{
 "id": "PleIAs/CommonLingua-Train",
 "owner": "PleIAs",
 "name": "CommonLingua-Train",
 "downloads": 78,
 "likes": 16,
 "last_modified": "2026-04-28T08:53:16.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "per-source",
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@misc{commonlingua-train,\n  author = {{PleIAs}},\n  title  = {CommonLingua-Train: A multi-source open dataset for byte-level language identification},\n  year   = {2026},\n  url    = {https://huggingface.co/datasets/PleIAs/CommonLingua-Train}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "a452a0816459c4370f1e440b5341ad82b14c583f",
 "stated_evidence": "https://huggingface.co/datasets/PleIAs/CommonLingua-Train/blob/a452a0816459c4370f1e440b5341ad82b14c583f/README.md",
 "file_evidence": "https://huggingface.co/datasets/PleIAs/CommonLingua-Train/tree/a452a0816459c4370f1e440b5341ad82b14c583f",
 "card_nc": false
}