{"url":"/dataset/statutory-interpretation-data-set","name":"Statutory Interpretation Data Set","full_name":null,"description_markdown":"This dataset contains a set of sentences by extracting all the sentences mentioning the term from the court decisions retrieved from the Caselaw access project data.\r\n\r\nIn total the corpus consists of 26,959 sentences.\r\n\r\nThe sentences are classified into four categories according to their usefulness for the interpretation:\r\n\r\n- high value - sentence intended to define or elaborate on the meaning of the term\r\n- certain value - sentence that provides grounds to elaborate on the term's meaning\r\n- potential value - sentence that provides additional information beyond what is known from the provision the term comes from\r\n- no value - no additional information over what is known from the provision","description_withheld":null,"homepage":"https://github.com/jsavelka/statutory_interpretation","introduced_date":"2021-12-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/discovering-explanatory-sentences-in-legal-1","title":"Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models","first_author":"Jaromir Savelka","url":null},"license":{"name":"Custom","url":"https://github.com/jsavelka/statutory_interpretation#terms-of-use"},"modalities":[],"tasks":[],"languages":[],"variants":["Statutory Interpretation Data Set"],"data_loaders":[],"num_papers_in_archive":3,"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."}