Dataset Viewer
images
images listlengths 1
1
| data_source
stringclasses 1
value | reward_model
dict | extra_info
dict | prompt
listlengths 2
2
| ability
stringlengths 7
31
| env_name
stringclasses 1
value |
|---|---|---|---|---|---|---|
infovqa_augmented
|
{
"ground_truth": "Tony Blair."
}
|
{
"all_answers": [
"Tony Blair."
],
"answer": "Tony Blair.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_0e373ef693ab6534",
"index": "infovqa_infovqa_000000_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "0e373ef693ab65342b07a76926d4b3ce475306b37679d774f79ab4fc25619fa7",
"original_question_id": "infovqa_000000",
"question": "What is the name of the famous person who was thrown with condoms?\nKeep it brief.",
"question_id": "infovqa_000000"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the name of the famous person who was thrown with condoms?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Tony Blair."
}
|
{
"all_answers": [
"Tony Blair."
],
"answer": "Tony Blair.",
"augmentation_index": 1,
"augmentation_type": "rot180",
"data_split": "train",
"doc_id": "Infographic-VQA_0e373ef693ab6534",
"index": "infovqa_infovqa_000000_aug1_rot180",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "0e373ef693ab65342b07a76926d4b3ce475306b37679d774f79ab4fc25619fa7",
"original_question_id": "infovqa_000000",
"question": "What is the name of the famous person who was thrown with condoms?\nKeep it brief.",
"question_id": "infovqa_000000"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the name of the famous person who was thrown with condoms?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_rot180
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Tony Blair."
}
|
{
"all_answers": [
"Tony Blair."
],
"answer": "Tony Blair.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_0e373ef693ab6534",
"index": "infovqa_infovqa_000000_aug2_flip_h_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "0e373ef693ab65342b07a76926d4b3ce475306b37679d774f79ab4fc25619fa7",
"original_question_id": "infovqa_000000",
"question": "What is the name of the famous person who was thrown with condoms?\nKeep it brief.",
"question_id": "infovqa_000000"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat is the name of the famous person who was thrown with condoms?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1964."
}
|
{
"all_answers": [
"1964."
],
"answer": "1964.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000001_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000001",
"question": "in which year was the skateboard the longest\nAnswer briefly.",
"question_id": "infovqa_000001"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nin which year was the skateboard the longest\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1964."
}
|
{
"all_answers": [
"1964."
],
"answer": "1964.",
"augmentation_index": 1,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000001_aug1_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000001",
"question": "in which year was the skateboard the longest\nAnswer briefly.",
"question_id": "infovqa_000001"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nin which year was the skateboard the longest\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1964."
}
|
{
"all_answers": [
"1964."
],
"answer": "1964.",
"augmentation_index": 2,
"augmentation_type": "rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000001_aug2_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000001",
"question": "in which year was the skateboard the longest\nAnswer briefly.",
"question_id": "infovqa_000001"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nin which year was the skateboard the longest\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Road rider crusier."
}
|
{
"all_answers": [
"Road rider crusier."
],
"answer": "Road rider crusier.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000002_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000002",
"question": "what was the name of the skateboard with precision bearings\nQuick response, please.",
"question_id": "infovqa_000002"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat was the name of the skateboard with precision bearings\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Road rider crusier."
}
|
{
"all_answers": [
"Road rider crusier."
],
"answer": "Road rider crusier.",
"augmentation_index": 1,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000002_aug1_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000002",
"question": "what was the name of the skateboard with precision bearings\nQuick response, please.",
"question_id": "infovqa_000002"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat was the name of the skateboard with precision bearings\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Road rider crusier."
}
|
{
"all_answers": [
"Road rider crusier."
],
"answer": "Road rider crusier.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000002_aug2_flip_h_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000002",
"question": "what was the name of the skateboard with precision bearings\nQuick response, please.",
"question_id": "infovqa_000002"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat was the name of the skateboard with precision bearings\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "10."
}
|
{
"all_answers": [
"10."
],
"answer": "10.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000003_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000003",
"question": "How many years did it take after 1990 for the new design\nShort answer required.",
"question_id": "infovqa_000003"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nHow many years did it take after 1990 for the new design\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "10."
}
|
{
"all_answers": [
"10."
