{"id":"W4390838289","doi":"10.1145/3640331","title":"Method-level Bug Prediction: Problems and Promises","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; York University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Software bug; Java; Class (philosophy); Software; Software regression; Granularity; Predictive modelling; Data science; Data mining; Machine learning; Software engineering; Artificial intelligence; Software development; Software quality; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001312369,0.0002476199,0.0002776837,0.0004913732,0.0001259933,0.0001682419,0.0003897849,0.0001827918,0.00001384533],"category_scores_gemma":[0.001424976,0.0002348746,0.00006573477,0.0005667481,0.00004338489,0.0003289241,0.00004859381,0.0005860392,0.000008997785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004735816,"about_ca_system_score_gemma":0.00005564476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002232737,"about_ca_topic_score_gemma":0.000001800041,"domain_scores_codex":[0.9983263,0.0001700147,0.0002356271,0.0006738312,0.0002046885,0.0003895348],"domain_scores_gemma":[0.9919333,0.007254753,0.00001553632,0.0005525803,0.00005261012,0.0001911889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001804049,0.00005972616,0.0004166232,0.001085974,0.0003430775,0.0000746478,0.00255323,0.07685511,0.003099262,0.003813466,0.000165436,0.9115154],"study_design_scores_gemma":[0.002672026,0.002425461,0.04075726,0.001788831,0.0003821378,0.006432719,0.0001418893,0.7285461,0.03042145,0.0144671,0.1689664,0.002998573],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004587601,0.002124972,0.9895179,0.0004896348,0.0009716522,0.0002287935,0.00002677288,0.002049005,0.000003688321],"genre_scores_gemma":[0.02586551,0.0003605185,0.9731036,0.00003760088,0.00008206664,0.000170971,0.000002265264,0.00004245773,0.0003349957],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9085168,"threshold_uncertainty_score":0.9577909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1337795702784962,"score_gpt":0.3378330058477902,"score_spread":0.2040534355692941,"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."}}