{"url":"/dataset/gitbugs","name":"GitBugs","full_name":"GitBugs: Bug Reports for Duplicate Detection, Retrieval Augmented Generation, Triage, and More","description_markdown":"GitBugs is a comprehensive and up-to-date dataset comprising over 150,000 bug reports from nine actively maintained open-source projects, including Firefox, Cassandra, and VS Code. GitBugs aggregates data from Github, Bugzilla and Jira issue trackers, offering standardized categorical fields for classification tasks and predefined train/test splits for duplicate bug detection. In addition, it includes exploratory analysis notebooks and detailed project-level statistics, such as duplicate rates and resolution times. GitBugs supports various software engineering research tasks, including duplicate detection, retrieval augmented generation, resolution prediction, automated triaging, and temporal analysis. The openly licensed dataset provides a valuable cross-project resource for bench- marking and advancing automated bug report analysis. Access the data and code at this https URL.","description_withheld":null,"homepage":"https://github.com/av9ash/gitbugs","introduced_date":"2025-04-13","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"modalities":[],"tasks":[{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GitBugs"],"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/on-gitbugs","task":"","dataset_variant":"GitBugs","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Logistic Regression","paper":"/paper/gitbugs-bug-reports-for-duplicate-detection-1","metrics":{"Accuracy":"82"},"code_links":[{"title":"av9ash/gitbugs","url":"https://github.com/av9ash/gitbugs"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/gitbugs-bug-reports-for-duplicate-detection-1","title":"GitBugs: Bug Reports for Duplicate Detection, Retrieval Augmented Generation, Triage, and More","date":null,"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."}