],
"answer": "10.",
"augmentation_index": 1,
"augmentation_type": "flip_v+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000003_aug1_flip_v_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000003",
"question": "How many years did it take after 1990 for the new design\nShort answer required.",
"question_id": "infovqa_000003"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nHow many years did it take after 1990 for the new design\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_flip_v_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "10."
}
|
{
"all_answers": [
"10."
],
"answer": "10.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000003_aug2_flip_h_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000003",
"question": "How many years did it take after 1990 for the new design\nShort answer required.",
"question_id": "infovqa_000003"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nHow many years did it take after 1990 for the new design\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_flip_h_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "G and S Fiberflex Pintail."
}
|
{
"all_answers": [
"G and S Fiberflex Pintail."
],
"answer": "G and S Fiberflex Pintail.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000004_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000004",
"question": "What was the name of the board introduced in 1964\nConcise answer only.",
"question_id": "infovqa_000004"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat was the name of the board introduced in 1964\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "G and S Fiberflex Pintail."
}
|
{
"all_answers": [
"G and S Fiberflex Pintail."
],
"answer": "G and S Fiberflex Pintail.",
"augmentation_index": 1,
"augmentation_type": "rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000004_aug1_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000004",
"question": "What was the name of the board introduced in 1964\nConcise answer only.",
"question_id": "infovqa_000004"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat was the name of the board introduced in 1964\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "G and S Fiberflex Pintail."
}
|
{
"all_answers": [
"G and S Fiberflex Pintail."
],
"answer": "G and S Fiberflex Pintail.",
"augmentation_index": 2,
"augmentation_type": "rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000004_aug2_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000004",
"question": "What was the name of the board introduced in 1964\nConcise answer only.",
"question_id": "infovqa_000004"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhat was the name of the board introduced in 1964\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "White."
}
|
{
"all_answers": [
"White."
],
"answer": "White.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000005_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000005",
"question": "what is the colour of all the boards, white or blue?\nQuick response, please.",
"question_id": "infovqa_000005"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat is the colour of all the boards, white or blue?\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "White."
}
|
{
"all_answers": [
"White."
],
"answer": "White.",
"augmentation_index": 1,
"augmentation_type": "flip_v+rot180",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000005_aug1_flip_v_rot180",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000005",
"question": "what is the colour of all the boards, white or blue?\nQuick response, please.",
"question_id": "infovqa_000005"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat is the colour of all the boards, white or blue?\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_v_rot180
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "White."
}
|
{
"all_answers": [
"White."
],
"answer": "White.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000005_aug2_flip_h_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000005",
"question": "what is the colour of all the boards, white or blue?\nQuick response, please.",
"question_id": "infovqa_000005"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat is the colour of all the boards, white or blue?\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1980."
}
|
{
"all_answers": [
"1980."
],
"answer": "1980.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000006_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000006",
"question": "when was the old school fishtail introduced?\nKeep it brief.",
"question_id": "infovqa_000006"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhen was the old school fishtail introduced?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1980."
}
|
{
"all_answers": [
"1980."
],
"answer": "1980.",
"augmentation_index": 1,
"augmentation_type": "rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000006_aug1_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000006",
"question": "when was the old school fishtail introduced?\nKeep it brief.",
"question_id": "infovqa_000006"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhen was the old school fishtail introduced?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1980."
}
|
{
"all_answers": [
"1980."
],
"answer": "1980.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000006_aug2_flip_h_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000006",
"question": "when was the old school fishtail introduced?\nKeep it brief.",
"question_id": "infovqa_000006"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhen was the old school fishtail introduced?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_flip_h_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1960."
}
|
{
"all_answers": [
"1960."
],
"answer": "1960.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000007_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000007",
"question": "when was nash shark introduced?\nAnswer briefly.",
"question_id": "infovqa_000007"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhen was nash shark introduced?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1960."
}
|
{
"all_answers": [
"1960."
],
"answer": "1960.",
"augmentation_index": 1,
"augmentation_type": "flip_v+rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000007_aug1_flip_v_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000007",
"question": "when was nash shark introduced?\nAnswer briefly.",
"question_id": "infovqa_000007"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhen was nash shark introduced?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_flip_v_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "1960."
}
|
{
"all_answers": [
"1960."
