{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003443667,0.000282026,0.0002245764,0.0003051761,0.0002943809,0.0002725372,0.0002651197,0.0001260977,0.000002225597],"category_scores_gemma":[0.0004255959,0.0002922316,0.0001344088,0.0004710964,0.00002598792,0.0006548538,0.00001067741,0.0003322635,0.000002604951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049137,"about_ca_system_score_gemma":0.00007390536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004810248,"about_ca_topic_score_gemma":0.00001136776,"domain_scores_codex":[0.9985114,0.00001151503,0.0002809961,0.000557418,0.0002006572,0.0004379714],"domain_scores_gemma":[0.9965426,0.002801317,0.00003393118,0.0004353531,0.00007047758,0.0001163512],"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":[0.00002653465,0.0006105746,0.003060476,0.003684525,0.0004057478,0.0003967201,0.01670396,0.8946993,0.007049777,0.003506947,0.003809768,0.06604563],"study_design_scores_gemma":[0.0001540956,0.0001173499,0.0000308666,0.0004419704,0.00003947857,0.0001092065,0.00002019333,0.992543,0.005458753,0.0004939426,0.0002731899,0.0003178867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008022438,0.0006244929,0.9593624,0.00003331389,0.0006667533,0.0002697343,0.000165932,0.03084956,0.000005382283],"genre_scores_gemma":[0.5993686,0.0000127603,0.4002969,0.000031263,0.00008010405,0.00008137764,0.000002688558,0.00005145224,0.00007480801],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5913462,"threshold_uncertainty_score":0.999953,"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."}}