{"url":"/dataset/contract-discovery","name":"Contract Discovery","full_name":null,"description_markdown":"A new shared task of semantic retrieval from legal texts, in which a so-called contract discovery is to be performed, where legal clauses are extracted from documents, given a few examples of similar clauses from other legal acts.\r\n\r\nSource: [Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines](/paper/searching-for-legal-clauses-by-analogy-few)","description_withheld":null,"homepage":"https://github.com/applicaai/contract-discovery","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/searching-for-legal-clauses-by-analogy-few","title":"Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines","first_author":"Łukasz Borchmann","url":null},"license":null,"modalities":[],"tasks":[{"name":"Semantic Retrieval","url":"/task/semantic-retrieval","datasets_with_task":"/datasets/task/semantic-retrieval"}],"languages":[],"variants":["Contract Discovery"],"data_loaders":[{"repo":"https://github.com/applicaai/contract-discovery","url":"https://github.com/applicaai/contract-discovery","frameworks":[]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-retrieval-on-contract-discovery","task":"Semantic Retrieval","dataset_variant":"Contract Discovery","rows":6,"metrics":["Soft-F1"],"first_row_in_archive_order":{"model":"Human baseline","paper":"/paper/searching-for-legal-clauses-by-analogy-few","metrics":{"Soft-F1":"0.84"},"code_links":[{"title":"applicaai/contract-discovery","url":"https://github.com/applicaai/contract-discovery"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dynamic-boundary-time-warping-for-sub","title":"Dynamic Boundary Time Warping for Sub-sequence Matching with Few Examples","date":"2020-10-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/searching-for-legal-clauses-by-analogy-few","title":"Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines","date":"2019-11-10","rows_on_this_dataset":5,"code_links":1,"syntology":null}],"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."}