{"id":"W2014820189","doi":"","title":"An Industrial Case Study on the Automated Detection of Performance Regressions in Heterogeneous Environments","year":2015,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Polytechnique Montréal; York University; Blackberry (Canada)","funders":"","keywords":"Computer science; Weighting; Automation; Benchmark (surveying); Regression testing; Machine learning; Data mining; Software; Artificial intelligence; Software system; Engineering; Operating system","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":[0.0008221999,0.00009446292,0.000120027,0.0000776905,0.00009033938,0.00002413816,0.0003573074,0.00007023401,0.000002703313],"category_scores_gemma":[0.0000384448,0.00005251734,0.00002057347,0.0002839752,0.00003283986,0.0002658756,0.00008819832,0.0001344627,0.00001740736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007551739,"about_ca_system_score_gemma":0.00004190083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002916578,"about_ca_topic_score_gemma":0.00007485791,"domain_scores_codex":[0.9988282,0.0002501587,0.0002700639,0.0002307471,0.000280508,0.0001403154],"domain_scores_gemma":[0.999064,0.00005736512,0.00008549141,0.0007052227,0.00001954815,0.00006832434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001992656,0.004196812,0.8470286,0.00001822087,0.00005503372,0.0006980433,0.01920802,0.03390895,0.002771535,0.0000339582,0.0001305739,0.09175102],"study_design_scores_gemma":[0.002873083,0.005232167,0.05403052,0.00006754599,0.00001061228,0.0008697133,0.004816029,0.8858491,0.04572972,0.00002061757,0.0001684275,0.0003325011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974788,0.00000426608,0.001547804,0.00002684748,0.0003080952,0.000445214,4.1862e-7,0.0001353236,0.00005323288],"genre_scores_gemma":[0.999835,8.368737e-7,0.00006976209,0.00001928876,0.00002385526,0.00003353184,2.35806e-7,0.000003870141,0.0000135883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8519401,"threshold_uncertainty_score":0.2141595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07025538241745381,"score_gpt":0.2929690648829657,"score_spread":0.2227136824655119,"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."}}