{"id":"W3096465442","doi":"10.1002/spe.2929","title":"Root causing, detecting, and fixing flaky tests: State of the art and future roadmap","year":2020,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University; University of Guelph; University of Guelph-Humber","funders":"","keywords":"Pace; Root cause; Software deployment; Test (biology); Field (mathematics); Computer science; Root (linguistics); Engineering; Data science; Software; Engineering management; Software engineering; Operations management","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":[0.0002809153,0.0001642202,0.0001720086,0.0000330297,0.0003235217,0.0002284659,0.0002804992,0.00005129842,0.000001721511],"category_scores_gemma":[0.003440591,0.0001250307,0.00002298587,0.0003399424,0.0001869742,0.0009898989,0.0005747635,0.0002492002,9.980786e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001036099,"about_ca_system_score_gemma":0.00005218411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008563777,"about_ca_topic_score_gemma":0.00001108394,"domain_scores_codex":[0.9987867,0.0000920899,0.000212847,0.0004509238,0.0002370912,0.0002203894],"domain_scores_gemma":[0.9984086,0.0007577459,0.0002342028,0.0003521668,0.0001121509,0.0001351302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009147711,0.00009781788,0.153048,0.000320777,0.00005050777,0.0001311183,0.1663176,0.0000182855,0.002741602,0.0006072491,0.005857283,0.6707183],"study_design_scores_gemma":[0.004287429,0.004560967,0.2358156,0.002549317,0.0003736497,0.00879459,0.01526256,0.04469772,0.0950712,0.05660688,0.5258419,0.006138196],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7290197,0.004796202,0.2489031,0.01284446,0.0003689431,0.0003966815,0.00000455329,0.003445715,0.0002206768],"genre_scores_gemma":[0.8479337,0.0001961554,0.1498688,0.00185841,0.00009132215,0.0000170337,2.573539e-7,0.00001284515,0.00002148797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.66458,"threshold_uncertainty_score":0.5098603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01675070680961436,"score_gpt":0.2725751747409247,"score_spread":0.2558244679313103,"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."}}