{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002461963,0.0002652926,0.0002891039,0.0004973583,0.0002297557,0.00002862621,0.0008263916,0.00008245023,0.00002983842],"category_scores_gemma":[0.0001792748,0.0002374483,0.0004678119,0.001548637,0.00005736394,0.000244813,0.00002788035,0.0007743549,0.000004238634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000525964,"about_ca_system_score_gemma":0.0001973177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007932048,"about_ca_topic_score_gemma":8.54756e-7,"domain_scores_codex":[0.9978737,0.0001194265,0.0003873116,0.0003958029,0.0008823552,0.0003414521],"domain_scores_gemma":[0.9975064,0.001194272,0.0001291881,0.0008981159,0.0001603981,0.0001115816],"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":[0.00002519211,0.00007636166,0.005575825,0.00007860965,0.00011941,0.000002546499,0.0004248659,0.9885891,0.003464928,0.00004663794,0.0001006408,0.001495871],"study_design_scores_gemma":[0.002217983,0.003130219,0.3844984,0.0005206557,0.00009169698,0.0001359114,0.00009516199,0.4817485,0.1261069,0.0001452158,0.0003406908,0.0009687291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4140313,0.00003656492,0.584515,0.00001147082,0.0006674746,0.0002580931,0.0001096146,0.0003689718,0.000001483238],"genre_scores_gemma":[0.9899175,0.000005558441,0.009820537,0.00001953094,0.00002535472,0.0001362607,0.000004158061,0.00004516642,0.00002594846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5758862,"threshold_uncertainty_score":0.968286,"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."}}