michael-guenther makram93 commited on
Commit
ef6c560
·
verified ·
1 Parent(s): d406962

add model to the vidore leaderboard (#27)

Browse files

- json result file for vidore (0410141cf1e8a8b2b103ec5bb160150e66330fda)
- fix: add vidore tag (07d331798d3f1237c85f1c2d19ddf87e25bdb725)


Co-authored-by: Mohammad Kalim Akram <[email protected]>

Files changed (2) hide show
  1. README.md +4 -0
  2. results.json +581 -0
README.md CHANGED
@@ -1,3 +1,7 @@
 
 
 
 
1
  <br><br>
2
 
3
  <p align="center">
 
1
+ ---
2
+ tags:
3
+ - vidore
4
+ ---
5
  <br><br>
6
 
7
  <p align="center">
results.json ADDED
@@ -0,0 +1,581 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "arxivqa_test_subsampled": {
3
+ "ndcg_at_1": 0.844,
4
+ "ndcg_at_3": 0.88524,
5
+ "ndcg_at_5": 0.88954,
6
+ "ndcg_at_10": 0.89512,
7
+ "ndcg_at_20": 0.90085,
8
+ "ndcg_at_50": 0.90479,
9
+ "ndcg_at_100": 0.90578,
10
+ "map_at_1": 0.844,
11
+ "map_at_3": 0.87467,
12
+ "map_at_5": 0.87717,
13
+ "map_at_10": 0.87933,
14
+ "map_at_20": 0.88099,
15
+ "map_at_50": 0.88161,
16
+ "map_at_100": 0.8817,
17
+ "recall_at_1": 0.844,
18
+ "recall_at_3": 0.916,
19
+ "recall_at_5": 0.926,
20
+ "recall_at_10": 0.944,
21
+ "recall_at_20": 0.966,
22
+ "recall_at_50": 0.986,
23
+ "recall_at_100": 0.992,
24
+ "precision_at_1": 0.844,
25
+ "precision_at_3": 0.30533,
26
+ "precision_at_5": 0.1852,
27
+ "precision_at_10": 0.0944,
28
+ "precision_at_20": 0.0483,
29
+ "precision_at_50": 0.01972,
30
+ "precision_at_100": 0.00992,
31
+ "mrr_at_1": 0.844,
32
+ "mrr_at_3": 0.8746666666666665,
33
+ "mrr_at_5": 0.8771666666666665,
34
+ "mrr_at_10": 0.8793301587301586,
35
+ "mrr_at_20": 0.880986183261183,
36
+ "mrr_at_50": 0.8816066058267283,
37
+ "mrr_at_100": 0.8816959272950264,
38
+ "naucs_at_1_max": 0.7413901379085128,
39
+ "naucs_at_1_std": 0.3454872013866209,
40
+ "naucs_at_1_diff1": 0.9600906830113787,
41
+ "naucs_at_3_max": 0.7713307545240329,
42
+ "naucs_at_3_std": 0.4801698457160663,
43
+ "naucs_at_3_diff1": 0.9489240140500664,
44
+ "naucs_at_5_max": 0.7514699573523106,
45
+ "naucs_at_5_std": 0.4375552022610836,
46
+ "naucs_at_5_diff1": 0.9526206879148043,
47
+ "naucs_at_10_max": 0.8086901427237575,
48
+ "naucs_at_10_std": 0.5144891289849284,
49
+ "naucs_at_10_diff1": 0.9513972255568919,
50
+ "naucs_at_20_max": 0.907453177349375,
51
+ "naucs_at_20_std": 0.5683802932937894,
52
+ "naucs_at_20_diff1": 0.9692425990003846,
53
+ "naucs_at_50_max": 0.8709483793517359,
54
+ "naucs_at_50_std": 0.7055488862211612,
