{"id":"W4250023757","doi":"10.1109/icse.2015.91","title":"Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models","year":2015,"lang":"en","type":"article","venue":"2015 IEEE/ACM 37th IEEE International Conference on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":319,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Replicate; Machine learning; Predictive modelling; Artificial intelligence; Software bug; Software; Data mining; Multivariate adaptive regression splines; Multivariate statistics; Set (abstract data type); Variety (cybernetics); Support vector machine; Regression; Logistic regression; Regression analysis; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.03935017,0.002905854,0.00217619,0.004008595,0.001493904,0.004896265,0.003404383,0.003137746,0.001138884],"category_scores_gemma":[0.126284,0.0007658417,0.003036417,0.003710856,0.002120036,0.006605088,0.002888683,0.006168012,0.001707942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001615507,"about_ca_system_score_gemma":0.001986554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01235269,"about_ca_topic_score_gemma":0.009795201,"domain_scores_codex":[0.9740099,0.01216054,0.001807254,0.005430808,0.005303357,0.001288079],"domain_scores_gemma":[0.8107314,0.1384245,0.007688556,0.02699335,0.01436601,0.001796228],"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":[0.005986311,0.002294016,0.3416805,0.001607538,0.002409377,0.0005787174,0.001376733,0.2113671,0.01256959,0.002705522,0.0301602,0.3872645],"study_design_scores_gemma":[0.0004263762,0.002228703,0.1029408,0.0004805963,0.0007865998,0.0005122807,0.001332108,0.85235,0.01908473,0.008189062,0.01140047,0.0002682326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9260817,0.01194302,0.04399415,0.003549683,0.0009555618,0.0002530794,0.005432867,0.002861566,0.004928352],"genre_scores_gemma":[0.94401,0.00122574,0.04259276,0.0005736468,0.0003772958,0.0001176802,0.00968091,0.0004227542,0.0009991587],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03935017,"threshold_uncertainty_score":0.208106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1198000391827528,"score_gpt":0.3409680431586617,"score_spread":0.2211680039759089,"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."}}