{"url":"/dataset/pile-of-law","name":"Pile of Law","full_name":null,"description_markdown":"Pile of Law is a ∼256GB (and growing) dataset of legal and administrative data which can be used for assessing norms on data sanitization across legal and administrative settings.","description_withheld":null,"homepage":"https://github.com/breakend/pileoflaw","introduced_date":"2022-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/pile-of-law-learning-responsible-data","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","first_author":"Peter Henderson","url":null},"license":{"name":"CreativeCommons Attribution-NonCommercial-ShareAlike 4.0 International","url":"https://huggingface.co/datasets/pile-of-law/pile-of-law#licensing-information"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Pile of Law"],"data_loaders":[],"num_papers_in_archive":15,"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."}