{"id":"W4313142332","doi":"10.1109/tse.2022.3220740","title":"A Comprehensive Investigation of the Impact of Class Overlap on Software Defect Prediction","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Class (philosophy); Software; Data mining; Rank (graph theory); Feature (linguistics); Machine learning; Identification (biology); Artificial intelligence; 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":[0.005345702,0.001074795,0.0008930256,0.002632229,0.0007145831,0.001367269,0.001162363,0.0008928963,0.0005121031],"category_scores_gemma":[0.02080443,0.0002911279,0.001038219,0.002044341,0.0006862734,0.002644639,0.001354886,0.00125566,0.0002622153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007366001,"about_ca_system_score_gemma":0.0009705519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006285302,"about_ca_topic_score_gemma":0.006757194,"domain_scores_codex":[0.9961258,0.0008478395,0.0002811112,0.001170923,0.001279272,0.0002951983],"domain_scores_gemma":[0.9789549,0.01315929,0.002136276,0.002864447,0.002311604,0.0005733693],"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":[0.0006304593,0.0006610195,0.4232097,0.0004277877,0.0005529684,0.0007890104,0.0006435552,0.2590231,0.008562104,0.001736037,0.007582851,0.2961814],"study_design_scores_gemma":[0.00002139458,0.0004081296,0.1026154,0.00007691019,0.0001089087,0.0005580258,0.0005022823,0.8827661,0.007388038,0.002602383,0.002906167,0.00004624818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9494919,0.001413555,0.04470295,0.0003754034,0.00006010638,0.0000690631,0.001164367,0.001011458,0.001711255],"genre_scores_gemma":[0.9770493,0.0002533663,0.01938656,0.00007075118,0.00003087579,0.00004235473,0.00274467,0.00006720523,0.0003549891],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006285302,"threshold_uncertainty_score":0.02827114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01802205262569819,"score_gpt":0.2426999532341404,"score_spread":0.2246779006084422,"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."}}