{
 "id": "ks48/url-atlas",
 "owner": "ks48",
 "name": "url-atlas",
 "downloads": 1872,
 "likes": 0,
 "last_modified": "2026-08-22T09:41:52.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "per-source-see-card",
 "licence_link": "https://huggingface.co/datasets/ks46/url-atlas#licensing-and-attribution",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval",
  "other"
 ],
 "citation": "This collection is a derivative work and **carries no single license**. Each\nconfig inherits the terms of the corpus it was extracted from — see the\n`derived from` column above and `source-notes/<source>.md` for the exact\nupstream, then follow that upstream's license. Notable cases: the Common Crawl\nindex is under Common Crawl's\n[terms of use](https://commoncrawl.org/terms-of-use); Wikimedia dumps are\nCC BY-SA / GFDL; most nhagar `*_urls` extracts inherit ODC-By from C4, FineWeb\nand friends.\n\nURLs are addresses, not content: nothing here reproduces the text of any page.\nSome URLs will nonetheless point at content that is offensive, illegal in your\njurisdiction, or personally identifying, and some will be dead. There is no\nsafety filtering of any kind.",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "fef4ce108022811b744204eddd9c543f48446445",
 "stated_evidence": "https://huggingface.co/datasets/ks48/url-atlas/blob/fef4ce108022811b744204eddd9c543f48446445/README.md",
 "file_evidence": "https://huggingface.co/datasets/ks48/url-atlas/tree/fef4ce108022811b744204eddd9c543f48446445",
 "card_nc": false
}