{"id":"W4205420848","doi":"10.1007/s10515-021-00319-5","title":"Improving the prediction of continuous integration build failures using deep learning","year":2022,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmark (surveying); Feature engineering; Process (computing); Machine learning; Artificial intelligence; Task (project management); Construct (python library); Outcome (game theory); Recurrent neural network; Deep learning; Software; Code (set theory); Feature (linguistics); Artificial neural network; Data mining; Engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006564429,0.0001901972,0.0002023049,0.0003185947,0.0003704845,0.0001194944,0.0008555611,0.00005924881,0.00001402015],"category_scores_gemma":[0.002105951,0.0001770511,0.00008276865,0.001066086,0.00002477125,0.0003967214,0.0005793216,0.0006773883,0.000002094901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002454636,"about_ca_system_score_gemma":0.00006640422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001654773,"about_ca_topic_score_gemma":0.000001094337,"domain_scores_codex":[0.9982219,0.0001005582,0.0003507807,0.0003295031,0.0006002967,0.0003970009],"domain_scores_gemma":[0.9983563,0.0008576721,0.0001341899,0.0004654353,0.0001252615,0.00006113233],"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":[0.000002804173,0.00001761308,0.005440239,0.00004440179,0.00003558163,0.00001191987,0.0009357649,0.9579356,0.02698838,0.0003343385,0.0000393639,0.008213965],"study_design_scores_gemma":[0.0001745858,0.00008959767,0.007783056,0.00003202374,0.00001012903,0.00006934722,0.0001269265,0.9867316,0.00450973,0.000007640994,0.000318016,0.0001472856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2512318,0.0002360063,0.744197,0.00002282798,0.0005039948,0.0001886442,0.000004688061,0.003613361,0.000001663836],"genre_scores_gemma":[0.932677,0.000002674604,0.06712757,0.000008755394,0.00004979296,0.00006741317,0.00001125961,0.00004026659,0.00001528513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6814452,"threshold_uncertainty_score":0.7219933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008641220931652826,"score_gpt":0.2206911880083849,"score_spread":0.2120499670767321,"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."}}