{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009342176,0.0002112683,0.0004373855,0.001208405,0.0001699948,0.0001208079,0.002391975,0.0001912757,0.00001046174],"category_scores_gemma":[0.0113188,0.0002032987,0.0003433888,0.003785378,0.00008021325,0.0004322974,0.0007268697,0.0002199648,0.000004213337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001625602,"about_ca_system_score_gemma":0.0004710597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002395764,"about_ca_topic_score_gemma":0.0000798137,"domain_scores_codex":[0.9975079,0.00005780836,0.0004697394,0.0009249859,0.0005996156,0.0004400001],"domain_scores_gemma":[0.9885542,0.008373293,0.0001005419,0.002460205,0.0003821787,0.0001295303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006390901,0.00009518784,0.8464178,0.0001493271,0.0005713791,0.000002479593,0.00005105629,0.07046399,0.00001029273,0.0001547154,0.006947941,0.07507186],"study_design_scores_gemma":[0.0007784759,0.0001398937,0.534538,0.0001436638,0.0004341906,6.981588e-7,0.000008708611,0.4558355,0.0001069995,0.001743237,0.006048909,0.0002217076],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02478054,0.0002526691,0.9728635,0.0001479148,0.0004229403,0.0004070917,0.0004685199,0.0006528918,0.000003911096],"genre_scores_gemma":[0.3334843,0.000005953037,0.6656069,0.0001390094,0.00003845619,0.00008394054,0.000574171,0.00002228131,0.00004500635],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3853715,"threshold_uncertainty_score":0.9970093,"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."}}