{"id":"W2103715428","doi":"10.1109/nafips.2007.383813","title":"Applying Novel Resampling Strategies To Software Defect Prediction","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Machine learning; Computer science; Resampling; Artificial intelligence; Software bug; Benchmark (surveying); Software; Software quality; Data mining; Class (philosophy); Skewness; Software metric; Classifier (UML); Software development","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":[0.0008890021,0.0001078593,0.00008772476,0.0002640405,0.0001119467,0.0002819733,0.000594791,0.00005605075,0.000009230403],"category_scores_gemma":[0.0006586013,0.0001035862,0.00004711853,0.0007290872,0.00001143519,0.0004932256,0.0002647425,0.000167925,0.00007370231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009406215,"about_ca_system_score_gemma":0.0000692122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005831198,"about_ca_topic_score_gemma":0.00001914922,"domain_scores_codex":[0.9985875,0.000006847831,0.0001716551,0.000362471,0.0004230141,0.0004484935],"domain_scores_gemma":[0.9984645,0.0007942672,0.00001636288,0.0004601898,0.00009843839,0.0001662717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006352032,0.0002695837,0.1039696,0.0002552102,0.0001562165,0.0001037665,0.003797878,0.208605,0.07539731,0.1268872,0.004634243,0.4758605],"study_design_scores_gemma":[0.002213097,0.001058309,0.7598075,0.000417563,0.00002372573,0.0002699221,0.001364896,0.1143007,0.05374189,0.005879885,0.05858654,0.002335957],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02520185,0.00003040201,0.9720852,0.00004709931,0.0003155257,0.0003181154,0.000001315162,0.001416881,0.0005835707],"genre_scores_gemma":[0.5020711,7.510014e-7,0.4975873,0.00007342781,0.00009173479,0.00004999682,0.000001137668,0.00001155354,0.0001130015],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.655838,"threshold_uncertainty_score":0.4224122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03284797929501758,"score_gpt":0.2967354537128123,"score_spread":0.2638874744177948,"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."}}