55
+ "naucs_at_50_diff1": 0.9626517273576126,
56
+ "naucs_at_100_max": 0.8068394024276366,
57
+ "naucs_at_100_std": 0.7076330532212914,
58
+ "naucs_at_100_diff1": 0.9673202614378978
59
+ },
60
+ "docvqa_test_subsampled": {
61
+ "ndcg_at_1": 0.52328,
62
+ "ndcg_at_3": 0.5841,
63
+ "ndcg_at_5": 0.59975,
64
+ "ndcg_at_10": 0.62669,
65
+ "ndcg_at_20": 0.64245,
66
+ "ndcg_at_50": 0.65661,
67
+ "ndcg_at_100": 0.66492,
68
+ "map_at_1": 0.52328,
69
+ "map_at_3": 0.56911,
70
+ "map_at_5": 0.57786,
71
+ "map_at_10": 0.58881,
72
+ "map_at_20": 0.59317,
73
+ "map_at_50": 0.59548,
74
+ "map_at_100": 0.59622,
75
+ "recall_at_1": 0.52328,
76
+ "recall_at_3": 0.62749,
77
+ "recall_at_5": 0.66519,
78
+ "recall_at_10": 0.74945,
79
+ "recall_at_20": 0.81153,
80
+ "recall_at_50": 0.88248,
81
+ "recall_at_100": 0.93348,
82
+ "precision_at_1": 0.52328,
83
+ "precision_at_3": 0.20916,
84
+ "precision_at_5": 0.13304,
85
+ "precision_at_10": 0.07494,
86
+ "precision_at_20": 0.04058,
87
+ "precision_at_50": 0.01765,
88
+ "precision_at_100": 0.00933,
89
+ "mrr_at_1": 0.5232815964523282,
90
+ "mrr_at_3": 0.5691056910569108,
91
+ "mrr_at_5": 0.5778640059127865,
92
+ "mrr_at_10": 0.5888132193010243,
93
+ "mrr_at_20": 0.5931663069177401,
94
+ "mrr_at_50": 0.5954783504735428,
95
+ "mrr_at_100": 0.5962169799244146,
96
+ "naucs_at_1_max": 0.46089368028029637,
97
+ "naucs_at_1_std": 0.19359243300005127,
98
+ "naucs_at_1_diff1": 0.8483527783001977,
99
+ "naucs_at_3_max": 0.4640279399849662,
100
+ "naucs_at_3_std": 0.1814509120980464,
101
+ "naucs_at_3_diff1": 0.7719022256243834,
102
+ "naucs_at_5_max": 0.45716016762761796,
103
+ "naucs_at_5_std": 0.16428980258139747,
104
+ "naucs_at_5_diff1": 0.750196647594659,
105
+ "naucs_at_10_max": 0.3956528364820721,
106
+ "naucs_at_10_std": 0.09973122080056422,
107
+ "naucs_at_10_diff1": 0.7237863238311393,
108
+ "naucs_at_20_max": 0.35927664451426317,
109
+ "naucs_at_20_std": 0.09080366240903168,
110
+ "naucs_at_20_diff1": 0.6946736504983693,
111
+ "naucs_at_50_max": 0.3626447370884348,
112
+ "naucs_at_50_std": 0.2775120087087966,
113
+ "naucs_at_50_diff1": 0.6534710933108262,
114
+ "naucs_at_100_max": 0.32155287639122004,
115
+ "naucs_at_100_std": 0.3495021025151782,
116
+ "naucs_at_100_diff1": 0.6165810885563539
117
+ },
118
+ "infovqa_test_subsampled": {
119
+ "ndcg_at_1": 0.90283,
120
+ "ndcg_at_3": 0.93062,
121
+ "ndcg_at_5": 0.93567,
122
+ "ndcg_at_10": 0.93969,
123
+ "ndcg_at_20": 0.94324,
124
+ "ndcg_at_50": 0.94401,