],
"answer": "1960.",
"augmentation_index": 2,
"augmentation_type": "flip_v+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_24e22b1bfebd454f",
"index": "infovqa_infovqa_000007_aug2_flip_v_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "24e22b1bfebd454f9d95400da2bd86f73f7fd9d430dcb0a869d0fa6e2e061018",
"original_question_id": "infovqa_000007",
"question": "when was nash shark introduced?\nAnswer briefly.",
"question_id": "infovqa_000007"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhen was nash shark introduced?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_flip_v_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "12."
}
|
{
"all_answers": [
"12."
],
"answer": "12.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000008_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000008",
"question": "how many enemies does the doctor have\nShort answer required.",
"question_id": "infovqa_000008"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nhow many enemies does the doctor have\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "12."
}
|
{
"all_answers": [
"12."
],
"answer": "12.",
"augmentation_index": 1,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000008_aug1_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000008",
"question": "how many enemies does the doctor have\nShort answer required.",
"question_id": "infovqa_000008"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nhow many enemies does the doctor have\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "12."
}
|
{
"all_answers": [
"12."
],
"answer": "12.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000008_aug2_flip_h_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000008",
"question": "how many enemies does the doctor have\nShort answer required.",
"question_id": "infovqa_000008"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nhow many enemies does the doctor have\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical_flip_h_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "The skarasen."
}
|
{
"all_answers": [
"The skarasen."
],
"answer": "The skarasen.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000009_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000009",
"question": "who is often mistaken for the lock ness monster\nConcise answer only.",
"question_id": "infovqa_000009"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho is often mistaken for the lock ness monster\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "The skarasen."
}
|
{
"all_answers": [
"The skarasen."
],
"answer": "The skarasen.",
"augmentation_index": 1,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000009_aug1_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000009",
"question": "who is often mistaken for the lock ness monster\nConcise answer only.",
"question_id": "infovqa_000009"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho is often mistaken for the lock ness monster\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "The skarasen."
}
|
{
"all_answers": [
"The skarasen."
],
"answer": "The skarasen.",
"augmentation_index": 2,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000009_aug2_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000009",
"question": "who is often mistaken for the lock ness monster\nConcise answer only.",
"question_id": "infovqa_000009"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho is often mistaken for the lock ness monster\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Ice warriors."
}
|
{
"all_answers": [
"Ice warriors."
],
"answer": "Ice warriors.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000010_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000010",
"question": "who are extremely sensitive to heat\nConcise answer only.",
"question_id": "infovqa_000010"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho are extremely sensitive to heat\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Ice warriors."
}
|
{
"all_answers": [
"Ice warriors."
],
"answer": "Ice warriors.",
"augmentation_index": 1,
"augmentation_type": "rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000010_aug1_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000010",
"question": "who are extremely sensitive to heat\nConcise answer only.",
"question_id": "infovqa_000010"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho are extremely sensitive to heat\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Ice warriors."
}
|
{
"all_answers": [
"Ice warriors."
],
"answer": "Ice warriors.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000010_aug2_flip_h_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000010",
"question": "who are extremely sensitive to heat\nConcise answer only.",
"question_id": "infovqa_000010"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho are extremely sensitive to heat\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "10."
}
|
{
"all_answers": [
"10."
],
"answer": "10.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000011_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000011",
"question": "the enemies identified are in a period of how many years\nKeep it brief.",
"question_id": "infovqa_000011"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nthe enemies identified are in a period of how many years\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "10."
}
|
{
"all_answers": [
"10."
],
"answer": "10.",
"augmentation_index": 1,
"augmentation_type": "rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000011_aug1_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000011",
"question": "the enemies identified are in a period of how many years\nKeep it brief.",
"question_id": "infovqa_000011"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nthe enemies identified are in a period of how many years\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "10."
}
|
{
"all_answers": [
"10."
],
"answer": "10.",
"augmentation_index": 2,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000011_aug2_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000011",
"question": "the enemies identified are in a period of how many years\nKeep it brief.",
"question_id": "infovqa_000011"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nthe enemies identified are in a period of how many years\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_temporal_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Blue."
}
|
{
"all_answers": [
"Blue."
