{"id":"W2606302229","doi":"10.1145/3030207.3030229","title":"Conducting Repeatable Experiments in Highly Variable Cloud Computing Environments","year":2017,"lang":"en","type":"article","venue":"","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cloud computing; Benchmark (surveying); Computer science; Variable (mathematics); Control (management); Distributed computing; Computer engineering; Operating system; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04819028,0.001149506,0.00148725,0.0006459437,0.001342502,0.001722452,0.003961021,0.001967486,0.001216163],"category_scores_gemma":[0.1516631,0.0008192015,0.001093416,0.0012188,0.002703652,0.00248459,0.001821572,0.002859907,0.0004098518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001567654,"about_ca_system_score_gemma":0.001806691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001728115,"about_ca_topic_score_gemma":0.001862098,"domain_scores_codex":[0.9523618,0.03081246,0.00267201,0.00594613,0.006531969,0.00167565],"domain_scores_gemma":[0.6922827,0.2195561,0.02476866,0.05183404,0.009621572,0.001936832],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.02999146,0.03590376,0.09195948,0.002769543,0.003418253,0.001319523,0.007140998,0.4089791,0.1728395,0.02049286,0.004577923,0.2206076],"study_design_scores_gemma":[0.005292844,0.09779065,0.08319562,0.0003830987,0.001514135,0.0007179484,0.00231274,0.531282,0.2020502,0.06506507,0.009564224,0.0008315772],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7720309,0.0001728549,0.2210863,0.0002234842,0.0001302921,0.003456341,0.0003357856,0.0007376889,0.001826292],"genre_scores_gemma":[0.8762766,0.00009096171,0.1174449,0.0003444484,0.00006004581,0.004957522,0.0002513028,0.0001385684,0.0004356597],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9518097,"threshold_uncertainty_score":0.2548576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04958635084348046,"score_gpt":0.2730522795999201,"score_spread":0.2234659287564397,"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."}}