{
 "id": "Voxel51/olmOCR_bench",
 "owner": "Voxel51",
 "name": "olmOCR_bench",
 "downloads": 1176,
 "likes": 0,
 "last_modified": "2026-02-24T02:30:14.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering"
 ],
 "citation": "@article{poznanski2025olmocr,\n  title   = {olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models},\n  author  = {Poznanski, Jake and Rangapur, Aman and Borchardt, Jon and Dunkelberger, Jason\n             and Huff, Regan and Lin, Daniel and Wilhelm, Christopher and Lo, Kyle and Soldaini, Luca},\n  journal = {arXiv preprint arXiv:2502.18443},\n  year    = {2025},\n  url     = {https://arxiv.org/abs/2502.18443}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "a9ed149d2be0c075e7bdf0887b6039aa211d365e",
 "stated_evidence": "https://huggingface.co/datasets/Voxel51/olmOCR_bench/blob/a9ed149d2be0c075e7bdf0887b6039aa211d365e/README.md",
 "file_evidence": "https://huggingface.co/datasets/Voxel51/olmOCR_bench/tree/a9ed149d2be0c075e7bdf0887b6039aa211d365e",
 "card_nc": false
}