{
 "id": "nvidia/Nemotron-CC-Math-v1",
 "owner": "nvidia",
 "name": "Nemotron-CC-Math-v1",
 "downloads": 8367,
 "likes": 104,
 "last_modified": "2025-12-23T00:17:16.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE.md"
 ],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{karimi2025nemotroncc,\n  title = {Nemotron-cc-math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset},\n  author = {Rabeeh Karimi Mahabadi, Sanjeev Satheesh, Shrimai Prabhumoye, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro },\n  url = {https://arxiv.org/abs/2508.15096},\n  year = {2025}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}