{"id":"W3004570974","doi":"10.1007/s10664-019-09781-y","title":"How bugs are born: a model to identify how bugs are introduced in software components","year":2020,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; University of Waterloo","funders":"H2020 Industrial Leadership; Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Software bug; Software regression; Computer science; False positive paradox; Source lines of code; Software; Source code; Open source; Debugging; Software maintenance; Snapshot (computer storage); Code (set theory); Security bug; Data mining; Software development; Software quality; Programming language; Machine learning; Database; Operating system; Set (abstract data type); Software security assurance","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007021497,0.001335622,0.001045068,0.00929131,0.0009392814,0.003845833,0.002130301,0.003091578,0.001811786],"category_scores_gemma":[0.04929294,0.0007353934,0.001804496,0.003447786,0.002521064,0.006107893,0.002321217,0.001607981,0.0007701086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002377215,"about_ca_system_score_gemma":0.001597568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01113884,"about_ca_topic_score_gemma":0.009765143,"domain_scores_codex":[0.9958449,0.001261345,0.0003803117,0.001313354,0.0008557821,0.000344249],"domain_scores_gemma":[0.939931,0.04215767,0.008307773,0.003470333,0.004912148,0.001221157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001368946,0.0005830828,0.5505127,0.001018617,0.0005237153,0.001182789,0.003410992,0.2692018,0.006679441,0.02390862,0.01221562,0.1293938],"study_design_scores_gemma":[0.00004769728,0.0001418221,0.03347481,0.0000883963,0.00007424544,0.0004268779,0.0004507943,0.9415368,0.001237047,0.02076133,0.001705557,0.00005461078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6244081,0.002124251,0.3592568,0.003666377,0.0001052938,0.0003507322,0.002888395,0.003922355,0.003277577],"genre_scores_gemma":[0.9424195,0.0002768179,0.05380355,0.0002613464,0.00004399051,0.000118649,0.002167532,0.0001172587,0.0007913049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01113884,"threshold_uncertainty_score":0.03713369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06211628819800336,"score_gpt":0.2983208692382943,"score_spread":0.236204581040291,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}