{"id":"W2154941531","doi":"10.1109/icsm.2009.5306331","title":"Automated performance analysis of load tests","year":2009,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada); Queen's University","funders":"","keywords":"Computer science; Baseline (sea); Load testing; Throughput; Reliability engineering; System under test; System testing; Test (biology); Real-time computing; Test case; Machine learning; 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":[0.0003396406,0.0000857404,0.0002421987,0.0001891106,0.0000469184,0.00002499429,0.0005114834,0.00004932191,0.00002531021],"category_scores_gemma":[0.00002765003,0.00006077936,0.0001083635,0.002141739,0.00002323601,0.0003761362,0.00004448916,0.00004477151,0.00004185532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004187009,"about_ca_system_score_gemma":0.00007649048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003213325,"about_ca_topic_score_gemma":0.000006306165,"domain_scores_codex":[0.9989986,0.00001958644,0.0002830652,0.0002223566,0.0003060512,0.0001703697],"domain_scores_gemma":[0.9989964,0.00003806374,0.00008482542,0.0006515791,0.0001807068,0.00004836286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002029255,0.0005088419,0.7656966,0.0001049663,0.0006015445,0.000005888619,0.001826743,0.01597018,0.002163331,0.00431371,0.004464098,0.2043238],"study_design_scores_gemma":[0.00006749351,0.0000704019,0.5337679,0.000006011036,0.00002772205,0.000001204586,0.000002450697,0.4647885,0.001069797,0.0000242993,0.0001146167,0.00005953623],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9675866,0.00004676488,0.0248504,0.0001910907,0.0001366417,0.0000807692,4.649577e-7,0.0009497603,0.006157454],"genre_scores_gemma":[0.9916031,0.00001066512,0.008000838,0.0001508204,0.000008718393,0.000001629427,0.000001095691,0.000001282558,0.0002218606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4488184,"threshold_uncertainty_score":0.247851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008841837450423766,"score_gpt":0.2554502326588025,"score_spread":0.2466083952083787,"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."}}