{
 "id": "zykan/pretraining-skill-annotations-2m",
 "owner": "zykan",
 "name": "pretraining-skill-annotations-2m",
 "downloads": 104,
 "likes": 0,
 "last_modified": "2026-10-30T18:47:00.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "source-specific-terms",
 "licence_link": "https://huggingface.co/datasets/zykan/pretraining-skill-annotations-2m#source-attribution-and-terms",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "- [FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) identifies its database license as [ODC-By](https://opendatacommons.org/licenses/by/1-0/). Attribution and upstream conditions are retained.\n- [RedPajama-Data-V2](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2) refers text-data users to the [Common Crawl Terms of Use](https://commoncrawl.org/terms-of-use); its code license must not be confused with a blanket license for all collected text.\n- Underlying webpages may carry their own rights and terms. This annotation upload does not replace or broaden the upstream permissions. No single new blanket text license is asserted for the combined repository.\n\n<!-- fine-grained-v3-20261031:start -->",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "7997dafb0b67ec44223444a1e729808c9d5aa3ea",
 "stated_evidence": "https://huggingface.co/datasets/zykan/pretraining-skill-annotations-2m/blob/7997dafb0b67ec44223444a1e729808c9d5aa3ea/README.md",
 "file_evidence": "https://huggingface.co/datasets/zykan/pretraining-skill-annotations-2m/tree/7997dafb0b67ec44223444a1e729808c9d5aa3ea",
 "card_nc": false
}