{"id":"W2067258447","doi":"10.1145/2188286.2188344","title":"Automated detection of performance regressions using statistical process control techniques","year":2012,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada); Queen's University","funders":"","keywords":"Regression testing; Computer science; Software performance testing; Process (computing); Software; Software regression; Non-regression testing; Software reliability testing; Data mining; Statistical process control; Statistical hypothesis testing; Machine learning; Software quality; Software system; Software development; Software construction; Statistics; 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":[0.0004540916,0.00009111023,0.0001607061,0.00007450667,0.0001132579,0.00001668124,0.0002277482,0.00007671628,0.000009781626],"category_scores_gemma":[0.00005883288,0.00006209262,0.00002604909,0.0002829534,0.00005728934,0.0007782359,0.00004303639,0.00008104764,0.000008625786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003878392,"about_ca_system_score_gemma":0.00005490199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002153314,"about_ca_topic_score_gemma":7.026951e-7,"domain_scores_codex":[0.999073,0.00005228987,0.0002730752,0.0001436722,0.0002148469,0.0002430794],"domain_scores_gemma":[0.9993011,0.00007190472,0.0001076001,0.0002942866,0.0001485573,0.00007652156],"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":[0.0001164931,0.0008962649,0.5979909,0.001661292,0.00008821674,0.000002474826,0.002460236,0.0006941769,0.1078283,0.005344176,0.0002477279,0.2826698],"study_design_scores_gemma":[0.0002038561,0.0001047349,0.03809829,0.0000948537,0.00001016499,0.00003663774,0.00002609647,0.7382048,0.2228784,0.00006019183,0.0001342448,0.0001477028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3533535,0.00002644452,0.6453601,0.00001081437,0.0001628839,0.0001520791,0.000001428075,0.0006886052,0.0002442356],"genre_scores_gemma":[0.9654836,0.000003284428,0.03441522,0.00002328615,0.00004210989,0.00001790042,4.6985e-7,0.000004727483,0.000009426896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7375106,"threshold_uncertainty_score":0.2532063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01484464576219385,"score_gpt":0.2998189450069804,"score_spread":0.2849742992447866,"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."}}