{"id":"W2914582798","doi":"10.1007/s10664-018-9679-5","title":"The impact of feature reduction techniques on defect prediction models","year":2019,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":99,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; University of Alberta","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Reduction (mathematics); Feature (linguistics); Computer science; Pattern recognition (psychology); Artificial intelligence; Data mining; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002374576,0.0001840588,0.0002037163,0.0001180731,0.00005930673,0.00003411161,0.0000928402,0.0002332192,0.00001004465],"category_scores_gemma":[0.00009053442,0.0001244991,0.0002559493,0.0003268671,0.000009070191,0.0001484613,0.00001505055,0.0003854626,0.00001858393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002398551,"about_ca_system_score_gemma":0.00001472298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001875091,"about_ca_topic_score_gemma":2.195277e-7,"domain_scores_codex":[0.9991366,0.00002296052,0.0002359898,0.0001603407,0.0002181227,0.0002259411],"domain_scores_gemma":[0.9994196,0.0001565247,0.00004057798,0.0002723955,0.00005105494,0.0000598707],"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":[0.00003950558,0.00001132726,0.001638452,0.00003721294,0.00008112747,5.741479e-7,0.00007398389,0.9787868,0.006662637,0.00001789259,0.005707563,0.006942984],"study_design_scores_gemma":[0.001408559,0.00280703,0.04219403,0.0009730902,0.00007965819,0.000164298,0.00009634214,0.8145137,0.1108816,0.0004520755,0.02514074,0.001288882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9525787,0.0002728411,0.0435232,0.00001191192,0.001389451,0.000494054,0.00002188538,0.001215069,0.0004929265],"genre_scores_gemma":[0.9991565,0.0000230945,0.000321502,0.000001716533,0.0003174478,0.00003017338,0.000006696374,0.00004476499,0.00009812917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.164273,"threshold_uncertainty_score":0.5076928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01584160135086377,"score_gpt":0.2569401352835333,"score_spread":0.2410985339326695,"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."}}