{
 "id": "ankitt6174/pdf-parse-bench",
 "owner": "ankitt6174",
 "name": "pdf-parse-bench",
 "downloads": 525,
 "likes": 0,
 "last_modified": "2026-09-16T07:53:25.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-to-text",
  "document-question-answering"
 ],
 "citation": "@misc{horn2025formulabench,\n    title = {Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs},\n    author = {Horn, Pius and Keuper, Janis},\n    year = {2025},\n    eprint = {2512.09874},\n    archivePrefix = {arXiv},\n    primaryClass = {cs.CV},\n    url = {https://arxiv.org/abs/2512.09874}\n}\n\n@misc{horn2026tablebench,\n    title = {Benchmarking PDF Parsers on Table Extraction with LLM-based Semantic Evaluation},\n    author = {Horn, Pius and Keuper, Janis},\n    year = {2026},\n    eprint = {2603.18652},\n    archivePrefix = {arXiv},\n    primaryClass = {cs.CV},\n    url = {https://arxiv.org/abs/2603.18652}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "bf5745e304b81386c79d7a4101efd8dc35e00527",
 "stated_evidence": "https://huggingface.co/datasets/ankitt6174/pdf-parse-bench/blob/bf5745e304b81386c79d7a4101efd8dc35e00527/README.md",
 "file_evidence": "https://huggingface.co/datasets/ankitt6174/pdf-parse-bench/tree/bf5745e304b81386c79d7a4101efd8dc35e00527",
 "card_nc": false
}