{"id":"W2023740829","doi":"10.5555/2486788.2486927","title":"Automatic detection of performance deviations in the load testing of large scale systems","year":2013,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"Computer science; Benchmark (surveying); False positive paradox; Overhead (engineering); Set (abstract data type); Data mining; Test set; Scale (ratio); Machine learning; Artificial intelligence; Reliability engineering; Real-time computing; Engineering","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":[0.0009386024,0.00005981206,0.0001336814,0.00006287642,0.00006394277,0.00002857677,0.0003898154,0.00003791982,0.000005729594],"category_scores_gemma":[0.0001039938,0.00003520521,0.00002654907,0.0006714892,0.00002397685,0.0004767335,0.00005200623,0.00006269321,0.00003094488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003733983,"about_ca_system_score_gemma":0.00005943567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004452101,"about_ca_topic_score_gemma":0.00004052373,"domain_scores_codex":[0.9990194,0.00007502347,0.0003892668,0.0001150834,0.0002627531,0.0001384962],"domain_scores_gemma":[0.9989998,0.0002114155,0.0001485465,0.0004039516,0.0002213854,0.00001491091],"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":[0.000001730627,0.0003748104,0.8879528,0.002221646,0.00001694941,3.367238e-7,0.00962417,0.003046619,0.006893089,0.001107237,0.000127923,0.08863267],"study_design_scores_gemma":[0.0001033199,0.00005090104,0.2864058,0.00009328034,0.000001665468,0.000006258315,0.0003020261,0.7107387,0.00219302,0.00003442566,0.00002954221,0.00004112803],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9286567,0.00005375089,0.06984811,0.00003879913,0.0001468602,0.0003543958,3.495778e-7,0.0000575798,0.0008434795],"genre_scores_gemma":[0.9969841,0.000002143702,0.002900711,0.00001738066,0.00001237298,0.00005982273,1.443812e-7,0.000001984936,0.00002134877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.707692,"threshold_uncertainty_score":0.1435627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01270176190692431,"score_gpt":0.226176354115137,"score_spread":0.2134745922082126,"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."}}