{"id":"W4400582991","doi":"10.1145/3643771","title":"RavenBuild: Context, Relevance, and Dependency Aware Build Outcome Prediction","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada); University of Waterloo","funders":"","keywords":"Relevance (law); Dependency (UML); Outcome (game theory); Context (archaeology); Computer science; Data science; Artificial intelligence; History; Political science; Mathematics","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":[0.0004358444,0.0002346056,0.0002659056,0.0001661503,0.00009758412,0.0001457691,0.001595415,0.0001333091,0.000003205674],"category_scores_gemma":[0.002028061,0.0001608377,0.0001322708,0.0005537814,0.00004861235,0.000631685,0.0007606488,0.0003682027,0.00001270863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008668735,"about_ca_system_score_gemma":0.00003725265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008970777,"about_ca_topic_score_gemma":4.743145e-7,"domain_scores_codex":[0.9984381,0.000004351766,0.0003661028,0.0004872209,0.0004315002,0.0002727107],"domain_scores_gemma":[0.9987736,0.00024759,0.00008685184,0.0006509208,0.000157888,0.00008313355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005659201,0.0001473786,0.8439011,0.007275922,0.0002606649,0.00001059549,0.002258293,0.00109832,0.002456807,0.03685208,0.02035125,0.08533101],"study_design_scores_gemma":[0.003468497,0.002048707,0.5299287,0.01209689,0.0003421648,0.001022501,0.0003644809,0.1909952,0.06247326,0.02331318,0.1702669,0.003679531],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8975648,0.003408414,0.08652608,0.002187717,0.005637605,0.001036245,0.00004710175,0.003448514,0.0001435226],"genre_scores_gemma":[0.9835694,0.00006490818,0.01584566,0.00008515114,0.0001451298,0.00004601099,6.025514e-7,0.0000288397,0.0002143264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3139724,"threshold_uncertainty_score":0.6558772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009439507259860338,"score_gpt":0.2265177608086981,"score_spread":0.2170782535488378,"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."}}