{
 "id": "FinetextPL/FinetextPL-Edu",
 "owner": "FinetextPL",
 "name": "FinetextPL-Edu",
 "downloads": 127,
 "likes": 2,
 "last_modified": "2026-08-11T17:42:04.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{FinetextPL_Edu,\nauthor = {Kowalik, Marcel and Poruba, Miłosz and Grzymkowski, Łukasz and Stefański, Tomasz},\ndoi = {10.1109/ACCESS.2026.3720484},\njournal = {IEEE Access},\nnote = {Advance online publication},\ntitle = {{FinetextPL-Edu: A High-Quality Polish Corpus for Large Language Model Pretraining via Educational Quality Filtering}}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "eefa4ea4aaea55d4267baf2411ca19ab9c532ade",
 "stated_evidence": "https://huggingface.co/datasets/FinetextPL/FinetextPL-Edu/blob/eefa4ea4aaea55d4267baf2411ca19ab9c532ade/README.md",
 "file_evidence": "https://huggingface.co/datasets/FinetextPL/FinetextPL-Edu/tree/eefa4ea4aaea55d4267baf2411ca19ab9c532ade",
 "card_nc": false
}