125
+ "ndcg_at_100": 0.945,
126
+ "map_at_1": 0.90283,
127
+ "map_at_3": 0.92409,
128
+ "map_at_5": 0.92692,
129
+ "map_at_10": 0.92863,
130
+ "map_at_20": 0.92959,
131
+ "map_at_50": 0.9297,
132
+ "map_at_100": 0.92979,
133
+ "recall_at_1": 0.90283,
134
+ "recall_at_3": 0.94939,
135
+ "recall_at_5": 0.96154,
136
+ "recall_at_10": 0.97368,
137
+ "recall_at_20": 0.98785,
138
+ "recall_at_50": 0.9919,
139
+ "recall_at_100": 0.99798,
140
+ "precision_at_1": 0.90283,
141
+ "precision_at_3": 0.31646,
142
+ "precision_at_5": 0.19231,
143
+ "precision_at_10": 0.09737,
144
+ "precision_at_20": 0.04939,
145
+ "precision_at_50": 0.01984,
146
+ "precision_at_100": 0.00998,
147
+ "mrr_at_1": 0.902834008097166,
148
+ "mrr_at_3": 0.9240890688259108,
149
+ "mrr_at_5": 0.9269230769230767,
150
+ "mrr_at_10": 0.9286316753422016,
151
+ "mrr_at_20": 0.9295898610333593,
152
+ "mrr_at_50": 0.929699602843506,
153
+ "mrr_at_100": 0.929788457049907,
154
+ "naucs_at_1_max": 0.6026903076230651,
155
+ "naucs_at_1_std": 0.261936050485784,
156
+ "naucs_at_1_diff1": 0.9396804875719484,
157
+ "naucs_at_3_max": 0.7565375225904929,
158
+ "naucs_at_3_std": 0.45980620999702715,
159
+ "naucs_at_3_diff1": 0.9534218386220948,
160
+ "naucs_at_5_max": 0.8235249494008307,
161
+ "naucs_at_5_std": 0.5316999544043512,
162
+ "naucs_at_5_diff1": 0.9524604670358964,
163
+ "naucs_at_10_max": 0.8684766575602219,
164
+ "naucs_at_10_std": 0.5944713216706646,
165
+ "naucs_at_10_diff1": 0.9405654098266761,
166
+ "naucs_at_20_max": 0.7830887900175995,
167
+ "naucs_at_20_std": 0.5643438299512757,
168
+ "naucs_at_20_diff1": 0.8929919636352566,
169
+ "naucs_at_50_max": 0.7072835485426375,
170
+ "naucs_at_50_std": 0.5764614839135555,
171
+ "naucs_at_50_diff1": 0.8394879454528887,
172
+ "naucs_at_100_max": 1.0,
173
+ "naucs_at_100_std": 1.0,
174
+ "naucs_at_100_diff1": 1.0
175
+ },
176
+ "tabfquad_test_subsampled": {
177
+ "ndcg_at_1": 0.9,
178
+ "ndcg_at_3": 0.94685,
179
+ "ndcg_at_5": 0.95131,
180
+ "ndcg_at_10": 0.95366,
181
+ "ndcg_at_20": 0.95455,
182
+ "ndcg_at_50": 0.9553,
183
+ "ndcg_at_100": 0.9553,
184
+ "map_at_1": 0.9,
185
+ "map_at_3": 0.9369,
186
+ "map_at_5": 0.9394,
187
+ "map_at_10": 0.9404,
188
+ "map_at_20": 0.94063,
189
+ "map_at_50": 0.94077,
190
+ "map_at_100": 0.94077,
191
+ "recall_at_1": 0.9,
192
+ "recall_at_3": 0.975,
193
+ "recall_at_5": 0.98571,
194
+ "recall_at_10": 0.99286,
195
+ "recall_at_20": 0.99643,
196
+ "recall_at_50": 1.0,
197
+ "recall_at_100": 1.0,
