{"id":"W2982119098","doi":"10.1016/j.infsof.2019.106205","title":"Automatic prediction of the severity of bugs using stack traces and categorical features","year":2019,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Engineering Research","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Categorical variable; Computer science; Software bug; Software regression; Data mining; Machine learning; Software; Classifier (UML); Tracing; Predictive modelling; Artificial intelligence; Reliability engineering; Software quality; Software development; Engineering; Operating system","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":[0.0001407805,0.00005444694,0.0001082437,0.0001961601,0.00003489103,0.00002082045,0.0002407081,0.0001133342,0.000003078287],"category_scores_gemma":[0.0003522103,0.0000401017,0.0000141925,0.0003829059,0.00009489286,0.0004975752,0.0001951757,0.0001322537,0.000001129286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001915041,"about_ca_system_score_gemma":0.00004126276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002187758,"about_ca_topic_score_gemma":8.898235e-7,"domain_scores_codex":[0.9994824,0.00001206101,0.0001884161,0.00006595397,0.0001591853,0.00009197757],"domain_scores_gemma":[0.9994456,0.000118748,0.00009364157,0.0002405921,0.00008444983,0.0000169472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006086256,0.00002791713,0.6386285,0.0006653938,0.0000322208,4.466528e-7,0.002795279,0.0005306666,0.0005118156,0.01405716,0.0001417462,0.3426028],"study_design_scores_gemma":[0.0004593268,0.0001329479,0.8553899,0.00006185786,0.000006961044,0.0001581294,0.0001984378,0.1342103,0.005308969,0.003618458,0.0003486038,0.0001060725],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9187691,0.00008563105,0.08053292,0.0001536961,0.00009016028,0.0001439331,0.000004383342,0.0002123571,0.000007805314],"genre_scores_gemma":[0.9877954,0.00001098528,0.01216802,0.00001301406,0.000001924279,0.000002792724,7.980955e-7,0.000001727383,0.000005390547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3424967,"threshold_uncertainty_score":0.16353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007654808858986597,"score_gpt":0.2244289516265802,"score_spread":0.2167741427675936,"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."}}