{"id":"W1994493193","doi":"10.5555/2819009.2819026","title":"Online defect prediction for imbalanced data","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Commit; Process (computing); Machine learning; Reliability (semiconductor); Data mining; Statistical classification; Predictive modelling; Resampling; Software bug; Artificial intelligence; Change detection; Software; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0004033437,0.00004705027,0.00005497249,0.0000457614,0.00001846117,0.00005436416,0.001084794,0.00002433434,0.000002208164],"category_scores_gemma":[0.001222272,0.00003998422,0.00001610628,0.0001745129,0.000007524178,0.0003700962,0.00041763,0.0000506855,0.00002107622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003177417,"about_ca_system_score_gemma":0.0000768616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001336395,"about_ca_topic_score_gemma":0.00000614557,"domain_scores_codex":[0.9993031,0.000009940897,0.0000735784,0.0002544529,0.0001964341,0.0001624868],"domain_scores_gemma":[0.9986167,0.0002602048,0.000009735752,0.0009284465,0.00008924981,0.00009565594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005100894,0.0005689461,0.09379779,0.0001059092,0.000131223,0.00001551183,0.0005320381,0.006594324,0.001177608,0.01702023,0.721832,0.1581734],"study_design_scores_gemma":[0.0005796695,0.0001437405,0.01529268,0.000006071919,0.000002391662,0.00000796191,0.000007362597,0.954348,0.0003345941,0.0007035803,0.02848854,0.00008541913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008823211,0.00004833265,0.9895745,0.0003312988,0.0003761108,0.0001483739,0.00004312579,0.0005285123,0.0001265421],"genre_scores_gemma":[0.4536246,0.000003996645,0.5448996,0.00009525318,0.0002753054,0.00002571734,0.0001924464,0.0000121868,0.000870926],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9477537,"threshold_uncertainty_score":0.2015836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1116123255897715,"score_gpt":0.3423711398886294,"score_spread":0.2307588142988579,"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."}}