{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03136452,0.002451341,0.001866494,0.00384349,0.001386161,0.003983231,0.003077206,0.00308925,0.001080411],"category_scores_gemma":[0.1108616,0.0006701419,0.002581959,0.003631491,0.001662483,0.00595384,0.002583072,0.006203885,0.001538909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001358168,"about_ca_system_score_gemma":0.001760666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009672066,"about_ca_topic_score_gemma":0.006958996,"domain_scores_codex":[0.9787845,0.01149796,0.001538852,0.003706581,0.003501399,0.0009706382],"domain_scores_gemma":[0.8083639,0.1448201,0.008287071,0.02261542,0.01390554,0.002008086],"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":[0.006148509,0.002539349,0.3168643,0.00115075,0.002186293,0.0003456082,0.000853087,0.2418352,0.009683012,0.00193261,0.02630511,0.3901561],"study_design_scores_gemma":[0.0002348843,0.00139885,0.04387443,0.0002556558,0.000453864,0.0002434427,0.0006414587,0.9327734,0.01186155,0.003912238,0.004216543,0.0001337676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9399507,0.008561662,0.03724997,0.00289688,0.000896674,0.0002086824,0.003746568,0.002698611,0.003790322],"genre_scores_gemma":[0.958965,0.0006948136,0.03316044,0.0003329282,0.0002953766,0.00007925631,0.005607225,0.0002583369,0.0006065842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03136452,"threshold_uncertainty_score":0.1658734,"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."}}