{
 "id": "thoughtworks/document-processing-benchmark",
 "owner": "thoughtworks",
 "name": "document-processing-benchmark",
 "downloads": 130,
 "likes": 1,
 "last_modified": "2026-05-24T18:24:23.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "mixed-research-and-permissive",
 "licence_link": "LICENSE",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-to-text",
  "visual-question-answering",
  "image-classification"
 ],
 "citation": "Cite the upstream sources per their published references:\n\n- CORD-v2: Park et al., 2019 (Naver Clova)\n- FUNSD: Jaume et al., 2019\n- SROIE: Huang et al., 2019 (ICDAR)\n- WildReceipt: Sun et al., 2021\n- FATURA: Limam et al., 2023\n- RVL-CDIP: Harley et al., 2015\n- MP-DocVQA: Tito et al., 2022\n- CUAD: Hendrycks et al., 2021\n\nThis benchmark assembly is released under the union of upstream licenses\nlisted in the Sources section. Filter by the per-row `license` column for\nyour use case (commercial vs research).",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "9a915e4e8980852a77b9be48586e4b9095ca8ded",
 "stated_evidence": "https://huggingface.co/datasets/thoughtworks/document-processing-benchmark/blob/9a915e4e8980852a77b9be48586e4b9095ca8ded/README.md",
 "file_evidence": "https://huggingface.co/datasets/thoughtworks/document-processing-benchmark/tree/9a915e4e8980852a77b9be48586e4b9095ca8ded",
 "card_nc": false
}