{
 "id": "SKocur/polish-pre1918-corpus",
 "owner": "SKocur",
 "name": "polish-pre1918-corpus",
 "downloads": 927,
 "likes": 2,
 "last_modified": "2026-10-19T17:41:42.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc0-1.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{kocur2026wieszcz,\n  title  = {Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch},\n  author = {Kocur, Szymon},\n  year   = {2026},\n  eprint = {2610.10592},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.CL},\n  url    = {https://arxiv.org/abs/2610.10592},\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc0-1.0) is classified as permissive.",
 "revision": "b70ffc9b90e181932276ad0f82fd05d12cb98fe3",
 "stated_evidence": "https://huggingface.co/datasets/SKocur/polish-pre1918-corpus/blob/b70ffc9b90e181932276ad0f82fd05d12cb98fe3/README.md",
 "file_evidence": "https://huggingface.co/datasets/SKocur/polish-pre1918-corpus/blob/b70ffc9b90e181932276ad0f82fd05d12cb98fe3/LICENSE",
 "card_nc": false
}