198
+ "precision_at_1": 0.9,
199
+ "precision_at_3": 0.325,
200
+ "precision_at_5": 0.19714,
201
+ "precision_at_10": 0.09929,
202
+ "precision_at_20": 0.04982,
203
+ "precision_at_50": 0.02,
204
+ "precision_at_100": 0.01,
205
+ "mrr_at_1": 0.9,
206
+ "mrr_at_3": 0.936904761904762,
207
+ "mrr_at_5": 0.9394047619047617,
208
+ "mrr_at_10": 0.9403968253968255,
209
+ "mrr_at_20": 0.9406349206349207,
210
+ "mrr_at_50": 0.9407722832722833,
211
+ "mrr_at_100": 0.9407722832722833,
212
+ "naucs_at_1_max": 0.39284046952114193,
213
+ "naucs_at_1_std": 0.06274176337201544,
214
+ "naucs_at_1_diff1": 0.9321395224756563,
215
+ "naucs_at_3_max": 0.98132586367881,
216
+ "naucs_at_3_std": 0.9042950513538718,
217
+ "naucs_at_3_diff1": 0.98132586367881,
218
+ "naucs_at_5_max": 0.967320261437913,
219
+ "naucs_at_5_std": 0.8978758169934754,
220
+ "naucs_at_5_diff1": 1.0,
221
+ "naucs_at_10_max": 1.0,
222
+ "naucs_at_10_std": 0.9346405228758269,
223
+ "naucs_at_10_diff1": 1.0,
224
+ "naucs_at_20_max": 1.0,
225
+ "naucs_at_20_std": 1.0,
226
+ "naucs_at_20_diff1": 1.0,
227
+ "naucs_at_50_max": 1.0,
228
+ "naucs_at_50_std": 1.0,
229
+ "naucs_at_50_diff1": 1.0,
230
+ "naucs_at_100_max": 1.0,
231
+ "naucs_at_100_std": 1.0,
232
+ "naucs_at_100_diff1": 1.0
233
+ },
234
+ "tatdqa_test": {
235
+ "ndcg_at_1": 0.68834,
236
+ "ndcg_at_3": 0.7834,
237
+ "ndcg_at_5": 0.80344,
238
+ "ndcg_at_10": 0.81851,
239
+ "ndcg_at_20": 0.82469,
240
+ "ndcg_at_50": 0.82852,
241
+ "ndcg_at_100": 0.82981,
242
+ "map_at_1": 0.68834,
243
+ "map_at_3": 0.76073,
244
+ "map_at_5": 0.772,
245
+ "map_at_10": 0.7783,
246
+ "map_at_20": 0.78002,
247
+ "map_at_50": 0.78067,
248
+ "map_at_100": 0.78079,
249
+ "recall_at_1": 0.68834,
250
+ "recall_at_3": 0.84872,
251
+ "recall_at_5": 0.89672,
252
+ "recall_at_10": 0.94289,
253
+ "recall_at_20": 0.96719,
254
+ "recall_at_50": 0.98603,
255
+ "recall_at_100": 0.99392,
256
+ "precision_at_1": 0.68834,
257
+ "precision_at_3": 0.28291,
258
+ "precision_at_5": 0.17934,
259
+ "precision_at_10": 0.09429,
260
+ "precision_at_20": 0.04836,
261
+ "precision_at_50": 0.01972,
262
+ "precision_at_100": 0.00994,
263
+ "mrr_at_1": 0.6865127582017011,
264
+ "mrr_at_3": 0.7598217901984609,
265
+ "mrr_at_5": 0.7710307816929933,
266
+ "mrr_at_10": 0.7773322532739296,
267
+ "mrr_at_20": 0.7790656715075932,
268
+ "mrr_at_50": 0.7797137179788176,
269
+ "mrr_at_100": 0.7798294471430899,
270
+ "naucs_at_1_max": 0.19289339347399329,
271
+ "naucs_at_1_std": -0.05373436574034402,
