{"url":"/dataset/github-python","name":"GitHub-Python","full_name":null,"description_markdown":"Repair AST parse (syntax) errors in Python code","description_withheld":null,"homepage":"https://github.com/michiyasunaga/bifi","introduced_date":"2021-06-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/break-it-fix-it-unsupervised-learning-for","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","first_author":"Michihiro Yasunaga","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Program Repair","url":"/task/program-repair","datasets_with_task":"/datasets/task/program-repair"}],"languages":[],"variants":["GitHub-Python"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/program-repair-on-github-python","task":"Program Repair","dataset_variant":"GitHub-Python","rows":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Transformer + BIFI","paper":"/paper/break-it-fix-it-unsupervised-learning-for","metrics":{"Accuracy (%)":"90.5"},"code_links":[{"title":"michiyasunaga/bifi","url":"https://github.com/michiyasunaga/bifi"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/break-it-fix-it-unsupervised-learning-for","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","date":"2021-06-11","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}