{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005737639,0.000747412,0.001112631,0.001843194,0.0004920651,0.0005531671,0.001099039,0.0008829386,0.0003842934],"category_scores_gemma":[0.01743908,0.0003206836,0.00077472,0.0007380631,0.0006202786,0.00110387,0.0008338717,0.0009026449,0.0002025321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004960052,"about_ca_system_score_gemma":0.0006040268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002632655,"about_ca_topic_score_gemma":0.004228039,"domain_scores_codex":[0.9978688,0.001136452,0.000127992,0.0002999354,0.0004586447,0.0001081682],"domain_scores_gemma":[0.9905763,0.005593548,0.000741926,0.001360603,0.001536467,0.0001912788],"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":[0.0007641438,0.0006585327,0.02225259,0.000144329,0.0003605242,0.000298141,0.0004484863,0.4477357,0.02375983,0.006994079,0.003748628,0.4928349],"study_design_scores_gemma":[0.00002369817,0.000139936,0.00200232,0.000007342961,0.00001842654,0.00005967386,0.00002873986,0.9891054,0.004802014,0.003254225,0.0005446781,0.00001351747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1489306,0.0005510284,0.8483515,0.0003047779,0.00008973134,0.0001509361,0.000107975,0.0008880566,0.0006252342],"genre_scores_gemma":[0.7009439,0.0002152494,0.2969584,0.000207359,0.0001339974,0.0001864736,0.0006263904,0.00006966494,0.0006585295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005737639,"threshold_uncertainty_score":0.03034389,"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."}}