{
 "id": "brian-learns/cdx-cc-news",
 "owner": "brian-learns",
 "name": "cdx-cc-news",
 "downloads": 7617,
 "likes": 8,
 "last_modified": "2026-09-02T12:20:34.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "- Common Crawl Foundation (2026). news-crawl: News crawling with StormCrawler [Computer software]. GitHub. https://github.com/commoncrawl/news-crawl\n\n - Tange, O. (2026). GNU Parallel 20260622 [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.20959929\n\n - Facebook AI (2026). Zstandard compression tool [Computer software]. https://facebook.github.io/zstd/\n\n - Webrecorder (2026). cdxj-indexer [Computer software]. GitHub. https://github.com/webrecorder/cdxj-indexer\n\n - Astral Software (2026). uv: An extremely fast Python package installer and resolver (Version 0.2.0) [Computer software]. GitHub.  https://docs.astral.sh/uv/\n\n - Internet Archive (2026). surt: Sort-friendly URI Reordering Transform [Computer software]. https://github.com/internetarchive/surt\n\n - Webrecorder (2022). Crawl Index JSON (CDXJ) [Technical Recomendation] https://specs.webrecorder.net/cdxj/0.1.0/\n\n - duckdb / sqlite",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "c5cb874d252f112ac708327613b886089e96e84c",
 "stated_evidence": "https://huggingface.co/datasets/brian-learns/cdx-cc-news/blob/c5cb874d252f112ac708327613b886089e96e84c/README.md",
 "file_evidence": "https://huggingface.co/datasets/brian-learns/cdx-cc-news/tree/c5cb874d252f112ac708327613b886089e96e84c",
 "card_nc": false
}