{"id":"W4400680686","doi":"10.1109/saner60148.2024.00065","title":"TraceJIT: Evaluating the Impact of Behavioral Code Change on Just-In-Time Defect Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Japan Society for the Promotion of Science","keywords":"Computer science; Code (set theory); Programming language","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":[0.006010927,0.001745218,0.0007554485,0.002796857,0.0003604825,0.00136947,0.001401683,0.001364807,0.0009820056],"category_scores_gemma":[0.02937843,0.0003504789,0.001005149,0.001279793,0.0006591844,0.002324834,0.001093501,0.001744504,0.0005402531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001030929,"about_ca_system_score_gemma":0.001468685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01556994,"about_ca_topic_score_gemma":0.01393535,"domain_scores_codex":[0.9969034,0.0009273878,0.0002234471,0.0007666843,0.0009856541,0.000193524],"domain_scores_gemma":[0.9684664,0.021198,0.002689752,0.003688297,0.002735783,0.001221682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001597343,0.001433332,0.3396376,0.0004692987,0.0006564509,0.000258831,0.0002997036,0.4502912,0.004844302,0.001215872,0.009654321,0.1896417],"study_design_scores_gemma":[0.00004517737,0.0008683685,0.02518089,0.00003430384,0.00006801721,0.0001001759,0.00007659123,0.9691862,0.002208872,0.0009660374,0.001224038,0.00004135481],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9485686,0.001847377,0.03323684,0.0006335032,0.0001925004,0.0001354461,0.003918101,0.00908025,0.002387417],"genre_scores_gemma":[0.9647515,0.0002455252,0.02636049,0.0001122824,0.00005925357,0.00006160128,0.007165059,0.000253052,0.0009912252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01556994,"threshold_uncertainty_score":0.03178924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1352479393944258,"score_gpt":0.4260565789846571,"score_spread":0.2908086395902313,"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."}}