{
 "id": "BAAI/CCI3-HQ-Annotation-Benchmark",
 "owner": "BAAI",
 "name": "CCI3-HQ-Annotation-Benchmark",
 "downloads": 89,
 "likes": 4,
 "last_modified": "2026-08-18T12:59:46.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{wang2024cci30hqlargescalechinesedataset,\n  title={CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models},\n  author={Liangdong Wang and Bo-Wen Zhang and Chengwei Wu and Hanyu Zhao and Xiaofeng Shi and Shuhao Gu and Jijie Li and Quanyue Ma and TengFei Pan and Guang Liu},\n  year={2024},\n  eprint={2410.18505},\n  archivePrefix={arXiv},\n  primaryClass={cs.CL},\n  url={https://arxiv.org/abs/2410.18505}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "4684f32b9f8596bc467c2d40e86efa322130b4bb",
 "stated_evidence": "https://huggingface.co/datasets/BAAI/CCI3-HQ-Annotation-Benchmark/blob/4684f32b9f8596bc467c2d40e86efa322130b4bb/README.md",
 "file_evidence": "https://huggingface.co/datasets/BAAI/CCI3-HQ-Annotation-Benchmark/tree/4684f32b9f8596bc467c2d40e86efa322130b4bb",
 "card_nc": false
}