{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003537882,0.0001349186,0.0001747913,0.0001741416,0.000135676,0.00008451093,0.0006103114,0.00006706084,0.000003409003],"category_scores_gemma":[0.00183924,0.0001229416,0.00004848666,0.0007484999,0.00001315223,0.0001824801,0.0003645735,0.0001768026,0.000008994384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003823283,"about_ca_system_score_gemma":0.00009521835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005177047,"about_ca_topic_score_gemma":0.000002389315,"domain_scores_codex":[0.9987758,0.0000243438,0.000307546,0.0004327536,0.0001998032,0.000259721],"domain_scores_gemma":[0.9983785,0.0005578998,0.00008418517,0.0007643758,0.0001453214,0.00006968062],"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":[0.000004080067,0.0002807728,0.3001338,0.00008908162,0.00004874928,0.001186071,0.0002775933,0.0001821811,0.00469427,0.0103089,0.2017603,0.4810342],"study_design_scores_gemma":[0.0007471413,0.0005518883,0.09940843,0.0008877469,0.00005850664,0.00178123,0.000004754002,0.4924258,0.02105838,0.2313681,0.1496563,0.002051651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002160165,0.00006218209,0.9610442,0.0007984504,0.0006971393,0.0000706251,6.676714e-8,0.02085659,0.0143106],"genre_scores_gemma":[0.3692505,5.717634e-7,0.6275213,0.00016318,0.00006401548,0.00001205158,5.568348e-7,0.000006692482,0.00298114],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4922436,"threshold_uncertainty_score":0.5013412,"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."}}