{"url":"/dataset/tfix-s-code-patch-data","name":"TFix's Code Patches Data","full_name":null,"description_markdown":"The dataset contains more than 100k code patch pairs extracted from open source projects on GitHub. Each pair comes with the erroneous and the fixed version of the corresponding code snippet. Instead of the whole file, the code snippets are extracted to focus on the problematic region (error line + other lines around it). For each sample, the repository name, the commit id, and the file names are provided so that one can access the complete files in case of interest.\r\n\r\nThe dataset only has JavaScript programs and the error are detected by the popular static code analyzer ESLint. The dataset can be used in the fields of: program repair, code generation, bug finding, transfer learning and many more fields related to machine learning for code","description_withheld":null,"homepage":"https://github.com/eth-sri/TFix","introduced_date":"2021-07-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/tfix-learning-to-fix-coding-errors-with-a","title":"TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer","first_author":"Berkay Berabi","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"},{"name":"Transfer Learning","url":"/task/transfer-learning","datasets_with_task":"/datasets/task/transfer-learning"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"},{"name":"Program Repair","url":"/task/program-repair","datasets_with_task":"/datasets/task/program-repair"}],"languages":[],"variants":["TFix's Code Patches Data"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/program-repair-on-tfix-s-code-patches-data","task":"Program Repair","dataset_variant":"TFix's Code Patches Data","rows":1,"metrics":["Error Removal","Exact Match"],"first_row_in_archive_order":{"model":"TFix","paper":"/paper/tfix-learning-to-fix-coding-errors-with-a","metrics":{"Error Removal":"67,8","Exact Match":"49,3"},"code_links":[{"title":"eth-sri/TFix","url":"https://github.com/eth-sri/TFix"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tfix-learning-to-fix-coding-errors-with-a","title":"TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer","date":"2021-07-18","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}