{"id":"W2163837601","doi":"","title":"Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":264,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Replicate; Machine learning; Predictive modelling; Software; Artificial intelligence; Multivariate adaptive regression splines; Data mining; Multivariate statistics; Software bug; Set (abstract data type); Variety (cybernetics); Regression; Support vector machine; Software quality; Logistic regression; Regression analysis; Statistics; Software development; Mathematics","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":[0.001263328,0.0000489929,0.0000599688,0.00005448627,0.00003197962,0.00002168261,0.0004990003,0.00002302086,0.00000162801],"category_scores_gemma":[0.0003245942,0.00002261266,0.00005038017,0.0003087432,0.00003147796,0.0002143183,0.00007241071,0.000100339,0.000001993562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005904493,"about_ca_system_score_gemma":0.00006207503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004148217,"about_ca_topic_score_gemma":7.301777e-8,"domain_scores_codex":[0.9993374,0.00005674913,0.0001298301,0.00009518578,0.0002889115,0.00009192349],"domain_scores_gemma":[0.9988005,0.0004563532,0.0000589483,0.0004928263,0.0001692674,0.00002214041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008791868,0.0001446668,0.1677008,0.0001781211,0.0001650065,7.265925e-7,0.004642062,0.3023508,0.03350927,0.1694558,0.005544788,0.31622],"study_design_scores_gemma":[0.00002900845,0.000172704,0.03714776,0.00004235824,0.000001239285,0.00000192071,0.00001582844,0.9404698,0.02173187,0.0003539266,0.00000789999,0.00002568258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6742279,0.00002670039,0.3237053,0.0002178616,0.0000182688,0.0001634699,8.349219e-7,0.0001238737,0.001515747],"genre_scores_gemma":[0.9967204,0.00001222711,0.003188344,0.000005386119,0.00003146652,0.00001630235,3.729211e-7,0.000003645687,0.00002185172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.638119,"threshold_uncertainty_score":0.0927275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.077198300332788,"score_gpt":0.3147743556056397,"score_spread":0.2375760552728516,"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."}}