));
396
-
397
- // active link on scroll
398
- const links = [
399
- ...(holder ? holder.querySelectorAll('a') : []),
400
- ...(holderMobile ? holderMobile.querySelectorAll('a') : [])
401
- ];
402
- const onScroll = () => {
403
- for (let i = headingsArr.length - 1; i >= 0; i--) {
404
- const top = headingsArr[i].getBoundingClientRect().top;
405
- if (top - 60 <= 0) {
406
- links.forEach(l => l.classList.remove('active'));
407
- const id = '#' + headingsArr[i].id;
408
- const actives = Array.from(links).filter(l => l.getAttribute('href') === id);
409
- actives.forEach(a => a.classList.add('active'));
410
- break;
411
- }
412
- }
413
- };
414
- window.addEventListener('scroll', onScroll);
415
- onScroll();
416
-
417
- // Close mobile accordion when a link inside it is clicked
418
- if (holderMobile) {
419
- const details = holderMobile.closest('details');
420
- holderMobile.addEventListener('click', (ev) => {
421
- const target = ev.target as Element | null;
422
- const anchor = target && 'closest' in target ? (target as Element).closest('a') : null;
423
- if (anchor instanceof HTMLAnchorElement && details && (details as HTMLDetailsElement).open) {
424
- (details as HTMLDetailsElement).open = false;
425
- }
426
- });
427
- }
428
- };
429
-
430
- if (document.readyState === 'loading') {
431
- document.addEventListener('DOMContentLoaded', buildTOC, { once: true });
432
- } else { buildTOC(); }
433
- </script>
434
-
435
- <!-- Removed JS fallback for language chips; labels handled by CSS/Shiki -->
436
  </body>
437
  </html>
438
 
 
4
  import Footer from '../components/Footer.astro';
5
  import ThemeToggle from '../components/ThemeToggle.astro';
6
  import Seo from '../components/Seo.astro';
7
+ import TableOfContents from '../components/TableOfContents.astro';
8
  // Default OG image served from public/
9
  const ogDefaultUrl = '/thumb.jpg';
10
  import 'katex/dist/katex.min.css';
 
18
  .replace(/\n/g, '<br/>');
19
  const subtitle = articleFM?.subtitle ?? '';
20
  const description = articleFM?.description ?? '';
21
+ // Accept authors as string[] or array of objects { name, url, affiliations? }
22
+ const rawAuthors = (articleFM as any)?.authors ?? [];
23
+ type Affiliation = { id: number; name: string; url?: string };
24
+ type Author = { name: string; url?: string; affiliationIndices?: number[] };
25
+
26
+ // Normalize affiliations from frontmatter: supports strings or objects { id?, name, url? }
27
+ const rawAffils = (articleFM as any)?.affiliations ?? (articleFM as any)?.affiliation ?? [];
28
+ const normalizedAffiliations: Affiliation[] = (() => {
29
+ const seen: Map<string, number> = new Map();
30
+ const list: Affiliation[] = [];
31
+ const pushUnique = (name: string, url?: string) => {
32
+ const key = `${String(name).trim()}|${url ? String(url).trim() : ''}`;
33
+ if (seen.has(key)) return seen.get(key)!;
34
+ const id = list.length + 1;
35
+ list.push({ id, name: String(name).trim(), url: url ? String(url) : undefined });
36
+ seen.set(key, id);
37
+ return id;
38
+ };
39
+ const input = Array.isArray(rawAffils) ? rawAffils : (rawAffils ? [rawAffils] : []);
40
+ for (const a of input) {
41
+ if (typeof a === 'string') {
42
+ pushUnique(a);
43
+ } else if (a && typeof a === 'object') {
44
+ const name = a.name ?? a.label ?? a.text ?? a.affiliation ?? '';
45
+ if (!String(name).trim()) continue;
46
+ const url = a.url || a.link;
47
+ // Respect provided numeric id for display stability if present and sequential; otherwise reassign
48
+ pushUnique(String(name), url ? String(url) : undefined);
49
+ }
50
+ }
51
+ return list;
52
+ })();
53
+
54
+ // Helper: ensure an affiliation exists and return its id
55
+ const ensureAffiliation = (val: any): number | undefined => {
56
+ if (val == null) return undefined;
57
+ if (typeof val === 'number' && Number.isFinite(val) && val > 0) {
58
+ return Math.floor(val);
59
+ }
60
+ const name = typeof val === 'string' ? val : (val?.name ?? val?.label ?? val?.text ?? val?.affiliation);
61
+ if (!name || !String(name).trim()) return undefined;
62
+ const existing = normalizedAffiliations.find(a => a.name === String(name).trim());
63
+ if (existing) return existing.id;
64
+ const id = normalizedAffiliations.length + 1;
65
+ normalizedAffiliations.push({ id, name: String(name).trim(), url: val?.url || val?.link });
66
+ return id;
67
+ };
68
+
69
+ // Normalize authors and map affiliations -> indices (Distill-like)
70
+ const normalizedAuthors: Author[] = (Array.isArray(rawAuthors) ? rawAuthors : [])
71
+ .map((a: any) => {
72
+ if (typeof a === 'string') {
73
+ return { name: a } as Author;
74
+ }
75
+ const name = String(a?.name || '').trim();
76
+ const url = a?.url || a?.link;
77
+ let indices: number[] | undefined = undefined;
78
+ const raw = a?.affiliations ?? a?.affiliation ?? a?.affils;
79
+ if (raw != null) {
80
+ const entries = Array.isArray(raw) ? raw : [raw];
81
+ const ids = entries.map(ensureAffiliation).filter((x): x is number => typeof x === 'number');
82
+ const unique = Array.from(new Set(ids)).sort((x, y) => x - y);
83
+ if (unique.length) indices = unique;
84
+ }
85
+ return { name, url, affiliationIndices: indices } as Author;
86
+ })
87
+ .filter((a: Author) => a.name && a.name.trim().length > 0);
88
+ const authorNames: string[] = normalizedAuthors.map(a => a.name);
89
  const published = articleFM?.published ?? undefined;
90
  const tags = articleFM?.tags ?? [];
91
+ // Prefer seoThumbImage from frontmatter if provided
92
+ const fmOg = articleFM?.seoThumbImage as string | undefined;
93
  const imageAbs: string = fmOg && fmOg.startsWith('http')
94
  ? fmOg
95
  : (Astro.site ? new URL((fmOg ?? ogDefaultUrl), Astro.site).toString() : (fmOg ?? ogDefaultUrl));
 
110
  };
111
 
112
  const year = extractYear(published);
113
+ const citationAuthorsText = authorNames.join(', ');
114
  const citationText = `${citationAuthorsText}${year ? ` (${year})` : ''}. "${titleFlat}".`;
115
 
116
+ const authorsBib = authorNames.join(' and ');
117
+ const keyAuthor = (authorNames[0] || 'article').split(/\s+/).slice(-1)[0].toLowerCase();
118
  const keyTitle = titleFlat.toLowerCase().replace(/[^a-z0-9]+/g, '_').replace(/^_|_$/g, '').slice(0, 24);
119
  const bibKey = `${keyAuthor}${year ?? ''}_${keyTitle}`;
120
+ const doi = (ArticleMod as any)?.frontmatter?.doi ? String((ArticleMod as any).frontmatter.doi) : undefined;
121
+ const bibtex = `@misc{${bibKey},\n title={${titleFlat}},\n author={${authorsBib}},\n ${year ? `year={${year}},\n ` : ''}${doi ? `doi={${doi}}` : ''}\n}`;
122
+ const envCollapse = false;
123
+ const tableOfContentAutoCollapse = Boolean(
124
+ (articleFM as any)?.tableOfContentAutoCollapse ?? (articleFM as any)?.tableOfContentsAutoCollapse ?? envCollapse
125
+ );
126
+ // Licence note (HTML allowed)
127
+ const licence = (articleFM as any)?.licence ?? (articleFM as any)?.license ?? (articleFM as any)?.licenseNote;
128
  ---
129
+ <html lang="en" data-theme="light" data-toc-auto-collapse={tableOfContentAutoCollapse ? '1' : '0'}>
130
  <head>
131
  <meta charset="utf-8" />
132
  <meta name="viewport" content="width=device-width, initial-scale=1" />
133
+ <Seo title={docTitle} description={description} authors={authorNames} published={published} tags={tags} image={imageAbs} />
134
  <script is:inline>
135
  (() => {
136
  try {
 
141
  } catch {}
142
  })();
143
  </script>
144
+ <script is:inline src="/scripts/color-palettes.js"></script>
145
 
