{"id":"W3059397974","doi":"10.1016/j.infsof.2020.106392","title":"Predicting continuous integration build failures using evolutionary search","year":2020,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Engineering Research","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Benchmark (surveying); Genetic programming; Context (archaeology); Process (computing); Software; Software engineering; Resource (disambiguation); Search-based software engineering; Machine learning; Outcome (game theory); Software development; Artificial intelligence; Data mining; Software development process; Programming language","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":[0.0001555622,0.0001033643,0.0001230989,0.0003777263,0.0001501035,0.0001362916,0.0004283712,0.0001590511,0.000007461929],"category_scores_gemma":[0.001721766,0.000102265,0.00002122137,0.000771068,0.00008289325,0.001447421,0.0003671315,0.0003337416,0.00003250774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005561276,"about_ca_system_score_gemma":0.00008259142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003807477,"about_ca_topic_score_gemma":0.000001269699,"domain_scores_codex":[0.9990836,0.00001889856,0.0002537933,0.0001580585,0.0002487774,0.0002369109],"domain_scores_gemma":[0.9992926,0.0001519544,0.00005673236,0.000209748,0.000202765,0.00008623114],"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":[0.00002097042,0.00002287724,0.3433807,0.0001566349,0.00004190914,0.00001636891,0.005038739,0.003993933,0.0009198894,0.04463395,0.001077553,0.6006965],"study_design_scores_gemma":[0.0007154467,0.0002918997,0.01973977,0.00007201102,0.000006054149,0.0001968592,0.0008068641,0.9643832,0.002858509,0.001563005,0.008997992,0.0003683556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1918855,0.0001208482,0.8032023,0.002855767,0.00007064182,0.0001542426,0.000003506658,0.001683768,0.0000234071],"genre_scores_gemma":[0.8519142,0.00001148775,0.1477714,0.0002489547,0.00002564197,0.00001177239,0.000007860857,0.000005068437,0.000003652005],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9603893,"threshold_uncertainty_score":0.4170246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01491868679929527,"score_gpt":0.247967591597911,"score_spread":0.2330489047986157,"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."}}