{"id":"W4407375771","doi":"10.1109/tse.2025.3541166","title":"Automated Test Case Repair Using Language Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Computer science; Programming language; Test (biology); Software engineering; Model-based testing; Reliability engineering; Test case; Natural language processing; Machine learning","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":[0.0001754403,0.0002229761,0.0001896687,0.0004364835,0.0002114916,0.00009569794,0.0003136881,0.0001111882,0.00000316187],"category_scores_gemma":[0.0001269132,0.0002428247,0.0001308215,0.0008844071,0.00001742564,0.0003541226,0.000007101853,0.0002822754,0.000005827598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001464468,"about_ca_system_score_gemma":0.00007236205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001809573,"about_ca_topic_score_gemma":0.000004738054,"domain_scores_codex":[0.9988812,0.00002033586,0.0002463415,0.0003911656,0.0001534266,0.0003074914],"domain_scores_gemma":[0.9984996,0.000632886,0.00003498438,0.0006849102,0.00006829957,0.00007936628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002251015,0.0001050715,0.00004631103,0.0000817144,0.00004489887,0.0008406144,0.000361434,0.9853131,0.0004115987,0.0001580571,0.0005646908,0.01207027],"study_design_scores_gemma":[0.0001379384,0.00003231957,0.00001197604,0.0002116372,0.00002124452,0.0006315795,0.000004883669,0.9922715,0.006227059,0.0001946797,0.00002675878,0.0002284032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009358951,0.00009649662,0.904767,0.00001547067,0.0004894387,0.0001318616,0.00001027758,0.08510706,0.00002342799],"genre_scores_gemma":[0.5348777,0.000001941582,0.4649621,0.00006583085,0.00001055454,0.00002198244,3.550935e-7,0.00001705102,0.00004259674],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5255187,"threshold_uncertainty_score":0.9902103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0169379124492823,"score_gpt":0.264907490693648,"score_spread":0.2479695782443657,"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."}}