146
  <!-- TO MANAGE PROPERLY -->
147
  <script src="https://cdn.plot.ly/plotly-3.0.0.min.js" charset="utf-8"></script>
148
  <script src="https://cdn.jsdelivr.net/npm/d3@7/dist/d3.min.js"></script>
149
+ <script src="https://cdn.jsdelivr.net/npm/medium-zoom@1.1.0/dist/medium-zoom.min.js"></script>
150
+
151
  </head>
152
  <body>
153
  <ThemeToggle />
154
+ <Hero title={docTitleHtml} titleRaw={docTitle} description={subtitle} authors={normalizedAuthors as any} affiliations={normalizedAffiliations as any} affiliation={articleFM?.affiliation} published={articleFM?.published} doi={doi} />
155
 
156
  <section class="content-grid">
157
+ <TableOfContents tableOfContentAutoCollapse={tableOfContentAutoCollapse} />
 
 
 
 
 
 
 
158
  <main>
159
  <Article />
 
 
 
 
160
  </main>
161
  </section>
162
 
163
+ <Footer citationText={citationText} bibtex={bibtex} licence={licence} doi={doi} />
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
164
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165
 
166
  <script>
167
  // Open external links in a new tab; keep internal anchors in-page
 
207
  });
208
  </script>
209
 
210
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
211
  </body>
212
  </html>
213
 
app/src/styles/_base.css CHANGED
@@ -1,19 +1,6 @@
1
- /* ============================================================================ */
2
- /* Base / Reset */
3
- /* ============================================================================ */
4
- html { box-sizing: border-box; }
5
- *, *::before, *::after { box-sizing: inherit; }
6
- body { margin: 0; font-family: system-ui, -apple-system, Segoe UI, Roboto, Ubuntu, Cantarell, Noto Sans, Helvetica Neue, Arial, Apple Color Emoji, Segoe UI Emoji; color: var(--text-color); }
7
- audio { display: block; width: 100%; }
8
- /* Avoid constraining <main> inside grid; scope container sizing elsewhere if needed */
9
- /* main { max-width: 980px; margin: 24px auto; padding: 16px; } */
10
 
11
- /* ============================================================================ */
12
- /* Typography (inspired by Distill) */
13
- /* ============================================================================ */
14
- html { font-size: 14px; line-height: 1.6; }
15
- @media (min-width: 768px) { html { font-size: 16px; } }
16
- @media (min-width: 1024px) { html { font-size: 17px; } }
17
 
18
  .content-grid main { color: var(--text-color); }
19
  .content-grid main p { margin: 0 0 var(--spacing-3); }
@@ -48,10 +35,14 @@ html { font-size: 14px; line-height: 1.6; }
48
  /* Do not underline heading links inside the article (not the TOC) */
49
  .content-grid main h2 a,
50
  .content-grid main h3 a,
51
- .content-grid main h4 a { color: inherit; border-bottom: none; text-decoration: none; }
 
 
52
  .content-grid main h2 a:hover,
53
  .content-grid main h3 a:hover,
54
- .content-grid main h4 a:hover { color: inherit; border-bottom: none; text-decoration: none; }
 
 
55
 
56
  .content-grid main ul,
57
  .content-grid main ol { padding-left: 24px; margin: 0 0 var(--spacing-3); }
@@ -66,211 +57,12 @@ html { font-size: 14px; line-height: 1.6; }
66
  margin: var(--spacing-4) 0;
67
  }
68
 
69
- /* Rely on Shiki's own token spans; no class remap */
70
- /* Placeholder block (discreet centered text) */
71
- .placeholder-block {
72
- display: grid;
73
- place-items: center;
74
- min-height: 120px;
75
- color: var(--muted-color);
76
- font-size: 12px;
77
- border: 1px dashed var(--border-color);
78
- border-radius: 8px;
79
- background: var(--surface-bg);
80
- }
81
-
82
- /* Demo blocks for width helpers */
83
- .demo-wide,
84
- .demo-full-width {
85
- display: grid;
86
- place-items: center;
87
- min-height: 150px;
88
- color: var(--muted-color);
89
- font-size: 12px;
90
- border: 1px dashed var(--border-color);
91
- border-radius: 8px;
92
- background: var(--surface-bg);
93
- }
94
-
95
-
96
- .content-grid main table { border-collapse: collapse; width: 100%; margin: 0 0 var(--spacing-4); }
97
- .content-grid main th, .content-grid main td { border-bottom: 1px solid var(--border-color); padding: 6px 8px; text-align: left; font-size: 15px; }
98
- .content-grid main thead th { border-bottom: 1px solid var(--border-color); }
99
-
100
  .content-grid main hr { border: none; border-bottom: 1px solid var(--border-color); margin: var(--spacing-5) 0; }
101
 
102
- /*
103
- .code-block {
104
- background: rgba(120, 120, 120, 0.5);
105
- border: 1px solid var(--border-color);
106
- border-radius: 6px;
107
- padding: var(--spacing-3);
108
- font-size: 14px;
109
- overflow: auto;
110
- }
111
- */
112
-
113
- /* ============================================================================ */
114
- /* Media / Figures */
115
- /* ============================================================================ */
116
- img,
117
- picture {
118
- max-width: 100%;
119
- height: auto;
120
- display: block;
121
- position: relative;
122
- z-index: var(--z-elevated);
123
- }
124
-
125
- /* Inline feature tags */
126
- .tag-list { display: flex; flex-wrap: wrap; gap: 8px; margin: 8px 0 16px; }
127
- .tag {
128
- display: inline-flex;
129
- align-items: center;
130
- gap: 6px;
131
- padding: 4px 8px;
132
- font-size: 12px;
133
- line-height: 1;
134
- border-radius: 999px;
135
- background: var(--surface-bg);
136
- border: 1px solid var(--border-color);
137
- color: var(--text-color);
138
- }
139
- [data-theme="dark"] .tag { background: #1a1f27; border-color: rgba(255,255,255,.15); }
140
-
141
-
142
-
143
- /* ============================================================================ */
144
- /* Figures, captions & image credits */
145
- /* ============================================================================ */
146
- figure { margin: 12px 0; }
147
- figcaption { text-align: left; font-size: 0.9rem; color: var(--muted-color); margin-top: 6px; }
148
- .image-credit { display: block; margin-top: 4px; font-size: 12px; color: var(--muted-color); }
149
- .image-credit a { color: inherit; text-decoration: underline; text-underline-offset: 2px; }
150
-
151
- /* Zoomable overlay container (if used by any lightbox implementation) */
152
- [data-zoom-overlay],
153
- .zoom-overlay {
154
- position: fixed;
155
- inset: 0;
156
- z-index: var(--z-overlay);
157
- }
158
-
159
- /* Download link inside figures */
160
- figure .download-link { position: relative; z-index: var(--z-elevated); }
161
-
162
- /* ============================================================================ */
163
- /* Buttons (minimal, clean) */
164
- /* ============================================================================ */
165
- button, .button {
166
- appearance: none;
167
- background: linear-gradient(15deg, var(--primary-color) 0%, var(--primary-color-hover) 35%);
168
- color: white!important;
169
- border: 1px solid transparent;
170
- border-radius: 6px;
171
- padding: 8px 12px;
172
- font-size: 14px;
173
- line-height: 1;
174
- cursor: pointer;
175
- display: inline-block;
176
- transition: background-color .15s ease, border-color .15s ease, box-shadow .15s ease, transform .02s ease;
177
- }
178
- /* Icon-only buttons: equal X/Y padding */
179
- button:has(> svg:only-child),
180
- .button:has(> svg:only-child) {
181
- padding: 8px !important;
182
- }
183
- button:hover, .button:hover {
184
- filter: brightness(96%);
185
- }
186
- button:active, .button:active {
187
- transform: translateY(1px);
188
- }
189
- button:focus-visible, .button:focus-visible {
190
- outline: none;
191
- }
192
- button:disabled, .button:disabled {
193
- opacity: .6;
194
- cursor: not-allowed;
195
- }
196
-
197
- /* Ghost/Muted button: subtle outline, primary color text/border */
198
- .button--ghost {
199
- background: transparent !important;
200
- color: var(--primary-color) !important;
201
- border-color: var(--primary-color) !important;
202
- }
203
- .button--ghost:hover {
204
- color: var(--primary-color-hover) !important;
205
- border-color: var(--primary-color-hover) !important;
206
- filter: none;
207
- }
208
-
209
- .button-group .button {
210
- margin: 5px;
211
- }
212
-
213
- /* ============================================================================ */
214
- /* Print styles */
215
- /* ========================================================================= */
216
- @media print {
217
- html, body { background: #fff; }
218
- /* Margins handled by Playwright; avoid extra global margins */
219
- body { margin: 0; }
220
-
221
- /* Keep the banner (hero), hide non-essential UI elements */
222
- #theme-toggle { display: none !important; }
223
-
224
- /* Links: remove underline */
225
- .content-grid main a { text-decoration: none; border-bottom: 1px solid rgba(0,0,0,.2); }
226
-
227
- /* Avoid breaks inside complex blocks */
228
- .content-grid main pre,
229
- .content-grid main blockquote,
230
- .content-grid main table,
231
- .content-grid main figure { break-inside: avoid; page-break-inside: avoid; }
232
-
233
- /* Soft page breaks around main headings */
234
- .content-grid main h2 { page-break-before: auto; page-break-after: avoid; break-after: avoid-page; }
235
-
236
- /* Small icon labels not needed when printing */
237
- .code-lang-chip { display: none !important; }
238
-
239
- /* Adjust more contrasty colors for print */
240
- :root {
241
- --border-color: rgba(0,0,0,.2);
242
- --link-underline: rgba(0,0,0,.3);
243
- --link-underline-hover: rgba(0,0,0,.4);
244
- }
245
-
246
- /* Force single column to reduce widows/orphans and awkward breaks */
247
- .content-grid { grid-template-columns: 1fr !important; }
248
- .toc, .right-aside, .toc-mobile { display: none !important; }
249
- main > nav:first-of-type { display: none !important; }
250
-
251
- /* Avoid page breaks inside complex visual blocks */
252
- .hero,
253
- .hero-banner,
254
- .d3-galaxy,
255
- .d3-galaxy svg,
256
- .html-embed__card,
257
- .html-embed__card,
258
- .js-plotly-plot,
259
- figure,
260
- pre,
261
- table,
262
- blockquote,
263
- .wide,
264
- .full-width {
265
- break-inside: avoid;
266
- page-break-inside: avoid;
267
- }
268
- /* Prefer keeping header+lead together */
269
- .hero { page-break-after: avoid; }
270
- }
271
-
272
  .muted {
273
  color: var(--muted-color);
274
  }
275
 
