{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001409481,0.001745761,0.001007735,0.002585822,0.0003663579,0.0009595298,0.001997584,0.001252216,0.001413465],"category_scores_gemma":[0.01129834,0.0005467289,0.0009242689,0.001295811,0.0005084722,0.00214714,0.001415772,0.00172894,0.00113376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007993166,"about_ca_system_score_gemma":0.001409623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00666044,"about_ca_topic_score_gemma":0.008770238,"domain_scores_codex":[0.9985266,0.0002172945,0.00009571145,0.0007631685,0.0002828922,0.0001142962],"domain_scores_gemma":[0.9939167,0.003000477,0.0008540167,0.000652677,0.001261816,0.0003142693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005125038,0.0006785159,0.08024874,0.0004939668,0.00026349,0.0004467361,0.0002733732,0.2355612,0.008460787,0.001053233,0.01394597,0.6580615],"study_design_scores_gemma":[0.00002682141,0.0001727863,0.005820498,0.00003667409,0.00005357281,0.000127884,0.00006260566,0.9869341,0.002750182,0.002339433,0.001657094,0.00001834895],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5342503,0.003954112,0.4340063,0.001585208,0.0004061976,0.0001992707,0.002623343,0.0193216,0.003653719],"genre_scores_gemma":[0.9280525,0.0003826546,0.0649595,0.0002852973,0.0001174988,0.00009218863,0.003344517,0.0002260513,0.002539829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00666044,"threshold_uncertainty_score":0.01324332,"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."}}