{
 "id": "brianshumate/chat-jfk",
 "owner": "brianshumate",
 "name": "chat-jfk",
 "downloads": 6425,
 "likes": 0,
 "last_modified": "2026-07-26T14:23:23.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{wang2026mineru2,\n  title={MinerU2. 5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale},\n  author={Wang, Bin and He, Tianyao and Ouyang, Linke and Wu, Fan and Zhao, Zhiyuan and Chu, Tao and Qu, Yuan and Jin, Zhenjiang and Zeng, Weijun and Miao, Ziyang and others},\n  journal={arXiv preprint arXiv:2604.04771},\n  year={2026}\n}\n\n@article{dong2026minerudiffusion,\n  title={MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding},\n  author={Dong, Hejun and Niu, Junbo and Wang, Bin and Zeng, Weijun and Zhang, Wentao and He, Conghui},\n  journal={arXiv preprint arXiv:2603.22458},\n  year={2026}\n}\n\n@article{niu2025mineru2,\n  title={Mineru2. 5: A decoupled vision-language model for efficient high-resolution document parsing},\n  author={Niu, Junbo and Liu, Zheng and Gu, Zhuangcheng and Wang, Bin and Ouyang, Linke and Zhao, Zhiyuan and Chu, Tao and He, Tianyao and Wu, Fan and Zhang, Qintong and others},\n  journal={arXiv preprint arXiv:2509.22186},\n  year={2025}\n}\n\n@article{wang2024mineru,\n  title={Mineru: An open-source solution for precise document content extraction},\n  author={Wang, Bin and Xu, Chao and Zhao, Xiaomeng and Ouyang, Linke and Wu, Fan and Zhao, Zhiyuan and Xu, Rui and Liu, Kaiwen and Qu, Yuan and Shang, Fukai and others},\n  journal={arXiv preprint arXiv:2409.18839},\n  year={2024}\n}\n\n@article{he2024opendatalab,\n  title={Opendatalab: Empowering general artificial intelligence with open datasets},\n  author={He, Conghui and ",
 "signal": "permissive",
 "reason": "The declared licence (cc0-1.0) is classified as permissive.",
 "revision": "45616c4e121f8a663bab1deb4fa89c74559ac191",
 "stated_evidence": "https://huggingface.co/datasets/brianshumate/chat-jfk/blob/45616c4e121f8a663bab1deb4fa89c74559ac191/README.md",
 "file_evidence": "https://huggingface.co/datasets/brianshumate/chat-jfk/tree/45616c4e121f8a663bab1deb4fa89c74559ac191",
 "card_nc": false
}