272
+ "naucs_at_1_diff1": 0.8118815353915732,
273
+ "naucs_at_3_max": 0.24444248974914928,
274
+ "naucs_at_3_std": 0.012951438245694854,
275
+ "naucs_at_3_diff1": 0.7252009696977523,
276
+ "naucs_at_5_max": 0.27477480629269946,
277
+ "naucs_at_5_std": 0.10687833140288663,
278
+ "naucs_at_5_diff1": 0.7019146338300569,
279
+ "naucs_at_10_max": 0.23474834180340118,
280
+ "naucs_at_10_std": 0.13375117651376378,
281
+ "naucs_at_10_diff1": 0.6766342016471449,
282
+ "naucs_at_20_max": 0.3762582961131715,
283
+ "naucs_at_20_std": 0.29216428469292166,
284
+ "naucs_at_20_diff1": 0.6564671335087516,
285
+ "naucs_at_50_max": 0.4691053847445,
286
+ "naucs_at_50_std": 0.4359718488363951,
287
+ "naucs_at_50_diff1": 0.7152604718494652,
288
+ "naucs_at_100_max": 0.5259975902909616,
289
+ "naucs_at_100_std": 0.651086653120611,
290
+ "naucs_at_100_diff1": 0.7663843453532901
291
+ },
292
+ "shiftproject_test": {
293
+ "ndcg_at_1": 0.85,
294
+ "ndcg_at_3": 0.91917,
295
+ "ndcg_at_5": 0.92347,
296
+ "ndcg_at_10": 0.92949,
297
+ "ndcg_at_20": 0.92949,
298
+ "ndcg_at_50": 0.92949,
299
+ "ndcg_at_100": 0.92949,
300
+ "map_at_1": 0.85,
301
+ "map_at_3": 0.90167,
302
+ "map_at_5": 0.90417,
303
+ "map_at_10": 0.90639,
304
+ "map_at_20": 0.90639,
305
+ "map_at_50": 0.90639,
306
+ "map_at_100": 0.90639,
307
+ "recall_at_1": 0.85,
308
+ "recall_at_3": 0.97,
309
+ "recall_at_5": 0.98,
310
+ "recall_at_10": 1.0,
311
+ "recall_at_20": 1.0,
312
+ "recall_at_50": 1.0,
313
+ "recall_at_100": 1.0,
314
+ "precision_at_1": 0.85,
315
+ "precision_at_3": 0.32333,
316
+ "precision_at_5": 0.196,
317
+ "precision_at_10": 0.1,
318
+ "precision_at_20": 0.05,
319
+ "precision_at_50": 0.02,
320
+ "precision_at_100": 0.01,
321
+ "mrr_at_1": 0.85,
322
+ "mrr_at_3": 0.9016666666666666,
323
+ "mrr_at_5": 0.9041666666666666,
324
+ "mrr_at_10": 0.9063888888888889,
325
+ "mrr_at_20": 0.9063888888888889,
326
+ "mrr_at_50": 0.9063888888888889,
327
+ "mrr_at_100": 0.9063888888888889,
328
+ "naucs_at_1_max": 0.029189716889034732,
329
+ "naucs_at_1_std": -0.37507321835340074,
330
+ "naucs_at_1_diff1": 0.7931012040351454,
331
+ "naucs_at_3_max": 0.5589791472144446,
332
+ "naucs_at_3_std": 0.09056956115779448,
333
+ "naucs_at_3_diff1": 0.9564270152505466,
334
+ "naucs_at_5_max": 0.3384687208216692,
335
+ "naucs_at_5_std": -0.2987861811391239,
336
+ "naucs_at_5_diff1": 1.0,
337
+ "naucs_at_10_max": 1.0,
338
+ "naucs_at_10_std": 1.0,
339
+ "naucs_at_10_diff1": 1.0,
340
