{"url":"/dataset/gigo-revisited-ml-publications-approaches-to","name":"GIGO revisited: ML publications' approaches to training data","full_name":null,"description_markdown":"A random sample of 200 machine learning publications, systematically analyzed by a team of labelers, who asked up to 15 questions about how the publication discusses its training data. More documentation in data/README.md.","description_withheld":null,"homepage":"https://github.com/staeiou/gigo_qss_2021","introduced_date":"2021-07-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/garbage-in-garbage-out-revisited-what-do","title":"\"Garbage In, Garbage Out\" Revisited: What Do Machine Learning Application Papers Report About Human-Labeled Training Data?","first_author":"R. Stuart Geiger","url":null},"license":{"name":"MIT License","url":null},"modalities":[],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GIGO revisited: ML publications' approaches to training data"],"data_loaders":[],"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."}