{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004371005,0.0007660761,0.0009336406,0.0006431398,0.0001411237,0.001011271,0.00266517,0.0003325434,0.000006869691],"category_scores_gemma":[0.01351179,0.0008349529,0.0002562053,0.002949003,0.00004051797,0.001148119,0.001698711,0.001367245,0.0001215157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005524658,"about_ca_system_score_gemma":0.0001221987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001697437,"about_ca_topic_score_gemma":0.000006936054,"domain_scores_codex":[0.9945916,0.00008934327,0.0005273791,0.001720893,0.001480073,0.001590737],"domain_scores_gemma":[0.9959326,0.001106275,0.0001425287,0.001270889,0.0002742854,0.001273462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00007407378,0.0002925231,0.3655783,0.0009722452,0.000155677,0.00104817,0.003595165,0.5887282,0.006323423,0.0000426643,0.0272344,0.00595525],"study_design_scores_gemma":[0.001400013,0.0001786758,0.5782471,0.0004889591,0.00001741664,0.00003571749,0.00007240051,0.4085321,0.002270009,0.0000810058,0.00687061,0.001805981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3051757,0.000235626,0.6740202,0.01735092,0.0004331913,0.000482423,0.00002905687,0.002272167,8.021084e-7],"genre_scores_gemma":[0.8617076,0.000008995316,0.1361791,0.001197873,0.0004453474,0.0001807591,0.00001866925,0.0001542697,0.0001073748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5565319,"threshold_uncertainty_score":0.9994102,"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."}}