],
"answer": "Blue.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000012_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000012",
"question": "what is the colour of the police box, blue, red?\nBe succinct.",
"question_id": "infovqa_000012"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat is the colour of the police box, blue, red?\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Blue."
}
|
{
"all_answers": [
"Blue."
],
"answer": "Blue.",
"augmentation_index": 1,
"augmentation_type": "rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000012_aug1_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000012",
"question": "what is the colour of the police box, blue, red?\nBe succinct.",
"question_id": "infovqa_000012"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat is the colour of the police box, blue, red?\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Blue."
}
|
{
"all_answers": [
"Blue."
],
"answer": "Blue.",
"augmentation_index": 2,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000012_aug2_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000012",
"question": "what is the colour of the police box, blue, red?\nBe succinct.",
"question_id": "infovqa_000012"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhat is the colour of the police box, blue, red?\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Sontarans."
}
|
{
"all_answers": [
"Sontarans."
],
"answer": "Sontarans.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000013_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000013",
"question": "who is holding a helmet in his hand?\nQuick response, please.",
"question_id": "infovqa_000013"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho is holding a helmet in his hand?\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Sontarans."
}
|
{
"all_answers": [
"Sontarans."
],
"answer": "Sontarans.",
"augmentation_index": 1,
"augmentation_type": "rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000013_aug1_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000013",
"question": "who is holding a helmet in his hand?\nQuick response, please.",
"question_id": "infovqa_000013"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho is holding a helmet in his hand?\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Sontarans."
}
|
{
"all_answers": [
"Sontarans."
],
"answer": "Sontarans.",
"augmentation_index": 2,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_84ddf5ccb6264b23",
"index": "infovqa_infovqa_000013_aug2_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "84ddf5ccb6264b23324ef25ad0131dcbcad80fda3c9d67ab4a4098155a8505b8",
"original_question_id": "infovqa_000013",
"question": "who is holding a helmet in his hand?\nQuick response, please.",
"question_id": "infovqa_000013"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwho is holding a helmet in his hand?\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Tim Hortons."
}
|
{
"all_answers": [
"Tim Hortons."
],
"answer": "Tim Hortons.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000014_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000014",
"question": "where should I eat if I am in Canada\nShort answer required.",
"question_id": "infovqa_000014"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I am in Canada\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Tim Hortons."
}
|
{
"all_answers": [
"Tim Hortons."
],
"answer": "Tim Hortons.",
"augmentation_index": 1,
"augmentation_type": "rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000014_aug1_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000014",
"question": "where should I eat if I am in Canada\nShort answer required.",
"question_id": "infovqa_000014"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I am in Canada\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Tim Hortons."
}
|
{
"all_answers": [
"Tim Hortons."
],
"answer": "Tim Hortons.",
"augmentation_index": 2,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000014_aug2_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000014",
"question": "where should I eat if I am in Canada\nShort answer required.",
"question_id": "infovqa_000014"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I am in Canada\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Taco bell."
}
|
{
"all_answers": [
"Taco bell."
],
"answer": "Taco bell.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000015_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000015",
"question": "where should I eat if I dont have more than $3\nAnswer briefly.",
"question_id": "infovqa_000015"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I dont have more than $3\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Taco bell."
}
|
{
"all_answers": [
"Taco bell."
],
"answer": "Taco bell.",
"augmentation_index": 1,
"augmentation_type": "flip_v+rot180",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000015_aug1_flip_v_rot180",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000015",
"question": "where should I eat if I dont have more than $3\nAnswer briefly.",
"question_id": "infovqa_000015"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I dont have more than $3\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_v_rot180
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Taco bell."
}
|
{
"all_answers": [
"Taco bell."
],
"answer": "Taco bell.",
"augmentation_index": 2,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000015_aug2_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000015",
"question": "where should I eat if I dont have more than $3\nAnswer briefly.",
"question_id": "infovqa_000015"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I dont have more than $3\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Burger King."
}
|
{
"all_answers": [
"Burger King."
],
"answer": "Burger King.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000016_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000016",
"question": "where should I eat if I am not older than 16?\nKeep it brief.",
"question_id": "infovqa_000016"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I am not older than 16?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Burger King."
}
|
{
"all_answers": [
"Burger King."
