{"id":"W7130731024","doi":"10.1109/swc65939.2025.00299","title":"Time Travel: LLM-Assisted Semantic Behavior Localization with Git Bisect","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University; University of Waterloo","funders":"","keywords":"Workflow; Annotation; Software; Semantics (computer science); Process (computing)","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":[0.002838739,0.002414255,0.0009598438,0.002462025,0.0008541706,0.002926576,0.003717344,0.001683107,0.006868028],"category_scores_gemma":[0.01946392,0.001181957,0.002247353,0.001397867,0.001519475,0.005725844,0.005621406,0.003563728,0.004968156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001619972,"about_ca_system_score_gemma":0.003860368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01012652,"about_ca_topic_score_gemma":0.0213336,"domain_scores_codex":[0.9969332,0.0007929819,0.000237084,0.0008573937,0.0009962292,0.000183074],"domain_scores_gemma":[0.9922225,0.00293891,0.0006951091,0.002731465,0.001157305,0.0002547736],"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":[0.001443967,0.0005526346,0.02301197,0.002057939,0.0004681221,0.001016821,0.004116731,0.1312419,0.04025564,0.06028846,0.1171161,0.6184298],"study_design_scores_gemma":[0.00009062823,0.0001252776,0.001178208,0.000118711,0.00009219511,0.0002137128,0.0003648385,0.878813,0.0282853,0.05340191,0.03721279,0.0001032972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01038069,0.000268471,0.7488756,0.0004158229,0.0001155722,0.0001329251,0.002673939,0.2354898,0.001647249],"genre_scores_gemma":[0.1978052,0.0002037047,0.7616524,0.0006487424,0.0000622904,0.0003886551,0.01229932,0.02284842,0.004091282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01012652,"threshold_uncertainty_score":0.02297586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01481386298805983,"score_gpt":0.2654844293814271,"score_spread":0.2506705663933673,"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."}}