{
 "id": "UniParser/OmniScience",
 "owner": "UniParser",
 "name": "OmniScience",
 "downloads": 566,
 "likes": 129,
 "last_modified": "2026-08-31T07:15:58.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "image-to-text"
 ],
 "citation": "@inproceedings{tao2026omniscience,\n  title={Omniscience: A large-scale multi-modal dataset for scientific image understanding},\n  author={Tao, Haoyi and Huang, Chaozheng and Wang, Nan and Lyu, Han and Zhang, Linfeng and Ke, Guolin and Fang, Xi},\n  booktitle={Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2},\n  pages={9860--9870},\n  year={2026}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "868a5a543d40c979d7dbb6d50f63d089c8bb7eb4",
 "stated_evidence": "https://huggingface.co/datasets/UniParser/OmniScience/blob/868a5a543d40c979d7dbb6d50f63d089c8bb7eb4/README.md",
 "file_evidence": "https://huggingface.co/datasets/UniParser/OmniScience/tree/868a5a543d40c979d7dbb6d50f63d089c8bb7eb4",
 "card_nc": false
}