{"url":"/dataset/wrench","name":"Wrench","full_name":null,"description_markdown":"Wrench is a benchmark platform for thorough and standardized evaluation of Weak Supervision (WS). It consists of 22 varied real-world datasets for classification and sequence tagging; a range of real, synthetic, and procedurally-generated weak supervision sources; and a modular, extensible framework for WS evaluation, including implementations for popular WS methods.","description_withheld":null,"homepage":"https://github.com/jieyuz2/wrench","introduced_date":"2021-09-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/wrench-a-comprehensive-benchmark-for-weak","title":"WRENCH: A Comprehensive Benchmark for Weak Supervision","first_author":"Jieyu Zhang","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Wrench"],"data_loaders":[],"num_papers_in_archive":33,"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."}