{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007619392,0.001465874,0.001147907,0.006302548,0.0005542691,0.001889198,0.001404594,0.0008485909,0.0007294491],"category_scores_gemma":[0.04179646,0.000506932,0.0006679893,0.003318863,0.0008554608,0.001536407,0.0008504048,0.00144519,0.0003116457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007808335,"about_ca_system_score_gemma":0.001580954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006452038,"about_ca_topic_score_gemma":0.003667355,"domain_scores_codex":[0.9882486,0.003670477,0.0008344332,0.001995195,0.004841531,0.0004097305],"domain_scores_gemma":[0.9231796,0.04286369,0.01585547,0.007954799,0.009572318,0.0005741175],"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":[0.0005674044,0.0005797183,0.09017208,0.0003564239,0.0003443859,0.0006335863,0.001016663,0.1957144,0.05235758,0.01020467,0.003856292,0.6441967],"study_design_scores_gemma":[0.00003894023,0.0001825773,0.01178267,0.00002991459,0.00004625007,0.0001929002,0.00005424846,0.9599037,0.02063136,0.005573435,0.001483158,0.00008082204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0688227,0.0003082529,0.9186235,0.0001212865,0.00003897839,0.0001614616,0.0002648103,0.0108708,0.0007882105],"genre_scores_gemma":[0.7599416,0.0002045797,0.2379098,0.00006898104,0.00007057756,0.0003177801,0.0006355628,0.0003962688,0.0004547706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007619392,"threshold_uncertainty_score":0.04029572,"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."}}