{"id":"W2367798545","doi":"10.1145/2884781.2884857","title":"Automated parameter optimization of classification techniques for defect prediction models","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":344,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Classifier (UML); Machine learning; Artificial intelligence; Random forest; Predictive modelling; Software bug; Decision tree; Software; Data mining","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":[0.000257479,0.00005306671,0.00006539369,0.0001298581,0.00002024928,0.00002247477,0.0002381271,0.00005572891,0.0000038614],"category_scores_gemma":[0.0003793845,0.00003588945,0.00004004321,0.0001928042,0.00001703102,0.000493885,0.00003778213,0.00001880155,0.000001655913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004876686,"about_ca_system_score_gemma":0.00002677225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003119842,"about_ca_topic_score_gemma":1.555198e-7,"domain_scores_codex":[0.999388,0.00001976864,0.0001465129,0.0001817259,0.0001495148,0.0001144154],"domain_scores_gemma":[0.9988785,0.0005649886,0.00003950585,0.0003042314,0.0001854589,0.00002729313],"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":[0.00007265652,0.0003088067,0.006789514,0.0002334644,0.0001382372,7.590652e-7,0.0003548501,0.3342766,0.124755,0.1435782,0.01298548,0.3765064],"study_design_scores_gemma":[0.0001084419,0.0000802977,0.0009741936,0.00002071871,0.000001961841,9.14549e-7,6.191631e-7,0.9606822,0.03669908,0.001351672,0.00003636851,0.0000435476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001893581,0.000006005664,0.9953596,0.0001647241,0.00005249564,0.0003136572,0.000004764956,0.002099149,0.0001060287],"genre_scores_gemma":[0.5420623,0.000005834042,0.4577642,0.000004803337,0.000007976663,0.0000925291,0.000002154739,0.000005228388,0.00005488135],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6264056,"threshold_uncertainty_score":0.1463529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03975154568969916,"score_gpt":0.2891461855171243,"score_spread":0.2493946398274251,"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."}}