276
-
 
 
 
1
+ @import "https://fonts.googleapis.com/css2?family=Source+Sans+Pro:ital,wght@0,200..900;1,200..900&display=swap";
 
 
 
 
 
 
 
 
2
 
3
+ html { font-size: 16px; line-height: 1.6; }
 
 
 
 
 
4
 
5
  .content-grid main { color: var(--text-color); }
6
  .content-grid main p { margin: 0 0 var(--spacing-3); }
 
35
  /* Do not underline heading links inside the article (not the TOC) */
36
  .content-grid main h2 a,
37
  .content-grid main h3 a,
38
+ .content-grid main h4 a,
39
+ .content-grid main h5 a,
40
+ .content-grid main h6 a { color: inherit; border-bottom: none; text-decoration: none; }
41
  .content-grid main h2 a:hover,
42
  .content-grid main h3 a:hover,
43
+ .content-grid main h4 a:hover,
44
+ .content-grid main h5 a:hover,
45
+ .content-grid main h6 a:hover { color: inherit; border-bottom: none; text-decoration: none; }
46
 
47
  .content-grid main ul,
48
  .content-grid main ol { padding-left: 24px; margin: 0 0 var(--spacing-3); }
 
57
  margin: var(--spacing-4) 0;
58
  }
59
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
  .content-grid main hr { border: none; border-bottom: 1px solid var(--border-color); margin: var(--spacing-5) 0; }
61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  .muted {
63
  color: var(--muted-color);
64
  }
65
 
66
+ [data-footnote-ref] {
67
+ margin-left: 4px;
68
+ }
app/src/styles/_layout.css CHANGED
@@ -1,96 +1,77 @@
1
  /* ============================================================================ */
2
- /* Layout – 3-column grid (TOC / Article / Aside) */
3
  /* ============================================================================ */
4
- :root {
5
- --content-padding-x: 16px;
6
- }
7
 
8
- .content-grid { max-width: 1280px; margin: 0 auto; padding: 0 var(--content-padding-x); margin-top: 40px; display: grid; grid-template-columns: 220px minmax(0, 680px) 260px; gap: 32px; align-items: start; }
9
- .content-grid > main { max-width: 100%; margin: 0; padding: 0; }
10
-
11
- /* TOC (left column) */
12
- .toc { position: sticky; top: 24px; }
13
- .toc nav { border-left: 1px solid var(--border-color); padding-left: 16px; font-size: 13px; }
14
- .toc .title { font-weight: 600; font-size: 14px; margin-bottom: 8px; }
15
-
16
- /* Hide in-article TOC (duplicated by sticky aside) */
17
- main > nav:first-of-type { display: none; }
18
-
19
- /* TOC look & feel */
20
- .toc nav ul { margin: 0 0 6px; padding-left: 1em; }
21
- .toc nav li { list-style: none; margin: .25em 0; }
22
- .toc nav a { color: var(--text-color); text-decoration: none; border-bottom: none; }
23
- .toc nav > ul > li > a { font-weight: 700; }
24
- .toc nav a:hover { text-decoration: underline solid var(--muted-color); }
25
- .toc nav a.active { text-decoration: underline; }
26
-
27
- /* Mobile TOC accordion */
28
- .toc-mobile { display: none; margin: 8px 0 16px; }
29
- .toc-mobile > summary { cursor: pointer; list-style: none; padding: 8px 12px; border: 1px solid var(--border-color); border-radius: 8px; color: var(--text-color); font-weight: 600; }
30
- .toc-mobile[open] > summary { border-bottom-left-radius: 0; border-bottom-right-radius: 0; }
31
- .toc-mobile nav { border-left: none; padding: 10px 12px; font-size: 14px; border: 1px solid var(--border-color); border-top: none; border-bottom-left-radius: 8px; border-bottom-right-radius: 8px; }
32
- .toc-mobile nav ul { margin: 0 0 6px; padding-left: 1em; }
33
- .toc-mobile nav li { list-style: none; margin: .25em 0; }
34
- .toc-mobile nav a { color: var(--text-color); text-decoration: none; border-bottom: none; }
35
- .toc-mobile nav > ul > li > a { font-weight: 700; }
36
- .toc-mobile nav a:hover { text-decoration: underline solid var(--muted-color); }
37
- .toc-mobile nav a.active { text-decoration: underline; }
38
-
39
- /* Right aside (notes) */
40
- .right-aside { position: sticky; top: 24px; }
41
- .right-aside .aside-card { background: var(--surface-bg); border: 1px solid var(--border-color); border-radius: 8px; padding: 10px; margin-bottom: 10px; font-size: 0.9rem; color: var(--text-color); }
42
-
43
- /* Responsive – collapse to single column */
44
- @media (max-width: 1100px) {
45
- .content-grid { grid-template-columns: 1fr; }
46
- .toc { position: static; display: none; }
47
- .toc-mobile { display: block; }
48
- .right-aside { display: none; }
49
- main > nav:first-of-type { display: block; }
50
  }
51
 
 
 
 
 
 
52
 
 
 
 
 
 
 
53
 
54
- .margin-aside { position: relative; margin: 12px 0; }
 
 
55
 
56
- .margin-aside__aside {
57
- position: absolute;
58
- top: 0;
59
- right: -260px; /* push into the right grid column (width 260 + gap 32) */
60
- width: 260px;
61
- border-radius: 8px;
62
- padding: 0 30px;
63
- font-size: 0.9rem;
64
- color: var(--muted-color);
65
- }
66
- @media (max-width: 1100px) {
67
- .margin-aside__aside {
68
  position: static;
69
- width: auto;
70
- margin-top: 8px;
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
  }
72
  }
73
 
74
 
 
75
  /* ============================================================================ */
76
  /* Width helpers – slightly wider than main column, and full-width to viewport */
77
  /* ---------------------------------------------------------------------------- */
78
- /* Usage in MDX: */
79
- /* <div className="wide"> ... </div> */
80
- /* <div className="full-width"> ... </div> */
81
- /* These center the content relative to the viewport while keeping it responsive. */
82
- /* */
83
- /* Notes: */
84
- /* - These helpers work inside the main article column; they break out visually */
85
- /* to be wider or fully span the viewport. On small screens, they fall back to 100%. */
86
- /* - Adjust the target width in .wide if desired. */
87
  .wide,
88
- .full-width { box-sizing: border-box; position: relative; z-index: var(--z-elevated); }
 
