{"url":"/dataset/cail2019-scm","name":"CAIL2019-SCM","full_name":null,"description_markdown":"Chinese AI and Law 2019 Similar Case Matching dataset. CAIL2019-SCM contains 8,964 triplets of cases published by the Supreme People's Court of China. CAIL2019-SCM focuses on detecting similar cases, and the participants are required to check which two cases are more similar in the triplets.\r\n\r\nSource: [CAIL2019-SCM: A Dataset of Similar Case Matching in Legal Domain](/paper/cail2019-scm-a-dataset-of-similar-case)","description_withheld":null,"homepage":"https://github.com/china-ai-law-challenge/CAIL2019/tree/master/scm","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/cail2019-scm-a-dataset-of-similar-case","title":"CAIL2019-SCM: A Dataset of Similar Case Matching in Legal Domain","first_author":"Chaojun Xiao","url":null},"license":null,"modalities":[],"tasks":[{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Aspect-Based Sentiment Analysis (ABSA)","url":"/task/aspect-based-sentiment-analysis","datasets_with_task":"/datasets/task/aspect-based-sentiment-analysis"},{"name":"Semantic Text Matching","url":"/task/semantic-text-matching","datasets_with_task":"/datasets/task/semantic-text-matching"}],"languages":[],"variants":["CAIL2019-SCM","CAIL2019-SCM - val","CAIL2019-SCM - test"],"data_loaders":[{"repo":"https://github.com/china-ai-law-challenge/CAIL2019","url":"https://github.com/china-ai-law-challenge/CAIL2019","frameworks":["tf"]}],"num_papers_in_archive":4,"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":"2026-09-24T18:15:14+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."}