+ "naucs_at_20_max": 1.0,
341
+ "naucs_at_20_std": 1.0,
342
+ "naucs_at_20_diff1": 1.0,
343
+ "naucs_at_50_max": null,
344
+ "naucs_at_50_std": null,
345
+ "naucs_at_50_diff1": null,
346
+ "naucs_at_100_max": null,
347
+ "naucs_at_100_std": null,
348
+ "naucs_at_100_diff1": null
349
+ },
350
+ "syntheticDocQA_artificial_intelligence_test": {
351
+ "ndcg_at_1": 0.98,
352
+ "ndcg_at_3": 0.99262,
353
+ "ndcg_at_5": 0.99262,
354
+ "ndcg_at_10": 0.99262,
355
+ "ndcg_at_20": 0.99262,
356
+ "ndcg_at_50": 0.99262,
357
+ "ndcg_at_100": 0.99262,
358
+ "map_at_1": 0.98,
359
+ "map_at_3": 0.99,
360
+ "map_at_5": 0.99,
361
+ "map_at_10": 0.99,
362
+ "map_at_20": 0.99,
363
+ "map_at_50": 0.99,
364
+ "map_at_100": 0.99,
365
+ "recall_at_1": 0.98,
366
+ "recall_at_3": 1.0,
367
+ "recall_at_5": 1.0,
368
+ "recall_at_10": 1.0,
369
+ "recall_at_20": 1.0,
370
+ "recall_at_50": 1.0,
371
+ "recall_at_100": 1.0,
372
+ "precision_at_1": 0.98,
373
+ "precision_at_3": 0.33333,
374
+ "precision_at_5": 0.2,
375
+ "precision_at_10": 0.1,
376
+ "precision_at_20": 0.05,
377
+ "precision_at_50": 0.02,
378
+ "precision_at_100": 0.01,
379
+ "mrr_at_1": 0.98,
380
+ "mrr_at_3": 0.99,
381
+ "mrr_at_5": 0.99,
382
+ "mrr_at_10": 0.99,
383
+ "mrr_at_20": 0.99,
384
+ "mrr_at_50": 0.99,
385
+ "mrr_at_100": 0.99,
386
+ "naucs_at_1_max": 0.540149393090569,
387
+ "naucs_at_1_std": 0.3384687208216605,
388
+ "naucs_at_1_diff1": 0.9346405228758133,
389
+ "naucs_at_3_max": 1.0,
390
+ "naucs_at_3_std": 1.0,
391
+ "naucs_at_3_diff1": 1.0,
392
+ "naucs_at_5_max": 1.0,
393
+ "naucs_at_5_std": 1.0,
394
+ "naucs_at_5_diff1": 1.0,
395
+ "naucs_at_10_max": 1.0,
396
+ "naucs_at_10_std": 1.0,
397
+ "naucs_at_10_diff1": 1.0,
398
+ "naucs_at_20_max": 1.0,
399
+ "naucs_at_20_std": 1.0,
400
+ "naucs_at_20_diff1": 1.0,
401
+ "naucs_at_50_max": null,
402
+ "naucs_at_50_std": null,
403
+ "naucs_at_50_diff1": null,
404
+ "naucs_at_100_max": null,
405
+ "naucs_at_100_std": null,
406
+ "naucs_at_100_diff1": null
407
+ },
408
+ "syntheticDocQA_energy_test": {
409
+ "ndcg_at_1": 0.95,
410
+ "ndcg_at_3": 0.96762,
411
+ "ndcg_at_5": 0.96762,
412
+ "ndcg_at_10": 0.97118,
413
+ "ndcg_at_20": 0.97118,
414
+ "ndcg_at_50": 0.973,
415
+ "ndcg_at_100": 0.973,
416
+ "map_at_1": 0.95,
417
+ "map_at_3": 0.96333,
418
+ "map_at_5": 0.96333,
419
+ "map_at_10": 0.965,
420
+ "map_at_20": 0.965,
421
+ "map_at_50": 0.96523,
422
+ "map_at_100": 0.96523,
423
+ "recall_at_1": 0.95,
424
+ "recall_at_3": 0.98,
425
+ "recall_at_5": 0.98,