 
 
 
89
 
90
  .wide {
91
- /* Target up to ~1400px while staying within viewport minus page gutters */
92
- width: min(1400px, 100vw - 32px);
93
- margin-left: 50%;
94
  transform: translateX(-50%);
95
  }
96
 
@@ -101,7 +82,7 @@ main > nav:first-of-type { display: none; }
101
  margin-right: calc(50% - 50vw);
102
  }
103
 
104
- @media (max-width: 1100px) {
105
  .wide,
106
  .full-width {
107
  width: 100%;
@@ -111,5 +92,40 @@ main > nav:first-of-type { display: none; }
111
  }
112
  }
113
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
 
115
 
 
1
  /* ============================================================================ */
2
+ /* Layout – 3-column grid (Table of Contents / Article / Aside) */
3
  /* ============================================================================ */
 
 
 
4
 
5
+ .content-grid {
6
+ max-width: 1280px;
7
+ margin: 0 auto;
8
+ padding: 0 var(--content-padding-x);
9
+ margin-top: 40px;
10
+ display: grid;
11
+ grid-template-columns: 220px minmax(0, 680px) 260px;
12
+ gap: 32px;
13
+ align-items: start;
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
15
 
16
+ .content-grid > main {
17
+ max-width: 100%;
18
+ margin: 0;
19
+ padding: 0;
20
+ }
21
 
22
+ @media (--bp-content-collapse) {
23
+ .content-grid {
24
+ overflow: hidden;
25
+ display: block;
26
+ margin-top: var(--spacing-2);
27
+ }
28
 
29
+ .content-grid {
30
+ grid-template-columns: 1fr;
31
+ }
32
 
33
+ .table-of-contents {
 
 
 
 
 
 
 
 
 
 
 
34
  position: static;
35
+ display: none;
36
+ }
37
+
38
+ .table-of-contents-mobile {
39
+ display: block;
40
+ }
41
+
42
+ .footer-inner {
43
+ grid-template-columns: 1fr;
44
+ gap: 16px;
45
+ }
46
+
47
+ .footer-inner > h3 {
48
+ grid-column: auto;
49
+ margin-top: 16px;
50
+ }
51
+
52
+ .footer-inner {
53
+ display: block;
54
+ padding: 40px 16px;
55
  }
56
  }
57
 
58
 
59
+
60
  /* ============================================================================ */
61
  /* Width helpers – slightly wider than main column, and full-width to viewport */
62
  /* ---------------------------------------------------------------------------- */
63
+
 
 
 
 
 
 
 
 
64
  .wide,
65
+ .full-width {
66
+ box-sizing: border-box;
67
+ position: relative;
68
+ z-index: var(--z-elevated);
69
+ }
70
 
71
  .wide {
72
+ /* Target up to ~1100px while staying within viewport minus page gutters */
73
+ width: min(1100px, 100vw - 32px);
74
+ margin-left: calc(50% + var(--content-padding-x) * 2);
75
  transform: translateX(-50%);
76
  }
77
 
 
82
  margin-right: calc(50% - 50vw);
83
  }
84
 
85
+ @media (--bp-content-collapse) {
86
  .wide,
87
  .full-width {
88
  width: 100%;
 
92
  }
93
  }
94
 
95
+ /* ------------------------------------------------------------------------- */
96
+ /* Hero meta bar responsiveness */
97
+ /* Two columns at collapse breakpoint, then one column below small screens */
98
+ /* ------------------------------------------------------------------------- */
99
+ @media (--bp-sm) {
100
+ header.meta .meta-container {
101
+ display: flex;
102
+ flex-wrap: wrap;
103
+ row-gap: 12px;
104
+ column-gap: 8px;
105
+ max-width: 100%;
106
+ padding: 0 var(--spacing-4);
107
+ }
108
+ header.meta .meta-container .meta-container-cell {
109
+ flex: 1 1 calc(50% - 8px);
110
+ min-width: 0;
111
+ }
112
+ }
113
+
114
+ @media (--bp-xxs) {
115
+ header.meta .meta-container .meta-container-cell {
116
+ flex-basis: 100%;
117
+ text-align: center;
118
+ }
119
+ /* Center ordered list numbers within meta (e.g., affiliations) */
120
+ header.meta .affiliations {
121
+ list-style-position: inside;
122
+ padding-left: 0;
123
+ margin-left: 0;
124
+ }
125
+ header.meta .affiliations li {
126
+ text-align: center;
127
+ }
128
+ }
129
+
130
 
131
 
app/src/styles/_print.css ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ /* ============================================================================ */
3
+ /* Print styles */
4
+ /* ========================================================================= */
5
+ @media print {
6
+ html, body { background: #fff; }
7
+ /* Margins handled by Playwright; avoid extra global margins */
8
+ body { margin: 0; }
9
+
10
+ /* Keep the banner (hero), hide non-essential UI elements */
11
+ #theme-toggle { display: none !important; }
12
+
13
+ /* Links: remove underline */
14
+ .content-grid main a { text-decoration: none; border-bottom: 1px solid rgba(0,0,0,.2); }
15
+
16
+ /* Avoid breaks inside complex blocks */
17
+ .content-grid main pre,
18
+ .content-grid main blockquote,
19
+ .content-grid main table,
20
+ .content-grid main figure { break-inside: avoid; page-break-inside: avoid; }
21
+
22
+ /* Soft page breaks around main headings */
23
+ .content-grid main h2 { page-break-before: auto; page-break-after: avoid; break-after: avoid-page; }
24
+
25
+ /* Small icon labels not needed when printing */
26
+ .code-lang-chip { display: none !important; }
27
+
28
+ /* Adjust more contrasty colors for print */
29
+ :root {
30
+ --border-color: rgba(0,0,0,.2);
31
+ --link-underline: rgba(0,0,0,.3);
32
+ --link-underline-hover: rgba(0,0,0,.4);
33
+ }
34
+
35
+ /* Force single column to reduce widows/orphans and awkward breaks */
36
+ .content-grid { grid-template-columns: 1fr !important; }
37
+ .table-of-contents, .right-aside, .table-of-contents-mobile { display: none !important; }
38
+ main > nav:first-of-type { display: none !important; }
39
+
40
+ /* Avoid page breaks inside complex visual blocks */
41
+ .hero,
42
+ .hero-banner,
43
+ .d3-galaxy,
44
+ .d3-galaxy svg,
45
+ .html-embed__card,
46
+ .html-embed__card,
47
+ .js-plotly-plot,
48
+ figure,
49
+ pre,
50
+ table,
51
+ blockquote,
52
+ .wide,
53
+ .full-width {
54
+ break-inside: avoid;
55
+ page-break-inside: avoid;
56
+ }
57
+ /* Prefer keeping header+lead together */
58
+ .hero { page-break-after: avoid; }
59
+ }
60
+
61
+
62
+ @media print {
63
+ .meta-container-cell--pdf {
64
+ display: none !important;
65
+ }
66
+ }
67
+
68
+
app/src/styles/_reset.css ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ html { box-sizing: border-box; }
2
+ *, *::before, *::after { box-sizing: inherit; }
3
+ body { margin: 0; font-family: var(--default-font-family); color: var(--text-color); }
4
+ audio { display: block; width: 100%; }
5
+
6
+ img,
7
+ picture {
8
+ max-width: 100%;
9
+ height: auto;
10
+ display: block;
11
+ position: relative;
12
+ z-index: var(--z-elevated);
13
+ }
app/src/styles/_variables.css CHANGED
@@ -1,28 +1,34 @@
1
  /* ============================================================================ */
2
- /* Theme Variables (inspired by Distill) */
3
  /* ============================================================================ */
4
  :root {
5
- /* Neutral palette */
6
  --neutral-600: rgb(107, 114, 128);
7
  --neutral-400: rgb(185, 185, 185);
8
  --neutral-300: rgb(228, 228, 228);
9
  --neutral-200: rgb(245, 245, 245);
10
 
11
- /* Primary brand color */
12
- --primary-color: rgb(232, 137, 171);
13
- --primary-color-hover: rgb(212, 126, 156);
 
 
 
 
14
  --on-primary: #ffffff;
15
 
 
16
  --text-color: rgba(0,0,0,.85);
17
  --muted-color: rgba(0,0,0,.6);
18
  --border-color: rgba(0,0,0,.1);
19
-
20
- /* Light surfaces & links */
21
  --surface-bg: #fafafa;
22
  --code-bg: #f6f8fa;
23
- --link-underline: var(--primary-color); /* based on --primary-color */
 
