{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05335568,0.003303454,0.003630097,0.005008307,0.001927422,0.006791856,0.006931013,0.004824227,0.002128061],"category_scores_gemma":[0.1765404,0.001584486,0.002647052,0.006993837,0.004306947,0.02022475,0.004503762,0.01220257,0.00426308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002392705,"about_ca_system_score_gemma":0.00486802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02095682,"about_ca_topic_score_gemma":0.01213527,"domain_scores_codex":[0.959857,0.01567339,0.001787013,0.01058561,0.01104679,0.001050192],"domain_scores_gemma":[0.7298616,0.1918579,0.008964104,0.03823204,0.02708658,0.003997786],"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":[0.0005330553,0.0005648086,0.1464151,0.001459975,0.0006345958,0.0001502853,0.001351462,0.03893546,0.001865855,0.01264215,0.0783708,0.7170764],"study_design_scores_gemma":[0.0001637315,0.0007664845,0.07051471,0.001849677,0.000351188,0.0007844293,0.002600492,0.6442244,0.005063422,0.1890712,0.08413029,0.0004799933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1097055,0.08647993,0.6149586,0.1528101,0.003472593,0.0003703209,0.01050763,0.01401522,0.007680085],"genre_scores_gemma":[0.560373,0.0200795,0.3750288,0.01110325,0.005251976,0.0006139664,0.01949944,0.002220972,0.005829174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05335568,"threshold_uncertainty_score":0.2821752,"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."}}