{"id":"W4403060990","doi":"10.1109/tse.2024.3472476","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","year":2024,"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":true,"ca_institutions":"York University; University of Ottawa","funders":"Science Foundation Ireland","keywords":"Computer science; Test (biology); Programming language; Code (set theory); Code coverage; Software engineering; Reliability engineering; Software; Engineering","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":[0.002000266,0.002218453,0.0008043775,0.002332951,0.000510273,0.001134538,0.001923972,0.001951194,0.001969409],"category_scores_gemma":[0.0106379,0.0005542759,0.001484144,0.0008857517,0.0006263684,0.002154561,0.001329823,0.003148502,0.001509498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001390245,"about_ca_system_score_gemma":0.001739137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01693412,"about_ca_topic_score_gemma":0.03020937,"domain_scores_codex":[0.9986584,0.0003922362,0.00008742434,0.000527372,0.0002233671,0.000111216],"domain_scores_gemma":[0.992694,0.004812276,0.000622818,0.0007803452,0.0007772539,0.0003132673],"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":[0.001210131,0.001245194,0.06855758,0.0008733444,0.0004568301,0.001067367,0.0007733957,0.3774287,0.01994033,0.002850067,0.03788181,0.4877153],"study_design_scores_gemma":[0.00004409345,0.0001582189,0.003011846,0.00003293166,0.00004009157,0.00009059631,0.00006794455,0.9862278,0.005425326,0.002782219,0.002078792,0.00004023271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4025442,0.002284654,0.4896101,0.001772476,0.0003709317,0.0005662098,0.01353,0.08664207,0.002679426],"genre_scores_gemma":[0.7101169,0.0003042731,0.2589047,0.0005967714,0.00007660829,0.0005226716,0.02508233,0.001397629,0.00299798],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01693412,"threshold_uncertainty_score":0.03367114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01784877115997165,"score_gpt":0.2560316308607052,"score_spread":0.2381828597007336,"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."}}