 
24
  --link-underline-hover: var(--primary-color-hover);
25
 
 
26
  --spacing-1: 8px;
27
  --spacing-2: 12px;
28
  --spacing-3: 16px;
@@ -34,29 +40,64 @@
34
  --spacing-9: 64px;
35
  --spacing-10: 72px;
36
 
37
- /* Z-index scale */
38
- --z-base: 0; /* background/base */
39
- --z-content: 1; /* regular content */
40
- --z-elevated: 10; /* wide/full-width blocks, images */
41
- --z-overlay: 1000; /* overlays/lightboxes */
42
- --z-modal: 1100; /* modals/dialogs */
43
- --z-tooltip: 1200; /* tooltips/popovers */
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  }
45
- /* Theme tokens for dark mode */
 
 
 
46
  [data-theme="dark"] {
47
  --text-color: rgba(255,255,255,.9);
48
  --muted-color: rgba(255,255,255,.7);
49
  --border-color: rgba(255,255,255,.15);
50
  --surface-bg: #12151b;
51
  --code-bg: #12151b;
52
- /* Primary in dark mode */
53
- --primary-color: rgb(232, 137, 171);
54
- --primary-color-hover: rgb(212, 126, 156);
 
 
55
  --on-primary: #0f1115;
56
 
57
  color-scheme: dark;
58
  background: #0f1115;
59
- }
60
-
61
-
62
-
 
1
  /* ============================================================================ */
2
+ /* Design Tokens */
3
  /* ============================================================================ */
4
  :root {
5
+ /* Neutrals */
6
  --neutral-600: rgb(107, 114, 128);
7
  --neutral-400: rgb(185, 185, 185);
8
  --neutral-300: rgb(228, 228, 228);
9
  --neutral-200: rgb(245, 245, 245);
10
 
11
+ --default-font-family: Source Sans Pro,ui-sans-serif,system-ui,sans-serif,"Apple Color Emoji","Segoe UI Emoji","Segoe UI Symbol","Noto Color Emoji";
12
+
13
+ /* Brand (OKLCH base + derived states) */
14
+ --primary-base: oklch(0.75 0.12 340);
15
+ --primary-color: var(--primary-base);
16
+ --primary-color-hover: oklch(from var(--primary-color) calc(l - 0.05) c h);
17
+ --primary-color-active: oklch(from var(--primary-color) calc(l - 0.10) c h);
18
  --on-primary: #ffffff;
19
 
20
+ /* Text & Surfaces */
21
  --text-color: rgba(0,0,0,.85);
22
  --muted-color: rgba(0,0,0,.6);
23
  --border-color: rgba(0,0,0,.1);
 
 
24
  --surface-bg: #fafafa;
25
  --code-bg: #f6f8fa;
26
+
27
+ /* Links */
28
+ --link-underline: var(--primary-color);
29
  --link-underline-hover: var(--primary-color-hover);
30
 
31
+ /* Spacing scale */
32
  --spacing-1: 8px;
33
  --spacing-2: 12px;
34
  --spacing-3: 16px;
 
40
  --spacing-9: 64px;
41
  --spacing-10: 72px;
42
 
43
+ /* Custom Media aliases compiled by PostCSS */
44
+ @custom-media --bp-xxs (max-width: 320px);
45
+ @custom-media --bp-xs (max-width: 480px);
46
+ @custom-media --bp-sm (max-width: 640px);
47
+ @custom-media --bp-md (max-width: 768px);
48
+ @custom-media --bp-lg (max-width: 1024px);
49
+ @custom-media --bp-xl (max-width: 1280px);
50
+ @custom-media --bp-content-collapse (max-width: 1100px);
51
+
52
+ /* Layout */
53
+ --content-padding-x: 16px; /* default page gutter */
54
+ --block-spacing-y: var(--spacing-4); /* default vertical spacing between block components */
55
+
56
+ /* Config */
57
+ --palette-count: 6;
58
+
59
+ /* Button tokens */
60
+ --button-radius: 6px;
61
+ --button-padding-x: 12px;
62
+ --button-padding-y: 8px;
63
+ --button-font-size: 14px;
64
+ --button-icon-padding: 8px;
65
+ /* Big button */
66
+ --button-big-padding-x: 16px;
67
+ --button-big-padding-y: 12px;
68
+ --button-big-font-size: 16px;
69
+ --button-big-icon-padding: 12px;
70
+
71
+ /* Table tokens */
72
+ --table-border-radius: 8px;
73
+ --table-header-bg: oklch(from var(--surface-bg) calc(l - 0.02) c h);
74
+ --table-row-odd-bg: oklch(from var(--surface-bg) calc(l - 0.01) c h);
75
+
76
+ /* Z-index */
77
+ --z-base: 0;
78
+ --z-content: 1;
79
+ --z-elevated: 10;
80
+ --z-overlay: 1000;
81
+ --z-modal: 1100;
82
+ --z-tooltip: 1200;
83
  }
84
+
85
+ /* ============================================================================ */
86
+ /* Dark Theme Overrides */
87
+ /* ============================================================================ */
88
  [data-theme="dark"] {
89
  --text-color: rgba(255,255,255,.9);
90
  --muted-color: rgba(255,255,255,.7);
91
  --border-color: rgba(255,255,255,.15);
92
  --surface-bg: #12151b;
93
  --code-bg: #12151b;
94
+
95
+ /* Primary (lower L in dark) */
96
+ --primary-color: oklch(from var(--primary-base) calc(l - 0.08) c h);
97
+ --primary-color-hover: oklch(from var(--primary-color) calc(l - 0.05) c h);
98
+ --primary-color-active: oklch(from var(--primary-color) calc(l - 0.10) c h);
99
  --on-primary: #0f1115;
100
 
101
  color-scheme: dark;
102
  background: #0f1115;
103
+ }
 
 
 
app/src/styles/components/_button.css ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ button, .button {
2
+ appearance: none;
3
+ background: linear-gradient(15deg, var(--primary-color) 0%, var(--primary-color-hover) 35%);
4
+ color: white!important;
5
+ border: 1px solid transparent;
6
+ border-radius: var(--button-radius);
7
+ padding: var(--button-padding-y) var(--button-padding-x);
8
+ font-size: var(--button-font-size);
9
+ line-height: 1;
10
+ cursor: pointer;
11
+ display: inline-block;
12
+ text-decoration: none;
13
+ transition: background-color .15s ease, border-color .15s ease, box-shadow .15s ease, transform .02s ease;
14
+ }
15
+ /* Icon-only buttons: equal X/Y padding */
16
+ button:has(> svg:only-child),
17
+ .button:has(> svg:only-child) {
18
+ padding: var(--button-icon-padding) !important;
19
+ }
20
+ button:hover, .button:hover {
21
+ filter: brightness(96%);
22
+ }
23
+ button:active, .button:active {
24
+ transform: translateY(1px);
25
+ }
26
+ button:focus-visible, .button:focus-visible {
27
+ outline: none;
28
+ }
29
+ button:disabled, .button:disabled {
30
+ opacity: .6;
31
+ cursor: not-allowed;
32
+ }
33
+
34
+ /* Ghost/Muted button: subtle outline, primary color text/border */
35
+ .button--ghost {
36
+ background: transparent !important;
37
+ color: var(--primary-color) !important;
38
+ border-color: var(--primary-color) !important;
39
+ }
40
+ .button--ghost:hover {
41
+ color: var(--primary-color-hover) !important;
42
+ border-color: var(--primary-color-hover) !important;
43
+ filter: none;
44
+ }
45
+
46
+ /* Big button: larger padding and font size */
47
+ .button--big {
48
+ padding: var(--button-big-padding-y) var(--button-big-padding-x) !important;
49
+ font-size: var(--button-big-font-size);
50
+ }
51
+ .button--big:has(> svg:only-child) {
52
+ padding: var(--button-big-icon-padding) !important;
53
+ }
54
+
55
+ .button-group .button {
56
+ margin: 5px;
57
+ }
58
+
app/src/styles/components/_code.css CHANGED
@@ -1,8 +1,10 @@
 
 
 
1
  code {
2
  font-size: 14px;
3
  font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
4
  background-color: var(--code-bg);
5
- padding: 0.2em 0.4em;
6
  border-radius: 0.3em;
7
  border: 1px solid var(--border-color);
8
  color: var(--text-color);
@@ -10,81 +12,141 @@ code {
10
  line-height: 1.5;
11
  }
12
 
13
- /* Sync Shiki variables with current theme */
14
- /* Standard wrapper look for code blocks */
15
- .astro-code { border: 1px solid var(--border-color); border-radius: 6px; padding: 0; font-size: 14px; --code-gutter-width: 2.5em; }
16
- .astro-code { position: relative; }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
 