426
+ "recall_at_10": 0.99,
427
+ "recall_at_20": 0.99,
428
+ "recall_at_50": 1.0,
429
+ "recall_at_100": 1.0,
430
+ "precision_at_1": 0.95,
431
+ "precision_at_3": 0.32667,
432
+ "precision_at_5": 0.196,
433
+ "precision_at_10": 0.099,
434
+ "precision_at_20": 0.0495,
435
+ "precision_at_50": 0.02,
436
+ "precision_at_100": 0.01,
437
+ "mrr_at_1": 0.95,
438
+ "mrr_at_3": 0.9633333333333333,
439
+ "mrr_at_5": 0.9633333333333333,
440
+ "mrr_at_10": 0.965,
441
+ "mrr_at_20": 0.965,
442
+ "mrr_at_50": 0.9652272727272727,
443
+ "mrr_at_100": 0.9652272727272727,
444
+ "naucs_at_1_max": 0.42726423902894384,
445
+ "naucs_at_1_std": -0.4889822595704953,
446
+ "naucs_at_1_diff1": 1.0,
447
+ "naucs_at_3_max": 0.6136788048552655,
448
+ "naucs_at_3_std": -0.6909430438842241,
449
+ "naucs_at_3_diff1": 1.0,
450
+ "naucs_at_5_max": 0.6136788048552745,
451
+ "naucs_at_5_std": -0.690943043884218,
452
+ "naucs_at_5_diff1": 1.0,
453
+ "naucs_at_10_max": 0.8692810457516413,
454
+ "naucs_at_10_std": 0.35807656395891135,
455
+ "naucs_at_10_diff1": 1.0,
456
+ "naucs_at_20_max": 0.8692810457516413,
457
+ "naucs_at_20_std": 0.35807656395891135,
458
+ "naucs_at_20_diff1": 1.0,
459
+ "naucs_at_50_max": null,
460
+ "naucs_at_50_std": null,
461
+ "naucs_at_50_diff1": null,
462
+ "naucs_at_100_max": null,
463
+ "naucs_at_100_std": null,
464
+ "naucs_at_100_diff1": null
465
+ },
466
+ "syntheticDocQA_government_reports_test": {
467
+ "ndcg_at_1": 0.93,
468
+ "ndcg_at_3": 0.96524,
469
+ "ndcg_at_5": 0.96954,
470
+ "ndcg_at_10": 0.96954,
471
+ "ndcg_at_20": 0.96954,
472
+ "ndcg_at_50": 0.96954,
473
+ "ndcg_at_100": 0.96954,
474
+ "map_at_1": 0.93,
475
+ "map_at_3": 0.95667,
476
+ "map_at_5": 0.95917,
477
+ "map_at_10": 0.95917,
478
+ "map_at_20": 0.95917,
479
+ "map_at_50": 0.95917,
480
+ "map_at_100": 0.95917,
481
+ "recall_at_1": 0.93,
482
+ "recall_at_3": 0.99,
483
+ "recall_at_5": 1.0,
484
+ "recall_at_10": 1.0,
485
+ "recall_at_20": 1.0,
486
+ "recall_at_50": 1.0,
487
+ "recall_at_100": 1.0,
488
+ "precision_at_1": 0.93,
489
+ "precision_at_3": 0.33,
490
+ "precision_at_5": 0.2,
491
+ "precision_at_10": 0.1,
492
+ "precision_at_20": 0.05,
493
+ "precision_at_50": 0.02,
494
+ "precision_at_100": 0.01,
495
+ "mrr_at_1": 0.93,
496
+ "mrr_at_3": 0.9566666666666667,
497
+ "mrr_at_5": 0.9591666666666667,
498
+ "mrr_at_10": 0.9591666666666667,
499
+ "mrr_at_20": 0.9591666666666667,
500
+ "mrr_at_50": 0.9591666666666667,
501
+ "mrr_at_100": 0.9591666666666667,
502
