{
 "id": "Voxel51/consolidated_receipt_dataset",
 "owner": "Voxel51",
 "name": "consolidated_receipt_dataset",
 "downloads": 2475,
 "likes": 5,
 "last_modified": "2025-10-21T18:19:04.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "object-detection",
  "visual-question-answering",
  "visual-document-retrieval"
 ],
 "citation": "@article{park2019cord,\n  title={CORD: A Consolidated Receipt Dataset for Post-OCR Parsing},\n  author={Park, Seunghyun and Shin, Seung and Lee, Bado and Lee, Junyeop and Surh, Jaeheung and Seo, Minjoon and Lee, Hwalsuk},\n  booktitle={Document Intelligence Workshop at Neural Information Processing Systems},\n  year={2019}\n}\n\n@article{hwang2019post,\n  title={Post-OCR parsing: building simple and robust parser via BIO tagging},\n  author={Hwang, Wonseok and Kim, Seonghyeon and Yim, Jinyeong and Seo, Minjoon and Park, Seunghyun and Park, Sungrae and Lee, Junyeop and Lee, Bado and Lee, Hwalsuk},\n  booktitle={Document Intelligence Workshop at Neural Information Processing Systems},\n  year={2019}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "a468aad0427a88453151d968c2f175299d9e0ba6",
 "stated_evidence": "https://huggingface.co/datasets/Voxel51/consolidated_receipt_dataset/blob/a468aad0427a88453151d968c2f175299d9e0ba6/README.md",
 "file_evidence": "https://huggingface.co/datasets/Voxel51/consolidated_receipt_dataset/tree/a468aad0427a88453151d968c2f175299d9e0ba6",
 "card_nc": false
}