{"url":"/dataset/proofnetverif","name":"ProofNetVerif","full_name":null,"description_markdown":"ProofNetVerif is an evaluation benchmark comprising 3,752 entries, each including an informal mathematical statement, its reference formalization, a predicted formalization, and a binary label indicating semantic equivalence. It is designed to assess autoformalization metrics by providing a challenging testbed for both reference-based and reference-free evaluation approaches.","description_withheld":null,"homepage":"https://huggingface.co/datasets/PAug/ProofNetVerif","introduced_date":"2025-02-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/improving-autoformalization-using-type","title":"Improving Autoformalization using Type Checking","first_author":"Auguste Poiroux","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Informal-to-formal Style Transfer","url":"/task/informal-to-formal-style-transfer","datasets_with_task":"/datasets/task/informal-to-formal-style-transfer"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ProofNetVerif"],"data_loaders":[{"repo":"https://github.com/augustepoiroux/LeanInteract","url":"https://huggingface.co/datasets/PAug/ProofNetVerif","frameworks":[]}],"num_papers_in_archive":1,"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."}