{
 "id": "taesiri/ArXivSignals-FullText",
 "owner": "taesiri",
 "name": "ArXivSignals-FullText",
 "downloads": 124,
 "likes": 0,
 "last_modified": "2026-07-14T13:44:03.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "mixed-see-description",
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "text-retrieval",
  "feature-extraction"
 ],
 "citation": "**This is important — read before redistributing.** The `ocr_markdown` /\n`ocr_layout` fields are a machine-generated transcription of arXiv PDFs. **arXiv\npapers are licensed individually by their authors** (arXiv's default non-exclusive\nlicense, or CC-BY / CC-BY-SA / CC0 / other, per submission), and **that license\ngoverns the underlying content of the OCR text.** This dataset does **not** grant\nany rights beyond those of each source paper.\n\n- **Metadata** (title, abstract, authors, categories) is provided under\n  [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/), consistent with the\n  companion catalog dataset.\n- **OCR full text** is provided **for research and text/data-mining purposes**, as a\n  derived representation of publicly available papers. Redistribution or reuse of any\n  paper's text is subject to that paper's own license — check it before reusing.\n- **Attribution:** always cite the original arXiv paper (`paper_id`), not this dataset,\n  as the source of the content.\n- **OCR is imperfect:** expect errors in math, tables, multi-column, and scanned pages.\n  Treat the text as machine-transcribed, not authoritative.\n- **Takedown / opt-out:** if you are an author (or rights holder) and want a paper\n  removed, open an issue / discussion on this dataset repo — it will be removed promptly.\n\nMaintained by [@taesiri](https://huggingface.co/taesiri) · powers\n[arxivsignals.io](https://arxivsignals.io).",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "d54b2558e5c07b1e302fc7298eabd0e9de822f4e",
 "stated_evidence": "https://huggingface.co/datasets/taesiri/ArXivSignals-FullText/blob/d54b2558e5c07b1e302fc7298eabd0e9de822f4e/README.md",
 "file_evidence": "https://huggingface.co/datasets/taesiri/ArXivSignals-FullText/tree/d54b2558e5c07b1e302fc7298eabd0e9de822f4e",
 "card_nc": false
}