{"id":"W4408693858","doi":"10.3390/software4020007","title":"Empirical Analysis of Data Sampling-Based Decision Forest Classifiers for Software Defect Prediction","year":2025,"lang":"en","type":"article","venue":"Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Decision tree; Computer science; Data mining; Sampling (signal processing); Machine learning; Software; Artificial intelligence; Statistics; Mathematics","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":[0.01467044,0.001478771,0.001643409,0.002449218,0.0007354288,0.001082552,0.001596161,0.001355549,0.0007734395],"category_scores_gemma":[0.02797598,0.0003134467,0.001209754,0.001693344,0.0007803046,0.001837056,0.0007474194,0.001858488,0.0003482181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001176509,"about_ca_system_score_gemma":0.001260524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007343754,"about_ca_topic_score_gemma":0.00576664,"domain_scores_codex":[0.9961994,0.001506946,0.0003119315,0.0006770787,0.0009467399,0.0003577792],"domain_scores_gemma":[0.9638953,0.02836932,0.001531904,0.001664117,0.004052693,0.00048664],"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":[0.001149448,0.0005018741,0.1104839,0.00037346,0.0002728764,0.000284595,0.0001823166,0.6943319,0.001591312,0.003644152,0.005538057,0.1816461],"study_design_scores_gemma":[0.00001338579,0.00008150097,0.005047658,0.00002627244,0.00002607286,0.00005738691,0.00003383804,0.9921862,0.0005913583,0.00157517,0.0003502652,0.00001083142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.683655,0.005584439,0.3044541,0.0007992883,0.0002176894,0.0003246116,0.002088605,0.0009562235,0.00191999],"genre_scores_gemma":[0.9611551,0.0005421013,0.03465826,0.0001120748,0.00008814521,0.0001284564,0.002838044,0.00003371125,0.0004440609],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01467044,"threshold_uncertainty_score":0.07758564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08940291661075161,"score_gpt":0.3824066076866245,"score_spread":0.2930036910758729,"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."}}