{"url":"/dataset/overruling","name":"Overruling","full_name":null,"description_markdown":"The **Overruling** dataset is a law dataset corresponding to the task of determining when a sentence is overruling a prior decision. This is a binary classification task, where positive examples are overruling sentences and negative examples are non-overruling sentences extracted from legal opinions. In law, an overruling sentence is a statement that nullifies a previous case decision as a precedent, by a constitutionally valid statute or a decision by the same or higher ranking court which establishes a different rule on the point of law involved. The Overruling dataset consists of 2,400 sentences.\r\n\r\nTo read more about the dataset, please see our [paper](https://arxiv.org/abs/2104.08671) or our [blogpost](https://reglab.stanford.edu/data/the-overruling-dataset-a-benchmark-for-detecting-legal-decisions-that-have-been-overruled/).","description_withheld":null,"homepage":"https://github.com/reglab/casehold","introduced_date":"2021-04-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/when-does-pretraining-help-assessing-self","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","first_author":"Lucia Zheng","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":"English","url":"/datasets/language/english"}],"variants":["Overruling"],"data_loaders":[{"repo":"https://github.com/reglab/casehold","url":"https://github.com/reglab/casehold","frameworks":["pytorch"]}],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-overruling","task":"Text Classification","dataset_variant":"Overruling","rows":3,"metrics":["F1(10-fold)"],"first_row_in_archive_order":{"model":"Custom Legal-BERT","paper":"/paper/when-does-pretraining-help-assessing-self","metrics":{"F1(10-fold)":"97.4"},"code_links":[{"title":"reglab/casehold","url":"https://github.com/reglab/casehold"},{"title":"trusthlt/privacy-legal-nlp-lm","url":"https://github.com/trusthlt/privacy-legal-nlp-lm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/when-does-pretraining-help-assessing-self","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","date":"2021-04-18","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}