{
 "id": "StentorLabs/StenCore-PDF",
 "owner": "StentorLabs",
 "name": "StenCore-PDF",
 "downloads": 123,
 "likes": 1,
 "last_modified": "2026-03-06T07:35:07.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "HuggingFaceFW/finepdfs-edu",
   "licence": "odc-by",
   "found": true,
   "evidence": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/blob/9cfabe2127faca99b3d5c4dc6d1fcb397399ebde/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@dataset{stencore_finepdfs_edu_curated,\n  title        = {StenCore: FinePDFs-Edu Curated},\n  author       = {StentorLabs},\n  year         = {2026},\n  note         = {StentorLabs' first dataset. StenCore pipeline v2026.03.\n                  584k docs in, 149k out. Adaptive heuristics, PII redaction,\n                  toxicity/decontam gates, MinHash + KenLM + neural perplexity,\n                  CQF scoring, proxy domain reweighting.},\n  howpublished = {\\url{https://huggingface.co/datasets/StentorLabs/stencore}}\n}\n\n@dataset{fineweb_finepdfs_edu,\n  author       = {HuggingFace FineWeb Team},\n  title        = {FinePDFs-Edu},\n  howpublished = {\\url{https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu}}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "36ed785ca6231416d776ebdd45cc9bc01fb6d248",
 "stated_evidence": "https://huggingface.co/datasets/StentorLabs/StenCore-PDF/blob/36ed785ca6231416d776ebdd45cc9bc01fb6d248/README.md",
 "file_evidence": "https://huggingface.co/datasets/StentorLabs/StenCore-PDF/tree/36ed785ca6231416d776ebdd45cc9bc01fb6d248",
 "card_nc": false
}