{"id":"W4411950604","doi":"10.1109/forge66646.2025.00020","title":"Testing Refactoring Engine via Historical Bug Report driven LLM","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code refactoring; Computer science; Programming language; Software engineering; Software","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":[0.003924555,0.001072848,0.0004523768,0.002202498,0.0002521098,0.0006808966,0.001964503,0.0007364608,0.0009749802],"category_scores_gemma":[0.01981851,0.0004566053,0.0005784632,0.00075197,0.0005721985,0.001393541,0.0009127781,0.0008289424,0.0005278061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006127251,"about_ca_system_score_gemma":0.0009096525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002290139,"about_ca_topic_score_gemma":0.002930643,"domain_scores_codex":[0.9949474,0.001071334,0.0003827575,0.00144388,0.001912441,0.0002421875],"domain_scores_gemma":[0.9799534,0.006651678,0.003156143,0.005285995,0.004500806,0.0004519489],"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":[0.0008872128,0.001235715,0.1047729,0.0008691701,0.000222317,0.001749294,0.001654523,0.06830437,0.1606889,0.003075525,0.004452828,0.6520873],"study_design_scores_gemma":[0.0002277487,0.002483163,0.04535762,0.000136469,0.0002964251,0.00138807,0.0003141961,0.6970916,0.238098,0.002701174,0.01172131,0.000184205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5764394,0.0007043162,0.3813134,0.000243674,0.00007916552,0.0004676478,0.001056774,0.03725947,0.00243607],"genre_scores_gemma":[0.793726,0.0001467287,0.2024566,0.0001104108,0.00001775249,0.0001955458,0.001450015,0.0007633671,0.001133612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003924555,"threshold_uncertainty_score":0.02075523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02902503802755674,"score_gpt":0.2717983015721504,"score_spread":0.2427732635445937,"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."}}