{"id":"W4385489212","doi":"10.1109/compsac57700.2023.00112","title":"Prediction of Bug Inducing Commits Using Metrics Trend Analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; IBM (Canada); Western University","funders":"","keywords":"Commit; Computer science; Metric (unit); Process (computing); Quality (philosophy); Source code; Software quality; Software development; Software; Programming language; Database; Engineering","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":[0.002871984,0.0009574895,0.0005329245,0.009773025,0.0003434726,0.0009288383,0.0006527412,0.0007102536,0.0006427569],"category_scores_gemma":[0.0187304,0.0003192331,0.00059134,0.00413085,0.0002271179,0.001313776,0.0006819385,0.001080389,0.0009036469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004918531,"about_ca_system_score_gemma":0.000746435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005252689,"about_ca_topic_score_gemma":0.008793457,"domain_scores_codex":[0.9985494,0.0001873962,0.0001603833,0.0004457933,0.0005442927,0.0001128463],"domain_scores_gemma":[0.9764512,0.009336947,0.006414208,0.002015349,0.004777203,0.001005042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003050608,0.000202552,0.84345,0.000240296,0.0001377622,0.0003444427,0.0003169533,0.01787178,0.005590524,0.0009125827,0.009107816,0.1215203],"study_design_scores_gemma":[0.00004847585,0.0006300391,0.5271839,0.00007900905,0.0001047845,0.000715001,0.00044145,0.4526202,0.007672499,0.002816991,0.007616368,0.00007124795],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9416671,0.0009856502,0.03886602,0.0003341016,0.0001021334,0.0001287789,0.01209897,0.004278739,0.00153846],"genre_scores_gemma":[0.9404684,0.0003564993,0.03334667,0.00003279726,0.00006692095,0.0001324458,0.02421018,0.0002507451,0.001135465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009773025,"threshold_uncertainty_score":0.01518869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1048188226508236,"score_gpt":0.3137697313756579,"score_spread":0.2089509087248343,"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."}}