{"url":"/dataset/rediscovery-datasets","name":"Rediscovery Datasets","full_name":null,"description_markdown":"We present three defect rediscovery datasets mined from Bugzilla. The datasets capture data for three groups of open source software projects: Apache, Eclipse, and KDE. The datasets contain information about approximately 914 thousands of defect reports over a period of 18 years (1999-2017) to capture the inter-relationships among duplicate defects.","description_withheld":null,"homepage":"https://zenodo.org/record/400614","introduced_date":"2017-03-18","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Rediscovery Datasets: Connecting Duplicate Reports","first_author":null,"url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Rediscovery Datasets"],"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."}