{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002480683,0.001877268,0.001282088,0.005639812,0.0005725692,0.001734343,0.001897909,0.0007344441,0.002694686],"category_scores_gemma":[0.02296013,0.0004892628,0.0006374579,0.001934546,0.0006071901,0.001560345,0.0009717479,0.001013881,0.00147375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001237774,"about_ca_system_score_gemma":0.001561563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004779414,"about_ca_topic_score_gemma":0.002488312,"domain_scores_codex":[0.9937599,0.001621561,0.0003867408,0.000786381,0.00297479,0.0004704956],"domain_scores_gemma":[0.970248,0.01449172,0.004722098,0.004265316,0.005854544,0.0004183743],"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":[0.001310495,0.001202335,0.09225629,0.000891372,0.0002737506,0.001225427,0.0008418175,0.2348255,0.08017631,0.005587604,0.01390249,0.5675067],"study_design_scores_gemma":[0.00006077349,0.0003186788,0.02710869,0.0000463318,0.0000503367,0.0002657298,0.0001350767,0.9291844,0.03488261,0.004747484,0.003122882,0.00007694411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5167966,0.0006979155,0.3979402,0.0003603421,0.00009209476,0.0004835544,0.003547571,0.07287571,0.00720597],"genre_scores_gemma":[0.9216573,0.000139723,0.07211965,0.00007566487,0.00006264277,0.000277125,0.003328832,0.001119765,0.00121938],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.005639812,"threshold_uncertainty_score":0.01311928,"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."}}