{"url":"/dataset/bugl","name":"BuGL","full_name":null,"description_markdown":"**BuGL** is a large-scale cross-language dataset for bug localization in code. BuGL constitutes of more than 10,000 bug reports drawn from open-source projects written in four programming languages, namely C, C++, Java, and Python. The dataset consists of information which includes Bug Reports and Pull-Requests. BuGL aims to unfold new research opportunities in the area of bug localization.","description_withheld":null,"homepage":"https://zenodo.org/record/3653836","introduced_date":"2020-04-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/bugl-a-cross-language-dataset-for-bug","title":"BuGL -- A Cross-Language Dataset for Bug Localization","first_author":null,"url":null},"license":{"name":"Attribution 4.0 International","url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"modalities":[],"tasks":[],"languages":[],"variants":["BuGL"],"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."}