{"url":"/dataset/naturalproofs","name":"NaturalProofs","full_name":null,"description_markdown":"The NaturalProofs Dataset is a large-scale dataset for studying mathematical reasoning in natural language. NaturalProofs consists of roughly 20,000 theorem statements and proofs, 12,500 definitions, and 1,000 additional pages (e.g. axioms, corollaries) derived from ProofWiki, an online compendium of mathematical proofs written by a community of contributors. \r\n\r\nSource: [NaturalProofs](https://zenodo.org/record/4632539#.YGwcNRNKiL8)","description_withheld":null,"homepage":"https://github.com/wellecks/naturalproofs#naturalproofs-dataset","introduced_date":"2021-03-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/naturalproofs-mathematical-theorem-proving-in","title":"NaturalProofs: Mathematical Theorem Proving in Natural Language","first_author":"Sean Welleck","url":null},"license":{"name":"Attribution 4.0 International","url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Mathematical Proofs","url":"/task/mathematical-proofs","datasets_with_task":"/datasets/task/mathematical-proofs"}],"languages":[],"variants":["NaturalProofs"],"data_loaders":[{"repo":"https://github.com/wellecks/naturalproofs","url":"https://github.com/wellecks/naturalproofs","frameworks":["pytorch"]}],"num_papers_in_archive":13,"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."}