{"id":"W4312429593","doi":"10.1109/icsme55016.2022.00039","title":"What Made This Test Flake? Pinpointing Classes Responsible for Test Flakiness","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Regression testing; Code (set theory); Quality (philosophy); Fault (geology); Test (biology); Test suite; Class (philosophy); Reliability engineering; Debugging; Test case; Programming language; Software; Machine learning; Artificial intelligence; Software development; Engineering; Regression analysis","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":[0.003300497,0.001688294,0.0008714529,0.003968749,0.0007944385,0.00231046,0.001631762,0.001957397,0.002983619],"category_scores_gemma":[0.04870695,0.0006485204,0.001165593,0.001585357,0.001367967,0.003634709,0.001630488,0.002267348,0.001953859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001169056,"about_ca_system_score_gemma":0.001972784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005797828,"about_ca_topic_score_gemma":0.008181059,"domain_scores_codex":[0.99383,0.001309288,0.0003787095,0.001547276,0.00218886,0.0007459007],"domain_scores_gemma":[0.9647248,0.01803004,0.006132133,0.004862932,0.004272541,0.00197764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001423359,0.0004170549,0.1725093,0.001156584,0.0002998816,0.003401688,0.003177206,0.01854728,0.1305043,0.005081101,0.01978953,0.6436927],"study_design_scores_gemma":[0.0003699691,0.002428825,0.1987077,0.00152171,0.001177672,0.008186671,0.004855003,0.3630383,0.3232017,0.02094549,0.07498936,0.0005777408],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6574647,0.003376654,0.2677212,0.005660165,0.0009772391,0.0004865689,0.001526702,0.05543119,0.007355538],"genre_scores_gemma":[0.8963423,0.0003678418,0.09640236,0.0009811715,0.00009341378,0.00009978034,0.0009160381,0.002062489,0.002734537],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005797828,"threshold_uncertainty_score":0.01745492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03059816568578549,"score_gpt":0.2858525494159046,"score_spread":0.2552543837301191,"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."}}