],
"answer": "Burger King.",
"augmentation_index": 1,
"augmentation_type": "rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000016_aug1_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000016",
"question": "where should I eat if I am not older than 16?\nKeep it brief.",
"question_id": "infovqa_000016"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I am not older than 16?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Burger King."
}
|
{
"all_answers": [
"Burger King."
],
"answer": "Burger King.",
"augmentation_index": 2,
"augmentation_type": "rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000016_aug2_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000016",
"question": "where should I eat if I am not older than 16?\nKeep it brief.",
"question_id": "infovqa_000016"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I am not older than 16?\nKeep it brief.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "McDonalds."
}
|
{
"all_answers": [
"McDonalds."
],
"answer": "McDonalds.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000017_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000017",
"question": "where should I eat if it is before 10:30 AM and I am not a police officer?\nGive a very brief answer.",
"question_id": "infovqa_000017"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if it is before 10:30 AM and I am not a police officer?\nGive a very brief answer.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "McDonalds."
}
|
{
"all_answers": [
"McDonalds."
],
"answer": "McDonalds.",
"augmentation_index": 1,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000017_aug1_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000017",
"question": "where should I eat if it is before 10:30 AM and I am not a police officer?\nGive a very brief answer.",
"question_id": "infovqa_000017"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if it is before 10:30 AM and I am not a police officer?\nGive a very brief answer.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "McDonalds."
}
|
{
"all_answers": [
"McDonalds."
],
"answer": "McDonalds.",
"augmentation_index": 2,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000017_aug2_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000017",
"question": "where should I eat if it is before 10:30 AM and I am not a police officer?\nGive a very brief answer.",
"question_id": "infovqa_000017"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if it is before 10:30 AM and I am not a police officer?\nGive a very brief answer.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "KFC."
}
|
{
"all_answers": [
"KFC."
],
"answer": "KFC.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000018_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000018",
"question": "where should I eat if I dont eat fish\nBe succinct.",
"question_id": "infovqa_000018"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I dont eat fish\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "KFC."
}
|
{
"all_answers": [
"KFC."
],
"answer": "KFC.",
"augmentation_index": 1,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000018_aug1_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000018",
"question": "where should I eat if I dont eat fish\nBe succinct.",
"question_id": "infovqa_000018"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I dont eat fish\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "KFC."
}
|
{
"all_answers": [
"KFC."
],
"answer": "KFC.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot180",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000018_aug2_flip_h_rot180",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000018",
"question": "where should I eat if I dont eat fish\nBe succinct.",
"question_id": "infovqa_000018"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nwhere should I eat if I dont eat fish\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_h_rot180
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "IN-N-OUT Burger."
}
|
{
"all_answers": [
"IN-N-OUT Burger."
],
"answer": "IN-N-OUT Burger.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000019_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000019",
"question": "Where should I eat if I live in westcoast and it is before 10:00PM\nShort answer required.",
"question_id": "infovqa_000019"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhere should I eat if I live in westcoast and it is before 10:00PM\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "IN-N-OUT Burger."
}
|
{
"all_answers": [
"IN-N-OUT Burger."
],
"answer": "IN-N-OUT Burger.",
"augmentation_index": 1,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000019_aug1_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000019",
"question": "Where should I eat if I live in westcoast and it is before 10:00PM\nShort answer required.",
"question_id": "infovqa_000019"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhere should I eat if I live in westcoast and it is before 10:00PM\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "IN-N-OUT Burger."
}
|
{
"all_answers": [
"IN-N-OUT Burger."
],
"answer": "IN-N-OUT Burger.",
"augmentation_index": 2,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000019_aug2_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000019",
"question": "Where should I eat if I live in westcoast and it is before 10:00PM\nShort answer required.",
"question_id": "infovqa_000019"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhere should I eat if I live in westcoast and it is before 10:00PM\nShort answer required.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "18."
}
|
{
"all_answers": [
"18."
],
"answer": "18.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000020_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000020",
"question": "How many eating joints have been mentioned here?\nAnswer briefly.",
"question_id": "infovqa_000020"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nHow many eating joints have been mentioned here?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "18."
}
|
{
"all_answers": [
"18."
],
"answer": "18.",
"augmentation_index": 1,
"augmentation_type": "rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000020_aug1_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000020",
"question": "How many eating joints have been mentioned here?\nAnswer briefly.",
"question_id": "infovqa_000020"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nHow many eating joints have been mentioned here?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "18."
