{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001261321,0.0009470721,0.000709823,0.002575781,0.0003960126,0.0008093413,0.001090791,0.001286824,0.001499369],"category_scores_gemma":[0.007618404,0.0004654153,0.0005586662,0.001410301,0.0003881679,0.001231017,0.0006246896,0.0009346077,0.0003186751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006704329,"about_ca_system_score_gemma":0.0006254239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009948942,"about_ca_topic_score_gemma":0.009976041,"domain_scores_codex":[0.9994839,0.0001235895,0.00003082885,0.0001186478,0.0001638383,0.00007905964],"domain_scores_gemma":[0.9946001,0.003785077,0.0005227219,0.0002512205,0.0006318755,0.0002090045],"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":[0.0002782324,0.0002808238,0.05223165,0.00004778161,0.000111208,0.0001495754,0.00006415392,0.8889114,0.001753919,0.0006551252,0.0005871085,0.05492903],"study_design_scores_gemma":[0.000004347995,0.00003909559,0.00237487,0.000003337019,0.00001070011,0.0000162248,0.00001433022,0.9969671,0.0002099003,0.0003239597,0.00003337182,0.000002716876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9419791,0.0003105821,0.05553288,0.0001230461,0.00002289214,0.00003552305,0.0001928146,0.0004422339,0.001360993],"genre_scores_gemma":[0.9888148,0.00004046358,0.01034805,0.00001072001,0.000004129868,0.0000134127,0.0002133126,0.00002344449,0.0005317276],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009948942,"threshold_uncertainty_score":0.01978207,"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."}}