18
- /* Prevent code blocks from breaking layout on small screens */
19
- .astro-code { overflow-x: auto; width: 100%; max-width: 100%; box-sizing: border-box; -webkit-overflow-scrolling: touch; }
20
- section.content-grid pre { overflow-x: auto; width: 100%; max-width: 100%; box-sizing: border-box; -webkit-overflow-scrolling: touch; padding: 0; }
21
- section.content-grid pre code { display: inline-block; min-width: 100%; }
 
 
22
 
23
- /* Wrap long lines on mobile to avoid overflow (URLs, etc.) */
24
  /* Wrap long lines only on small screens to prevent layout overflow */
25
- @media (max-width: 1100px) {
26
  .astro-code,
27
- section.content-grid pre { white-space: pre-wrap; overflow-wrap: anywhere; word-break: break-word; }
28
- section.content-grid pre code { white-space: pre-wrap; display: block; min-width: 0; }
 
 
 
 
 
 
 
 
 
29
  }
30
 
31
- html[data-theme='light'] .astro-code { background-color: var(--code-bg); }
32
-
33
- html[data-theme='dark'] .astro-code { background-color: var(--shiki-dark-bg); }
34
 
35
  /* Apply token color from per-span vars exposed by Shiki dual themes */
36
- html[data-theme='light'] .astro-code span { color: var(--shiki-light) !important; }
37
- html[data-theme='dark'] .astro-code span { color: var(--shiki-dark) !important; }
38
 
39
- /* Token color remapping using Shiki CSS variables on the wrapper */
40
  /* Optional: boost contrast for light theme */
41
- html[data-theme='light'] .astro-code {
42
  --shiki-foreground: #24292f;
43
  --shiki-background: #ffffff;
44
  }
45
 
46
  /* Line numbers for Shiki-rendered code blocks */
47
- .astro-code code { counter-reset: astro-code-line; display: block; background: none; border: none; }
48
- .astro-code .line { display: inline-block; position: relative; padding-left: calc(var(--code-gutter-width) + var(--spacing-1)); min-height: 1.25em; }
49
- .astro-code .line::before { counter-increment: astro-code-line; content: counter(astro-code-line); position: absolute; left: 0; top: 0; bottom: 0; width: calc(var(--code-gutter-width)); text-align: right; color: var(--muted-color); opacity: .30; user-select: none; padding-right: var(--spacing-2); border-right: 1px solid var(--border-color); }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  .astro-code .line:empty::after { content: "\00a0"; }
 
51
  /* Hide trailing empty line added by parsers */
52
  .astro-code code > .line:last-child:empty { display: none; }
53
 
54
- /* (Removed JS fallback chip: label handled via CSS in _base.css) */
55
-
56
- /* Rehype-injected wrapper for non-Shiki pre blocks */
57
  .code-card { position: relative; }
 
58
  .code-card .code-copy {
59
- position: absolute; top: 6px; right: 6px; z-index: 3; padding: 6px 12px; border: none;
 
 
 
 
60
  }
61
- .code-card .code-copy svg { width: 16px; height: 16px; display: block; fill: currentColor; }
62
- .code-card pre { margin: 0; margin-bottom: var(--spacing-1);}
63
 
64
- /* Discreet filetype/language label shown under the Copy button */
65
- .code-card::after {
66
- content: attr(data-language);
67
- position: absolute;
68
- top: 8px;
69
- right: 56px; /* leave room for copy button */
70
- font-size: 10px;
71
- line-height: 1;
72
- text-transform: uppercase;
73
- color: var(--muted-color);
74
- pointer-events: none;
75
- z-index: 2;
76
  }
77
 
78
- /* When no copy button (single-line), keep the label in the top-right corner */
79
- .code-card.no-copy::after { top: 8px; right: 8px; }
 
 
 
 
80
 
 
81
 
 
 
82
 
83
- /* Overrides inside Accordion: remove padding and border on code containers */
 
 
 
84
  .accordion .astro-code { padding: 0; border: none; }
85
 
86
- /* Language/extension vignette for Shiki blocks (bottom-right, discreet) */
87
- .astro-code::after {
 
 
88
  content: attr(data-language);
89
  position: absolute;
90
  right: 0;
@@ -96,11 +158,11 @@ html[data-theme='light'] .astro-code {
96
  background: var(--surface-bg);
97
  border-top: 1px solid var(--border-color);
98
  border-left: 1px solid var(--border-color);
99
- opacity: 0.5;
100
- border-radius: 8px 0 0 0; /* round only top-left */
101
  padding: 4px 6px;
102
  pointer-events: none;
103
- }
104
 
105
  /* Fallback if Shiki uses data-lang instead of data-language */
106
  .astro-code[data-lang]::after { content: attr(data-lang); }
 
1
+ /* ============================================================================ */
2
+ /* Inline code */
3
+ /* ============================================================================ */
4
  code {
5
  font-size: 14px;
6
  font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
7
  background-color: var(--code-bg);
 
8
  border-radius: 0.3em;
9
  border: 1px solid var(--border-color);
10
  color: var(--text-color);
 
12
  line-height: 1.5;
13
  }
14
 
15
+ /* ============================================================================ */
16
+ /* Shiki code blocks */
17
+ /* ============================================================================ */
18
+ .astro-code {
19
+ position: relative;
20
+ border: 1px solid var(--border-color);
21
+ border-radius: 6px;
22
+ padding: 0;
23
+ font-size: 14px;
24
+ --code-gutter-width: 2.5em;
25
+ }
26
+
27
+ /* Shared sizing & horizontal scroll for code containers */
28
+ .astro-code,
29
+ section.content-grid pre {
30
+ overflow-x: auto;
31
+ width: 100%;
32
+ max-width: 100%;
33
+ box-sizing: border-box;
34
+ -webkit-overflow-scrolling: touch;
35
+ padding: 0;
36
+ margin-bottom: var(--block-spacing-y) !important;
37
+ }
38
 
39
+ section.content-grid pre { margin: 0; }
40
+
41
+ section.content-grid pre code {
42
+ display: inline-block;
43
+ min-width: 100%;
44
+ }
45
 
 
46
  /* Wrap long lines only on small screens to prevent layout overflow */
47
+ @media (--bp-content-collapse) {
48
  .astro-code,
49
+ section.content-grid pre {
50
+ white-space: pre-wrap;
51
+ overflow-wrap: anywhere;
52
+ word-break: break-word;
53
+ }
54
+
55
+ section.content-grid pre code {
56
+ white-space: pre-wrap;
57
+ display: block;
58
+ min-width: 0;
59
+ }
60
  }
61
 
62
+ /* Themes */
63
+ [data-theme='light'] .astro-code { background-color: var(--code-bg); }
 
64
 
65
  /* Apply token color from per-span vars exposed by Shiki dual themes */
66
+ [data-theme='light'] .astro-code span { color: var(--shiki-light) !important; }
67
+ [data-theme='dark'] .astro-code span { color: var(--shiki-dark) !important; }
68
 
 
69
  /* Optional: boost contrast for light theme */
70
+ [data-theme='light'] .astro-code {
71
  --shiki-foreground: #24292f;
72
  --shiki-background: #ffffff;
73
  }
74
 
75
  /* Line numbers for Shiki-rendered code blocks */
76
+ .astro-code code {
77
+ counter-reset: astro-code-line;
78
+ display: block;
79
+ background: none;
80
+ border: none;
81
+ }
82
+
83
+ .astro-code .line {
84
+ display: inline-block;
85
+ position: relative;
86
+ padding-left: calc(var(--code-gutter-width) + var(--spacing-1));
87
+ min-height: 1.25em;
88
+ }
89
+
90
+ .astro-code .line::before {
91
+ counter-increment: astro-code-line;
92
+ content: counter(astro-code-line);
93
+ position: absolute;
94
+ left: 0;
95
+ top: 0;
96
+ bottom: 0;
97
+ width: calc(var(--code-gutter-width));
98
+ text-align: right;
99
+ color: var(--muted-color);
100
+ opacity: .3;
101
+ user-select: none;
102
+ padding-right: var(--spacing-2);
103
+ border-right: 1px solid var(--border-color);
104
+ }
105
+
106
  .astro-code .line:empty::after { content: "\00a0"; }
107
+
108
  /* Hide trailing empty line added by parsers */
109
  .astro-code code > .line:last-child:empty { display: none; }
110
 