}
|
{
"all_answers": [
"18."
],
"answer": "18.",
"augmentation_index": 2,
"augmentation_type": "rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000020_aug2_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000020",
"question": "How many eating joints have been mentioned here?\nAnswer briefly.",
"question_id": "infovqa_000020"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nHow many eating joints have been mentioned here?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "SONIC."
}
|
{
"all_answers": [
"SONIC."
],
"answer": "SONIC.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000021_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000021",
"question": "Where can I go if I am in a car\nQuick response, please.",
"question_id": "infovqa_000021"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhere can I go if I am in a car\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "SONIC."
}
|
{
"all_answers": [
"SONIC."
],
"answer": "SONIC.",
"augmentation_index": 1,
"augmentation_type": "rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000021_aug1_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000021",
"question": "Where can I go if I am in a car\nQuick response, please.",
"question_id": "infovqa_000021"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhere can I go if I am in a car\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "SONIC."
}
|
{
"all_answers": [
"SONIC."
],
"answer": "SONIC.",
"augmentation_index": 2,
"augmentation_type": "flip_v+rot180",
"data_split": "train",
"doc_id": "Infographic-VQA_98fe47f5c7b5c509",
"index": "infovqa_infovqa_000021_aug2_flip_v_rot180",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "98fe47f5c7b5c50984efca4babeb2a224cadaab79ebcfae743a22b23c5aeb3a1",
"original_question_id": "infovqa_000021",
"question": "Where can I go if I am in a car\nQuick response, please.",
"question_id": "infovqa_000021"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhere can I go if I am in a car\nQuick response, please.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_spatial_flip_v_rot180
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "6."
}
|
{
"all_answers": [
"6."
],
"answer": "6.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000022_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000022",
"question": "LIver is a source of how many of the vitamins shown here?\nConcise answer only.",
"question_id": "infovqa_000022"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nLIver is a source of how many of the vitamins shown here?\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "6."
}
|
{
"all_answers": [
"6."
],
"answer": "6.",
"augmentation_index": 1,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000022_aug1_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000022",
"question": "LIver is a source of how many of the vitamins shown here?\nConcise answer only.",
"question_id": "infovqa_000022"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nLIver is a source of how many of the vitamins shown here?\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "6."
}
|
{
"all_answers": [
"6."
],
"answer": "6.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot270",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000022_aug2_flip_h_rot270",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000022",
"question": "LIver is a source of how many of the vitamins shown here?\nConcise answer only.",
"question_id": "infovqa_000022"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nLIver is a source of how many of the vitamins shown here?\nConcise answer only.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_numerical_flip_h_rot270
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Egg yolks."
}
|
{
"all_answers": [
"Egg yolks."
],
"answer": "Egg yolks.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000023_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000023",
"question": "Which dairy item is a source of vitamin b9?\nAnswer briefly.",
"question_id": "infovqa_000023"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich dairy item is a source of vitamin b9?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Egg yolks."
}
|
{
"all_answers": [
"Egg yolks."
],
"answer": "Egg yolks.",
"augmentation_index": 1,
"augmentation_type": "flip_v+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000023_aug1_flip_v_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000023",
"question": "Which dairy item is a source of vitamin b9?\nAnswer briefly.",
"question_id": "infovqa_000023"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich dairy item is a source of vitamin b9?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_v_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Egg yolks."
}
|
{
"all_answers": [
"Egg yolks."
],
"answer": "Egg yolks.",
"augmentation_index": 2,
"augmentation_type": "flip_v+rot180",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000023_aug2_flip_v_rot180",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000023",
"question": "Which dairy item is a source of vitamin b9?\nAnswer briefly.",
"question_id": "infovqa_000023"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich dairy item is a source of vitamin b9?\nAnswer briefly.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_v_rot180
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Liver."
}
|
{
"all_answers": [
"Liver."
],
"answer": "Liver.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000024_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000024",
"question": "Which fish/meat item is a source of vitamin k?\nWrite a very short answer.",
"question_id": "infovqa_000024"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich fish/meat item is a source of vitamin k?\nWrite a very short answer.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Liver."
