{"id":"W1516438975","doi":"10.1002/stvr.1573","title":"Anomaly detection in performance regression testing by transaction profile estimation","year":2015,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Science Foundation Ireland","keywords":"Computer science; Regression testing; Workload; Anomaly detection; Data mining; Software performance testing; Software regression; Regression analysis; Regression; Non-regression testing; Software; Machine learning; Software quality; Statistics; Software system; Operating system; Software development","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":[0.001929767,0.0002208593,0.0002323832,0.0001283945,0.0002721793,0.0001110696,0.0002756256,0.0001901713,0.000001805713],"category_scores_gemma":[0.003299922,0.0001865492,0.00002962808,0.0011521,0.0001050616,0.001235154,0.00005406051,0.0002952946,0.00002034396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002848464,"about_ca_system_score_gemma":0.0001708186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003442207,"about_ca_topic_score_gemma":0.000006932316,"domain_scores_codex":[0.9978537,0.0001943199,0.0005750292,0.0007147665,0.0003638329,0.0002983711],"domain_scores_gemma":[0.9981153,0.0003822539,0.000260836,0.0006286632,0.0004525615,0.0001603933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003637037,0.0001505478,0.3654985,0.0002951489,0.000002232373,7.647214e-7,0.0007417316,0.002854885,0.001882943,0.00000571389,0.00009483311,0.6284363],"study_design_scores_gemma":[0.000617818,0.000273753,0.358707,0.0001997264,0.000006728042,0.00003421579,0.00005503312,0.6332483,0.005865254,0.000501832,0.0001824974,0.0003078927],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7072811,0.00008577246,0.2909878,0.0001127639,0.0003030442,0.0004193423,0.000002384817,0.0006720973,0.0001357021],"genre_scores_gemma":[0.8725328,0.00000757046,0.1272496,0.00002537708,0.00002767152,0.00009068862,0.00001175431,0.00001160483,0.00004291932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6303934,"threshold_uncertainty_score":0.7607256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02938539619239948,"score_gpt":0.2524789475198476,"score_spread":0.2230935513274481,"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."}}