111
+ /* ============================================================================ */
112
+ /* Non-Shiki pre wrapper (rehype) */
113
+ /* ============================================================================ */
114
  .code-card { position: relative; }
115
+
116
  .code-card .code-copy {
117
+ position: absolute;
118
+ top: var(--spacing-2);
119
+ right: var(--spacing-2);
120
+ z-index: 3;
121
+ display: none;
122
  }
 
 
123
 
124
+ .code-card:hover .code-copy {
125
+ display: block;
 
 
 
 
 
 
 
 
 
 
126
  }
127
 
128
+ .code-card .code-copy svg {
129
+ width: 16px;
130
+ height: 16px;
131
+ display: block;
132
+ fill: currentColor;
133
+ }
134
 
135
+ .code-card pre { margin: 0 0 var(--spacing-1); }
136
 
137
+ /* When no copy button (single-line), keep the label in the top-right corner */
138
+ .code-card.no-copy::after { top: 8px; right: 8px; }
139
 
140
+ /* ============================================================================ */
141
+ /* Contextual overrides */
142
+ /* ============================================================================ */
143
+ /* Inside Accordions: remove padding and border on code containers */
144
  .accordion .astro-code { padding: 0; border: none; }
145
 
146
+ /* ============================================================================ */
147
+ /* Language/extension vignette (bottom-right, discreet) */
148
+ /* ============================================================================ */
149
+ /* .astro-code::after {
150
  content: attr(data-language);
151
  position: absolute;
152
  right: 0;
 
158
  background: var(--surface-bg);
159
  border-top: 1px solid var(--border-color);
160
  border-left: 1px solid var(--border-color);
161
+ opacity: 1;
162
+ border-radius: 8px 0 0 0;
163
  padding: 4px 6px;
164
  pointer-events: none;
165
+ } */
166
 
167
  /* Fallback if Shiki uses data-lang instead of data-language */
168
  .astro-code[data-lang]::after { content: attr(data-lang); }
app/src/styles/components/_footer.css DELETED
@@ -1,56 +0,0 @@
1
- .distill-footer { contain: layout style; font-size: 0.8em; line-height: 1.7em; margin-top: 60px; margin-bottom: 0; border-top: 1px solid rgba(0, 0, 0, 0.1); color: rgba(0, 0, 0, 0.5); }
2
- .footer-inner { max-width: 1280px; margin: 0 auto; padding: 60px 16px 48px; display: grid; grid-template-columns: 220px minmax(0, 680px) 260px; gap: 32px; align-items: start; }
3
-
4
- /* Use the parent grid (3 columns like .content-grid) */
5
- .citation-block,
6
- .references-block { display: contents; }
7
- .citation-block > h3,
8
- .references-block > h3 { grid-column: 1; font-size: 15px; margin: 0; text-align: right; padding-right: 30px; }
9
- .citation-block > :not(h3),
10
- .references-block > :not(h3) { grid-column: 2; }
11
- @media (max-width: 1100px) {
12
- .footer-inner { grid-template-columns: 1fr; gap: 16px; }
13
- .footer-inner > h3 { grid-column: auto; margin-top: 16px; }
14
- }
15
- .citation-block h3 { margin: 0 0 8px; }
16
- .citation-block h4 { margin: 16px 0 8px; font-size: 14px; text-transform: uppercase; color: var(--muted-color); }
17
-
18
- .citation-block p, .references {
19
- margin-top:0;
20
- }
21
-
22
- /* Distill-like appendix citation styling */
23
- .citation {
24
- font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
25
- font-size: 11px;
26
- line-height: 15px;
27
- border-left: 1px solid rgba(0, 0, 0, 0.1);
28
- padding-left: 18px;
29
- border: 1px solid rgba(0,0,0,0.1);
30
- background: rgba(0, 0, 0, 0.02);
31
- padding: 10px 18px;
32
- border-radius: 3px;
33
- color: rgba(150, 150, 150, 1);
34
- overflow: hidden;
35
- margin-top: -12px;
36
- white-space: pre-wrap;
37
- word-wrap: break-word;
38
- }
39
-
40
- .citation a { color: rgba(0, 0, 0, 0.6); text-decoration: underline; }
41
-
42
- .citation.short { margin-top: -4px; }
43
-
44
- .references-block h3 { margin: 0; }
45
-
46
- /* Distill-like list styling for references/footnotes */
47
- .references-block ol { padding: 0 0 0 15px; }
48
- @media (min-width: 768px) { .references-block ol { padding: 0 0 0 30px; margin-left: -30px; } }
49
- .references-block li { margin-bottom: 1em; }
50
- .references-block a { color: rgba(0, 0, 0, 0.6); }
51
-
52
- @media (max-width: 1100px) {
53
- .footer-inner { display: block; padding: 40px 16px; }
54
- }
55
-
56
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/styles/components/_poltly.css DELETED
@@ -1,44 +0,0 @@
1
- /* ============================================================================ */
2
- /* Plotly – fragments & controls */
3
- /* ============================================================================ */
4
- .html-embed__card svg text { fill: var(--text-color) !important; }
5
- .html-embed__card label { color: var(--text-color) !important; }
6
- .plotly-graph-div { width: 100% !important; min-height: 320px; }
7
- @media (max-width: 768px) { .plotly-graph-div { min-height: 260px; } }
8
- [id^="plot-"] { display: flex; flex-direction: column; align-items: center; gap: 15px; }
9
- .plotly_caption { font-style: italic; margin-top: 10px; }
10
- .plotly_controls { display: flex; flex-wrap: wrap; justify-content: center; gap: 30px; }
11
- .plotly_input_container { display: flex; align-items: center; flex-direction: column; gap: 10px; }
12
- .plotly_input_container > select { padding: 2px 4px; line-height: 1.5em; text-align: center; border-radius: 4px; font-size: 12px; background-color: var(--neutral-200); outline: none; border: 1px solid var(--neutral-300); }
13
- .plotly_slider { display: flex; align-items: center; gap: 10px; }
14
- .plotly_slider > input[type="range"] { -webkit-appearance: none; appearance: none; height: 2px; background: var(--neutral-400); border-radius: 5px; outline: none; }
15
- .plotly_slider > input[type="range"]::-webkit-slider-thumb { -webkit-appearance: none; width: 18px; height: 18px; border-radius: 50%; background: var(--primary-color); cursor: pointer; }
16
- .plotly_slider > input[type="range"]::-moz-range-thumb { width: 18px; height: 18px; border-radius: 50%; background: var(--primary-color); cursor: pointer; }
17
- .plotly_slider > span { font-size: 14px; line-height: 1.6em; min-width: 16px; }
18
-
19
- /* ---------------------------------------------------------------------------- */
20
- /* Dark mode overrides for Plotly readability */
21
- /* ---------------------------------------------------------------------------- */
22
- [data-theme="dark"] .html-embed__card .xaxislayer-above text,
23
- [data-theme="dark"] .html-embed__card .yaxislayer-above text,
24
- [data-theme="dark"] .html-embed__card .infolayer text,
25
- [data-theme="dark"] .html-embed__card .legend text,
26
- [data-theme="dark"] .html-embed__card .annotation text,
27
- [data-theme="dark"] .html-embed__card .colorbar text,
28
- [data-theme="dark"] .html-embed__card .hoverlayer text { fill: #fff !important; }
29
-
30
- [data-theme="dark"] .html-embed__card .xaxislayer-above path,
31
- [data-theme="dark"] .html-embed__card .yaxislayer-above path,
32
- [data-theme="dark"] .html-embed__card .xlines-above,
33
- [data-theme="dark"] .html-embed__card .ylines-above { stroke: rgba(255,255,255,.35) !important; }
34
-
35
- [data-theme="dark"] .html-embed__card .gridlayer path { stroke: rgba(255,255,255,.15) !important; }
36
-
37
- /* Legend and hover backgrounds */
38
- [data-theme="dark"] .html-embed__card .legend rect.bg { fill: rgba(0,0,0,.25) !important; stroke: rgba(255,255,255,.2) !important; }
39
- [data-theme="dark"] .html-embed__card .hoverlayer .bg { fill: rgba(0,0,0,.8) !important; stroke: rgba(255,255,255,.2) !important; }
40
-
41
- /* Colorbar background (keep gradient intact) */
42
- [data-theme="dark"] .html-embed__card .colorbar .cbbg { fill: rgba(0,0,0,.25) !important; stroke: rgba(255,255,255,.2) !important; }
43
-
44
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app/src/styles/components/_table.css ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ .content-grid main table {
2
+ border-collapse: collapse;
3
+ table-layout: auto;
4
+ margin: 0;
5
+ }
6
+ .content-grid main th, .content-grid main td {
7
+ border-bottom: 1px solid var(--border-color);
8
+ padding: 6px 8px;
9
+ text-align: left;
10
+ font-size: 15px;
11
+ white-space: nowrap; /* prevent squashing; allow horizontal scroll instead */
12
+ }
13
+ .content-grid main thead th { border-bottom: 1px solid var(--border-color); }
14
+ .content-grid main thead th {
15
+ border-bottom: 1px solid var(--border-color);
16
+ }
17
+ .content-grid main thead th {
18
+ background: var(--table-header-bg);
19
+ padding-top: 10px;
20
+ padding-bottom: 10px;
21
+ font-weight: 600;
22
+ }
23
+
24
+ .content-grid main hr {
25
+ border: none;
26
+ border-bottom: 1px solid var(--border-color);
27
+ margin: var(--spacing-5) 0;
28
+ }
29
+
30
+ /* Scroll wrapper: keeps table 100% width but enables horizontal scroll when needed */
31
+ .content-grid main .table-scroll {
32
+ width: 100%;
33
+ overflow-x: auto;
34
+ -webkit-overflow-scrolling: touch;
35
+ border: 1px solid var(--border-color);
36
+ border-radius: var(--table-border-radius);
37
+ background: var(--surface-bg);
38
+ margin: 0 0 var(--block-spacing-y);
39
+ }
40
+ .content-grid main .table-scroll > table {
41
+ width: fit-content;
42
+ min-width: 100%;
43
+ max-width: none;
44
+ }
45
+ /* Vertical dividers between columns (no outer right border) */
46
+ .content-grid main .table-scroll > table th,
47
+ .content-grid main .table-scroll > table td {
48
+ border-right: 1px solid var(--border-color);
49
+ }
50
+ .content-grid main .table-scroll > table th:last-child,
51
+ .content-grid main .table-scroll > table td:last-child {
52
+ border-right: none;
53
+ }
54
+ .content-grid main .table-scroll > table thead th:first-child {
55
+ border-top-left-radius: var(--table-border-radius);
56
+ }
57
+ .content-grid main .table-scroll > table thead th:last-child {
58
+ border-top-right-radius: var(--table-border-radius);
59
+ }
60
+ .content-grid main .table-scroll > table tbody tr:last-child td:first-child {
61
+ border-bottom-left-radius: var(--table-border-radius);
62
+ }
63
+ .content-grid main .table-scroll > table tbody tr:last-child td:last-child {
64
+ border-bottom-right-radius: var(--table-border-radius);
65
+ }
66
+ /* Zebra striping for odd rows */
67
+ .content-grid main .table-scroll > table tbody tr:nth-child(odd) td {
68
+ background: var(--table-row-odd-bg);
69
+ }
70
+ /* Remove bottom border on last row */
71
+ .content-grid main .table-scroll > table tbody tr:last-child td {
72
+ border-bottom: none;
73
+ }
74
+
75
+ /* Accordion context: remove outer borders/radius and fit content flush */
76
+ .accordion .accordion__content .table-scroll {
77
+ border: none;
78
+ border-radius: 0;
79
+ margin: 0;
80
+ }
81
+ .accordion .accordion__content .table-scroll > table thead th:first-child,
82
+ .accordion .accordion__content .table-scroll > table thead th:last-child,
83
+ .accordion .accordion__content .table-scroll > table tbody tr:last-child td:first-child,
84
+ .accordion .accordion__content .table-scroll > table tbody tr:last-child td:last-child {
85
+ border-radius: 0;
86
+ }
87
+
88
+ /* Fallback for browsers without fit-content support */
89
+ @supports not (width: fit-content) {
90
+ .content-grid main .table-scroll > table {
91
+ width: max-content;
92
+ min-width: 100%;
93
+ }
94
+ }
95
+
app/src/styles/components/_tag.css ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ .tag-list { display: flex; flex-wrap: wrap; gap: 8px; margin: 8px 0 16px; }
2
+
3
+ .tag {
4
+ display: inline-flex;
5
+ align-items: center;
6
+ gap: 6px;
7
+ padding: 10px 16px;
8
+ font-size: 12px;
9
+ line-height: 1;
10
+ border-radius: 100px;
11
+ background: var(--surface-bg);
12
+ border: 1px solid var(--border-color);
13
+ color: var(--text-color);
14
+ }
app/src/styles/global.css CHANGED
@@ -1,56 +1,27 @@
1
  @import './_variables.css';
 
