{"id":"W2920526824","doi":"10.1007/s10664-019-09695-9","title":"An empirical study of the long duration of continuous integration builds","year":2019,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Duration (music); Computer science; Set (abstract data type); Empirical research; Software development; Cache; Software; Software engineering; Process management; Engineering; Statistics; Operating system; 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":[0.0004725772,0.0001942511,0.0003262995,0.0001803148,0.00003991037,0.00005668537,0.001116576,0.0001132402,0.00001514307],"category_scores_gemma":[0.001536262,0.0001474092,0.0000979603,0.001048696,0.00002426989,0.0004284882,0.0002677703,0.0003617307,0.000009487519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009197221,"about_ca_system_score_gemma":0.00006817066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003744035,"about_ca_topic_score_gemma":0.000006948583,"domain_scores_codex":[0.9979908,0.00009961973,0.0005054274,0.0003893855,0.0007200167,0.000294764],"domain_scores_gemma":[0.9977026,0.0008527294,0.0001189817,0.001013509,0.0002091985,0.0001029907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006631778,0.0002795185,0.9615797,0.00004176248,0.00002366179,0.000003088157,0.001571316,0.03270349,0.002013381,0.00003172963,0.00006666603,0.001679079],"study_design_scores_gemma":[0.0004034713,0.0005050916,0.9385241,0.00005527132,0.000007447658,0.000007128902,0.00005644591,0.05427423,0.005923209,0.00001590691,0.00005983316,0.0001678586],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6099686,0.00002438615,0.3891019,0.00004963697,0.0003219886,0.0003246614,0.000001065559,0.00020485,0.000002899779],"genre_scores_gemma":[0.9910079,7.491404e-7,0.008839797,0.00002245738,0.00005046264,0.00002193018,0.00000222915,0.00002494539,0.00002957281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3810393,"threshold_uncertainty_score":0.6011171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01694477932419394,"score_gpt":0.2973705753052279,"score_spread":0.280425795981034,"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."}}