{"id":"W2484023394","doi":"10.1109/icst.2016.9","title":"A Framework to Evaluate the Effectiveness of Different Load Testing Analysis Techniques","year":2016,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; System under test; Oracle; Load testing; Reliability engineering; Data mining; Test data; Test case; Test (biology); Regression testing; Test Management Approach; Software; Regression analysis; Machine learning; Software system; Engineering","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":[0.002379412,0.0001030145,0.0002442514,0.0000879684,0.00006801,0.0000298524,0.0006913099,0.00005107634,0.00001097302],"category_scores_gemma":[0.001027419,0.00003764937,0.0001167592,0.001230013,0.00004258949,0.0001136445,0.0002670909,0.00005214932,0.00001852772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008360304,"about_ca_system_score_gemma":0.00004709028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008739454,"about_ca_topic_score_gemma":0.000007785125,"domain_scores_codex":[0.9986232,0.0003423007,0.0002182934,0.0002821711,0.0003666536,0.0001674186],"domain_scores_gemma":[0.9957704,0.002934463,0.00004834623,0.0008933963,0.0003067204,0.00004665983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004236038,0.0001062847,0.7506209,0.0001259564,0.0002963948,9.177606e-7,0.0004074261,0.00006211077,0.01819193,0.01090106,0.00003963347,0.2192051],"study_design_scores_gemma":[0.0001240737,0.0002506587,0.7949716,0.0004821234,0.00009350316,0.000001867702,0.000008459387,0.002464124,0.1826512,0.01872491,0.00004414197,0.0001832947],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3611347,0.000009777164,0.6377821,0.0002025355,0.00006212472,0.0002314611,4.15403e-7,0.0001353948,0.0004415137],"genre_scores_gemma":[0.9739037,0.000001699828,0.02591356,0.00005270125,0.0000204701,0.0000785481,4.563081e-8,0.000002969604,0.00002633577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.612769,"threshold_uncertainty_score":0.1535297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0205680247550138,"score_gpt":0.2989416562815763,"score_spread":0.2783736315265625,"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."}}