{"id":"W7125894075","doi":"10.1109/ase63991.2025.00121","title":"Rechecking Recheck Requests in Continuous Integration: An Empirical Study of OpenStack","year":2025,"lang":"","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Process (computing); Set (abstract data type); Empirical research; Work (physics); Baseline (sea); Scheme (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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004659917,0.0003933971,0.001019058,0.0005263072,0.0001981365,0.000285056,0.001643368,0.0004218659,0.00006122338],"category_scores_gemma":[0.0006156799,0.0003229004,0.0001213535,0.003131916,0.0001470789,0.001462293,0.0006744511,0.0007470434,0.00002251617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003680073,"about_ca_system_score_gemma":0.000680681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002221877,"about_ca_topic_score_gemma":0.004011196,"domain_scores_codex":[0.99414,0.00143201,0.002077545,0.001273855,0.0005585052,0.0005180679],"domain_scores_gemma":[0.9964044,0.0003627552,0.0003674179,0.002058245,0.0006787397,0.0001284242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001449329,0.003939923,0.7955737,0.0001829639,0.00004954758,0.00003099194,0.02186091,0.0001672423,0.00006587376,0.0008388955,0.0005216195,0.1766234],"study_design_scores_gemma":[0.006009238,0.006486787,0.7861131,0.00268917,0.00008435411,0.00002409394,0.02569218,0.1641523,0.004485731,0.002197739,0.0009594448,0.001105844],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9355722,0.000225133,0.04774442,0.0006594042,0.001961692,0.001913601,0.000001116972,0.0001388774,0.01178358],"genre_scores_gemma":[0.9922214,0.00004452941,0.005933343,0.0002382975,0.00005870488,0.00005650672,0.000001964343,0.00001132418,0.00143393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1755176,"threshold_uncertainty_score":0.9999223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06000843371496265,"score_gpt":0.3846077370672249,"score_spread":0.3245993033522622,"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."}}