2
  @import './_base.css';
3
  @import './_layout.css';
4
- @import './components/_footer.css';
5
  @import './components/_code.css';
6
- @import './components/_poltly.css';
 
 
7
 
8
- /* Dark-mode form tweak */
9
- [data-theme="dark"] .plotly_input_container > select { background-color: #1a1f27; border-color: var(--border-color); color: var(--text-color); }
10
-
11
- [data-theme="dark"] .html-embed__card:not(.is-frameless) { background: #12151b; border-color: rgba(255,255,255,.15); }
12
- [data-theme="dark"] .right-aside .aside-card { background: #12151b; border-color: rgba(255,255,255,.15); }
13
- [data-theme="dark"] .content-grid main pre { background: #12151b; border-color: rgba(255,255,255,.15); }
14
- [data-theme="dark"] .toc nav { border-left-color: rgba(255,255,255,.15); }
15
- [data-theme="dark"] .distill-footer { border-top-color: rgba(255,255,255,.15); color: rgba(200,200,200,.8); }
16
- [data-theme="dark"] .citation { background: rgba(255,255,255,0.04); border-color: rgba(255,255,255,.15); color: rgba(200,200,200,1); }
17
- [data-theme="dark"] .citation a { color: rgba(255,255,255,0.75); }
18
-
19
- /* Opt-in zoomable images */
20
- img[data-zoomable] { cursor: zoom-in; }
21
- .medium-zoom--opened img[data-zoomable] { cursor: zoom-out; }
22
-
23
- /* Download button for img[data-downloadable] */
24
- figure.has-dl-btn { position: relative; }
25
- .dl-host { position: relative; }
26
- .img-dl-wrap { position: relative; display: inline-block; }
27
- .img-dl-btn {
28
- position: absolute;
29
- right: 8px;
30
- bottom: 8px;
31
- align-items: center;
32
- justify-content: center;
33
- width: 30px;
34
- height: 30px;
35
- border-radius: 6px;
36
- color: white;
37
- text-decoration: none;
38
- border: 1px solid rgba(255,255,255,0.25);
39
- z-index: var(--z-elevated);
40
- display: none;
41
  }
42
- .img-dl-btn svg { width: 18px; height: 18px; fill: currentColor; }
43
- .img-dl-wrap:hover .img-dl-btn { display: inline-flex; }
44
- [data-theme="dark"] .img-dl-btn { background: rgba(255,255,255,0.15); color: white; border-color: rgba(255,255,255,0.25); }
45
- [data-theme="dark"] .img-dl-btn:hover { background: rgba(255,255,255,0.25); }
46
-
47
- /* ============================================================================ */
48
- /* Theme Toggle button (moved from component) */
49
- /* ============================================================================ */
50
- #theme-toggle { display: inline-flex; align-items: center; gap: 8px; border: none; background: transparent; padding: 6px 10px; border-radius: 8px; cursor: pointer; margin: 12px 16px; color: var(--text-color) !important; }
51
- #theme-toggle .icon.dark { display: none; }
52
- [data-theme="dark"] #theme-toggle .icon.light { display: none; }
53
- [data-theme="dark"] #theme-toggle .icon.dark { display: inline; }
54
- #theme-toggle .icon { filter: none !important; }
55
-
56
 
 
 
 
 
 
1
  @import './_variables.css';
2
+ @import './_reset.css';
3
  @import './_base.css';
4
  @import './_layout.css';
5
+ @import './_print.css';
6
  @import './components/_code.css';
7
+ @import './components/_button.css';
8
+ @import './components/_table.css';
9
+ @import './components/_tag.css';
10
 
11
+ .demo-wide,
12
+ .demo-full-width {
13
+ display: grid;
14
+ place-items: center;
15
+ min-height: 150px;
16
+ color: var(--muted-color);
17
+ font-size: 12px;
18
+ border: 1px dashed var(--border-color);
19
+ border-radius: 8px;
20
+ background: var(--surface-bg);
21
+ margin-bottom: var(--block-spacing-y);
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
 
24
+ .mermaid {
25
+ background: none!important;
26
+ margin-bottom: var(--block-spacing-y) !important;
27
+ }