{"id":"W1967311823","doi":"10.5555/2819009.2819227","title":"Load testing large-scale software systems","year":2015,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Load testing; Software reliability testing; Reliability engineering; Software performance testing; Software engineering; Scale (ratio); System integration testing; Software; Software system; Software construction; Operating 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":[0.001177522,0.0001288084,0.0001864589,0.00004096463,0.0001144854,0.0001782152,0.0006746716,0.00008200842,0.00000471242],"category_scores_gemma":[0.0004217901,0.00009316446,0.00004208959,0.000471314,0.00002235149,0.0005864642,0.0002841918,0.0001033199,0.0006201494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000146501,"about_ca_system_score_gemma":0.0003326665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002386224,"about_ca_topic_score_gemma":0.00001576885,"domain_scores_codex":[0.9984273,0.00005709407,0.0002767985,0.0003642982,0.0005093209,0.0003652309],"domain_scores_gemma":[0.9983265,0.0001222834,0.00007290652,0.0007558522,0.0005101081,0.0002123044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001260628,0.0003553602,0.8775619,0.0004196777,0.00003954044,0.0000485293,0.006562931,0.004865329,0.00006555278,0.004939591,0.0687105,0.03641848],"study_design_scores_gemma":[0.002852418,0.0005811158,0.02365285,0.0003527705,0.00001881288,0.0004330521,0.001939524,0.817648,0.0005789077,0.002616305,0.1478578,0.001468473],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04255699,0.0004215215,0.9408048,0.0001380688,0.002084089,0.0002499574,0.000001968148,0.001473784,0.01226887],"genre_scores_gemma":[0.8553797,0.000001524498,0.1415245,0.0002219095,0.0002651011,0.00003663723,0.00000138809,0.00001261952,0.002556588],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8539091,"threshold_uncertainty_score":0.7970972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03668064642877483,"score_gpt":0.2519114779276128,"score_spread":0.2152308314988379,"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."}}