{
 "id": "mtybilly/apex-r1-real-world-documents",
 "owner": "mtybilly",
 "name": "apex-r1-real-world-documents",
 "downloads": 1298,
 "likes": 0,
 "last_modified": "2026-07-13T16:38:45.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "document-question-answering",
  "question-answering",
  "text-generation"
 ],
 "citation": "This repository aggregates sources under multiple licenses (hence the top-level `license: other`); the per-source `PROVENANCE.md` files are authoritative. Notable requirements:\n\n- **CUAD** — Contract Understanding Atticus Dataset v1, **CC BY 4.0**. Attribution: The Atticus Project (https://www.atticusprojectai.org/cuad).\n- **DABstep** — **CC BY 4.0**. Attribution: Adyen (https://huggingface.co/datasets/adyen/DABstep).\n- **SEC-EDGAR**, **HTS-Tariffs** — US government / public record, no restrictions.\n- **GovDocs1** — Digital Corpora, distributed for free redistribution.\n- **SpreadsheetBench/v2** — MIT.\n\nOnly publicly redistributable sources are published here. **SpreadsheetBench v1** (forum-sourced workbooks, not per-file rights-cleared) is deliberately **excluded** from this public dataset and retained only as internal seed material.",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "63691f42faf31bfb72ae071335ad0a4997b67532",
 "stated_evidence": "https://huggingface.co/datasets/mtybilly/apex-r1-real-world-documents/blob/63691f42faf31bfb72ae071335ad0a4997b67532/README.md",
 "file_evidence": "https://huggingface.co/datasets/mtybilly/apex-r1-real-world-documents/tree/63691f42faf31bfb72ae071335ad0a4997b67532",
 "card_nc": false
}