{"id":"W2474835145","doi":"10.1109/tse.2016.2584050","title":"An Empirical Comparison of Model Validation Techniques for Defect Prediction Models","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":566,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Japan Society for the Promotion of Science; Japan Society for the Promotion of Science London; Compute Canada","keywords":"Computer science; Variance (accounting); Context (archaeology); Cross-validation; Model validation; Sample (material); Data mining; Predictive modelling; Software bug; Software; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003212065,0.0002042513,0.0002466572,0.0004190811,0.00008337912,0.00004312172,0.0004915613,0.0001532788,0.000002969512],"category_scores_gemma":[0.0001035692,0.0001782765,0.0001656938,0.0003574999,0.00002276338,0.0009693491,0.000003723997,0.0001737507,0.000002650515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001685106,"about_ca_system_score_gemma":0.00006566503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003028263,"about_ca_topic_score_gemma":6.254527e-7,"domain_scores_codex":[0.9984806,0.00002520264,0.0003582603,0.0004250034,0.0003868086,0.0003241243],"domain_scores_gemma":[0.9981589,0.0008458697,0.0000532902,0.0006226194,0.0001861913,0.0001331503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001689331,0.0001314405,0.0003223868,0.00005110861,0.00002859238,2.914992e-7,0.0002106711,0.955961,0.01061431,0.0001580717,0.00005540389,0.03244981],"study_design_scores_gemma":[0.0002099715,0.0002504718,0.0001038202,0.00007659016,0.00001146334,0.000002492684,0.000002023153,0.7427968,0.2561853,0.0001876273,0.00002553545,0.0001478868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02838135,0.00001809275,0.9689415,0.00003086786,0.0002841988,0.0003858494,0.00006864707,0.001887654,0.000001916634],"genre_scores_gemma":[0.6654122,0.000005783577,0.3343129,0.000004862213,0.0000252649,0.0001907291,0.000002072479,0.00003141115,0.0000148123],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6370308,"threshold_uncertainty_score":0.7269905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05422237551678902,"score_gpt":0.3303165094466313,"score_spread":0.2760941339298422,"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."}}