{"url":"/dataset/chinese-ai-and-law-cail-2018","name":"Chinese AI and Law (CAIL) 2018","full_name":null,"description_markdown":"Large-scale Chinese legal dataset for judgment prediction. \\dataset contains more than 2.6  million criminal cases published by the Supreme People's Court of China, which are several times larger than other datasets in existing works on judgment prediction.\r\n\r\nSource: [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](/paper/cail2018-a-large-scale-legal-dataset-for)","description_withheld":null,"homepage":"https://github.com/thunlp/CAIL/blob/master/README_en.md","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/cail2018-a-large-scale-legal-dataset-for","title":"CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction","first_author":"Chaojun Xiao","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Chinese AI and Law (CAIL) 2018"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/china-ai-law-challenge/cail2018","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/polinaeterna/cail2018","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cail2018","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/thunlp/CAIL","url":"https://github.com/thunlp/CAIL","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}