{
 "id": "vidore/arxivqa_test_subsampled",
 "owner": "vidore",
 "name": "arxivqa_test_subsampled",
 "downloads": 986,
 "likes": 4,
 "last_modified": "2025-06-20T15:48:48.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "document-question-answering",
  "visual-document-retrieval"
 ],
 "citation": "@misc{li2024multimodal,\n            title={Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models}, \n            author={Lei Li and Yuqi Wang and Runxin Xu and Peiyi Wang and Xiachong Feng and Lingpeng Kong and Qi Liu},\n            year={2024},\n            eprint={2403.00231},\n            archivePrefix={arXiv},\n            primaryClass={cs.CV}\n        }",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "b8a106812c8682bab08935cf5d1b4566c82562de",
 "stated_evidence": "https://huggingface.co/datasets/vidore/arxivqa_test_subsampled/blob/b8a106812c8682bab08935cf5d1b4566c82562de/README.md",
 "file_evidence": "https://huggingface.co/datasets/vidore/arxivqa_test_subsampled/tree/b8a106812c8682bab08935cf5d1b4566c82562de",
 "card_nc": false
}