{
 "id": "CASIA-LM/ChineseWebText",
 "owner": "CASIA-LM",
 "name": "ChineseWebText",
 "downloads": 9096,
 "likes": 45,
 "last_modified": "2023-11-13T01:59:09.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "Please cite the paper if you use the data in this repo.\n```shell\n@misc{chen2023chinesewebtext,\n      title={ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model}, \n      author={Jianghao Chen and Pu Jian and Tengxiao Xi and Dongyi Yi and Qianlong Du and Chenglin Ding and Guibo Zhu and Chengqing Zong and Jinqiao Wang and Jiajun Zhang},\n      year={2023},\n      eprint={2311.01149},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}\n```",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}