{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02242176,0.00432796,0.001567704,0.01180909,0.001102584,0.003113271,0.00271912,0.001731826,0.001431037],"category_scores_gemma":[0.05241861,0.0006621517,0.002234081,0.003677607,0.001520821,0.004238084,0.00169594,0.001831339,0.0005953699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00396116,"about_ca_system_score_gemma":0.0037516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01678747,"about_ca_topic_score_gemma":0.009456672,"domain_scores_codex":[0.9788962,0.008350888,0.002590244,0.002087098,0.007067436,0.001008075],"domain_scores_gemma":[0.9443716,0.03114238,0.007719513,0.004262467,0.01148004,0.001024079],"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":[0.001691137,0.006604391,0.1073921,0.00276035,0.001484245,0.000467091,0.0009749954,0.2273388,0.06599589,0.02346425,0.01335378,0.5484729],"study_design_scores_gemma":[0.0003321426,0.009204502,0.04157289,0.000582441,0.0004907647,0.0005419499,0.000656966,0.8910797,0.04060224,0.006012559,0.008581049,0.0003428059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2059786,0.00214081,0.7482672,0.001033993,0.0001830505,0.005994442,0.004253819,0.02563667,0.006511434],"genre_scores_gemma":[0.4214162,0.0003730087,0.5715907,0.0001816407,0.0000436444,0.002219295,0.003156141,0.0004426347,0.0005767561],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02242176,"threshold_uncertainty_score":0.118579,"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."}}