{"id":"W2089863833","doi":"10.1109/seaa.2011.59","title":"Empirical Evaluation of Mixed-Project Defect Prediction Models","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Metric (unit); Predictive modelling; Product metric; Data modeling; Data mining; Focus (optics); Project management; Data collection; Software bug; Empirical research; Data science; Machine learning; Database; Software; Engineering; Systems engineering; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001368433,0.00005916207,0.00007322751,0.0001605128,0.00002014852,0.00001432407,0.0003633015,0.00004525532,0.00003241852],"category_scores_gemma":[0.0003590666,0.00005027949,0.0000513474,0.0003909469,0.00001773868,0.0003765826,0.0001169207,0.00007115247,0.00001650396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005586266,"about_ca_system_score_gemma":0.0001469398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008007223,"about_ca_topic_score_gemma":0.000003729632,"domain_scores_codex":[0.9986951,0.0001070448,0.0001371381,0.000209011,0.000706276,0.0001454218],"domain_scores_gemma":[0.9991142,0.0001579582,0.00002263053,0.0004013537,0.0002677085,0.00003617808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008450268,0.001301266,0.4196983,0.0002180342,0.0004130644,0.00001434456,0.01948584,0.07794626,0.002789569,0.06708612,0.03661828,0.3743445],"study_design_scores_gemma":[0.0001995581,0.0001056071,0.08238657,0.000006733305,0.000008995686,0.000004509108,0.000008551932,0.9071521,0.0049274,0.005125547,0.00001815106,0.00005628823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2627924,0.00003876822,0.7331247,0.00001067008,0.0001581806,0.000164866,7.649996e-7,0.0002033771,0.003506298],"genre_scores_gemma":[0.9574423,0.000002406565,0.04246086,0.000006096373,0.00001624187,0.00003000266,9.776229e-7,0.000004962736,0.00003619138],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8292058,"threshold_uncertainty_score":0.2050338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.232463589436113,"score_gpt":0.3634117234265972,"score_spread":0.1309481339904842,"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."}}