{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008591433,0.00128294,0.0007417723,0.0011507,0.0002449366,0.0007160535,0.001098183,0.001031262,0.001235694],"category_scores_gemma":[0.003836959,0.0004696681,0.0004930637,0.0006845973,0.0003226416,0.001271251,0.0007843236,0.001915004,0.0006040198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000669302,"about_ca_system_score_gemma":0.0008945202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01121935,"about_ca_topic_score_gemma":0.01465304,"domain_scores_codex":[0.9995561,0.00007301444,0.0000243555,0.0001331158,0.0001192862,0.00009415318],"domain_scores_gemma":[0.9972017,0.001452312,0.0003206646,0.0002319967,0.0006232563,0.0001701321],"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":[0.000459747,0.000613889,0.03538254,0.00009252821,0.0001190057,0.000201416,0.00006007767,0.7616726,0.004627315,0.0009529972,0.006144384,0.1896735],"study_design_scores_gemma":[0.000002320194,0.00001324429,0.0005595333,0.000002349927,0.000003219636,0.000004547484,0.000002500673,0.9986717,0.0003450783,0.0003408267,0.00005318157,0.00000154294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7332541,0.001781819,0.2563053,0.000755304,0.0002030581,0.00003742253,0.0008616496,0.004411182,0.002390036],"genre_scores_gemma":[0.9871076,0.0001125077,0.01082975,0.00005779697,0.00003147306,0.00001156486,0.0006324796,0.00004371865,0.001173216],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01121935,"threshold_uncertainty_score":0.02230811,"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."}}