{"id":"W4415312861","doi":"10.1145/3771929","title":"Continuously Learning Bug Locations","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Software bug; Software regression; Software; Code (set theory); Deep learning; Forgetting; Source code; Mean reciprocal rank","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":[0.0007663402,0.0001837872,0.0002524266,0.0005557821,0.0001961413,0.00006949469,0.0005932382,0.000147211,0.00001085379],"category_scores_gemma":[0.005517759,0.0001981802,0.00006773136,0.0006876444,0.00004507727,0.0001510238,0.0000421373,0.0006335224,0.00001529173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005466277,"about_ca_system_score_gemma":0.00006991105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000276297,"about_ca_topic_score_gemma":0.000002096452,"domain_scores_codex":[0.9986951,0.0001685073,0.0002079317,0.000430553,0.0001323864,0.0003655283],"domain_scores_gemma":[0.9915089,0.007619965,0.00002350767,0.0006583335,0.00008569851,0.0001035833],"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":[0.00002699008,0.0001222343,0.00552695,0.0002363949,0.0003091192,0.00002939738,0.0009997223,0.3675894,0.002008633,0.01336822,0.0002854414,0.6094975],"study_design_scores_gemma":[0.008429484,0.00239902,0.2658579,0.001529125,0.0004794021,0.0009639293,0.0006338134,0.3138723,0.08132032,0.01730101,0.3019162,0.005297579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009920311,0.0003992738,0.9868856,0.0005749574,0.0007568836,0.0001248511,0.000001660486,0.00131786,0.00001856648],"genre_scores_gemma":[0.2065006,0.00009656909,0.7921096,0.0001159752,0.00002307594,0.0000863328,0.000001587397,0.00001937659,0.001046914],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6041999,"threshold_uncertainty_score":0.8081554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04947276161402145,"score_gpt":0.3231860867865974,"score_spread":0.273713325172576,"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."}}