}
|
{
"all_answers": [
"Liver."
],
"answer": "Liver.",
"augmentation_index": 1,
"augmentation_type": "flip_v+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000024_aug1_flip_v_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000024",
"question": "Which fish/meat item is a source of vitamin k?\nWrite a very short answer.",
"question_id": "infovqa_000024"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich fish/meat item is a source of vitamin k?\nWrite a very short answer.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_v_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Liver."
}
|
{
"all_answers": [
"Liver."
],
"answer": "Liver.",
"augmentation_index": 2,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000024_aug2_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000024",
"question": "Which fish/meat item is a source of vitamin k?\nWrite a very short answer.",
"question_id": "infovqa_000024"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich fish/meat item is a source of vitamin k?\nWrite a very short answer.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Shellfish."
}
|
{
"all_answers": [
"Shellfish."
],
"answer": "Shellfish.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000025_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000025",
"question": "Which fish/meat item is a source of vitamin E?\nBe succinct.",
"question_id": "infovqa_000025"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich fish/meat item is a source of vitamin E?\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Shellfish."
}
|
{
"all_answers": [
"Shellfish."
],
"answer": "Shellfish.",
"augmentation_index": 1,
"augmentation_type": "flip_v",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000025_aug1_flip_v",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000025",
"question": "Which fish/meat item is a source of vitamin E?\nBe succinct.",
"question_id": "infovqa_000025"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich fish/meat item is a source of vitamin E?\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_v
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Shellfish."
}
|
{
"all_answers": [
"Shellfish."
],
"answer": "Shellfish.",
"augmentation_index": 2,
"augmentation_type": "flip_h+rot90",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000025_aug2_flip_h_rot90",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000025",
"question": "Which fish/meat item is a source of vitamin E?\nBe succinct.",
"question_id": "infovqa_000025"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich fish/meat item is a source of vitamin E?\nBe succinct.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h_rot90
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Avocado."
}
|
{
"all_answers": [
"Avocado."
],
"answer": "Avocado.",
"augmentation_index": 0,
"augmentation_type": "original",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000026_aug0_original",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000026",
"question": "Which fruit is a source of vitamin E?\nWrite a very short answer.",
"question_id": "infovqa_000026"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich fruit is a source of vitamin E?\nWrite a very short answer.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual
|
visual_toolbox_v2
|
|
infovqa_augmented
|
{
"ground_truth": "Avocado."
}
|
{
"all_answers": [
"Avocado."
],
"answer": "Avocado.",
"augmentation_index": 1,
"augmentation_type": "flip_h",
"data_split": "train",
"doc_id": "Infographic-VQA_007fba93483d51fa",
"index": "infovqa_infovqa_000026_aug1_flip_h",
"infovqa_source": "Infographic-VQA",
"original_image_filename": "007fba93483d51faaec1d521b3f905ae4289825ab886c8f94d4235e723b54bca",
"original_question_id": "infovqa_000026",
"question": "Which fruit is a source of vitamin E?\nWrite a very short answer.",
"question_id": "infovqa_000026"
}
|
[
{
"content": "You are a helpful assistant.\n\n# Tools\nYou may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\":\"function\",\"function\":{\"name\":\"image_zoom_in_tool\",\"description\":\"Zoom in on a specific region of an image by cropping it based on a bounding box (bbox) and an optional object label.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"bbox_2d\":{\"type\":\"array\",\"items\":{\"type\":\"number\"},\"minItems\":4,\"maxItems\":4,\"description\":\"The bounding box of the region to zoom in, as [x1, y1, x2, y2], where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.\"},\"label\":{\"type\":\"string\",\"description\":\"The name or label of the object in the specified bounding box (optional).\"}},\"required\":[\"bbox\"]}}}\n</tools>\n\n# How to call a tool\nReturn a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n**Example**: \n<tool_call> \n{\"name\": \"image_zoom_in_tool\", \"arguments\": {\"bbox_2d\": [10, 20, 100, 200], \"label\": \"the apple on the desk\"}} \n</tool_call>",
"role": "system"
},
{
"content": "<image>\nWhich fruit is a source of vitamin E?\nWrite a very short answer.\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] |
infovqa_factual_flip_h
|
visual_toolbox_v2
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 84