+ "naucs_at_1_max": 0.6809390422835813,
503
+ "naucs_at_1_std": 0.5458850206749362,
504
+ "naucs_at_1_diff1": 0.9229691876750709,
505
+ "naucs_at_3_max": 1.0,
506
+ "naucs_at_3_std": 1.0,
507
+ "naucs_at_3_diff1": 1.0,
508
+ "naucs_at_5_max": 1.0,
509
+ "naucs_at_5_std": 1.0,
510
+ "naucs_at_5_diff1": 1.0,
511
+ "naucs_at_10_max": 1.0,
512
+ "naucs_at_10_std": 1.0,
513
+ "naucs_at_10_diff1": 1.0,
514
+ "naucs_at_20_max": 1.0,
515
+ "naucs_at_20_std": 1.0,
516
+ "naucs_at_20_diff1": 1.0,
517
+ "naucs_at_50_max": null,
518
+ "naucs_at_50_std": null,
519
+ "naucs_at_50_diff1": null,
520
+ "naucs_at_100_max": null,
521
+ "naucs_at_100_std": null,
522
+ "naucs_at_100_diff1": null
523
+ },
524
+ "syntheticDocQA_healthcare_industry_test": {
525
+ "ndcg_at_1": 0.96,
526
+ "ndcg_at_3": 0.98393,
527
+ "ndcg_at_5": 0.98393,
528
+ "ndcg_at_10": 0.98393,
529
+ "ndcg_at_20": 0.98393,
530
+ "ndcg_at_50": 0.98393,
531
+ "ndcg_at_100": 0.98393,
532
+ "map_at_1": 0.96,
533
+ "map_at_3": 0.97833,
534
+ "map_at_5": 0.97833,
535
+ "map_at_10": 0.97833,
536
+ "map_at_20": 0.97833,
537
+ "map_at_50": 0.97833,
538
+ "map_at_100": 0.97833,
539
+ "recall_at_1": 0.96,
540
+ "recall_at_3": 1.0,
541
+ "recall_at_5": 1.0,
542
+ "recall_at_10": 1.0,
543
+ "recall_at_20": 1.0,
544
+ "recall_at_50": 1.0,
545
+ "recall_at_100": 1.0,
546
+ "precision_at_1": 0.96,
547
+ "precision_at_3": 0.33333,
548
+ "precision_at_5": 0.2,
549
+ "precision_at_10": 0.1,
550
+ "precision_at_20": 0.05,
551
+ "precision_at_50": 0.02,
552
+ "precision_at_100": 0.01,
553
+ "mrr_at_1": 0.96,
554
+ "mrr_at_3": 0.9783333333333333,
555
+ "mrr_at_5": 0.9783333333333333,
556
+ "mrr_at_10": 0.9783333333333333,
557
+ "mrr_at_20": 0.9783333333333333,
558
+ "mrr_at_50": 0.9783333333333333,
559
+ "mrr_at_100": 0.9783333333333333,
560
+ "naucs_at_1_max": 0.7047152194211012,
561
+ "naucs_at_1_std": 0.32037815126050734,
562
+ "naucs_at_1_diff1": 1.0,
563
+ "naucs_at_3_max": 1.0,
564
+ "naucs_at_3_std": 1.0,
565
+ "naucs_at_3_diff1": 1.0,
566
+ "naucs_at_5_max": 1.0,
567
+ "naucs_at_5_std": 1.0,
568
+ "naucs_at_5_diff1": 1.0,
569
+ "naucs_at_10_max": 1.0,
570
+ "naucs_at_10_std": 1.0,
571
+ "naucs_at_10_diff1": 1.0,
572
+ "naucs_at_20_max": 1.0,
573
+ "naucs_at_20_std": 1.0,
574
+ "naucs_at_20_diff1": 1.0,
575
+ "naucs_at_50_max": null,
576
+ "naucs_at_50_std": null,
577
+ "naucs_at_50_diff1": null,
578
+ "naucs_at_100_max": null,
579
+ "naucs_at_100_std": null,
580
+ "naucs_at_100_diff1": null
581
+ }