{"id":"W2958385005","doi":"10.1109/tse.2019.2927908","title":"Methodological Principles for Reproducible Performance Evaluation in Cloud Computing","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Electronic Components and Systems for European Leadership; Deutsche Forschungsgemeinschaft; Stiftelsen för Strategisk Forskning; Knowledge Foundation; Oracle; National Science Foundation","keywords":"Cloud computing; Computer science; Data science; Benchmark (surveying); Set (abstract data type); Systematic review; Open research; Domain (mathematical analysis); Field (mathematics); World Wide Web; MEDLINE","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7030904,0.004085388,0.005108708,0.01127684,0.006187883,0.01627765,0.009943871,0.009710663,0.004275299],"category_scores_gemma":[0.8078597,0.002904835,0.007794969,0.01138442,0.02152878,0.01340261,0.01290246,0.01244719,0.002942758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008415102,"about_ca_system_score_gemma":0.03360966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003074705,"about_ca_topic_score_gemma":0.002372669,"domain_scores_codex":[0.1926548,0.6657112,0.06781175,0.01844428,0.05321197,0.002165926],"domain_scores_gemma":[0.1334994,0.5693154,0.06215487,0.1553617,0.07763869,0.002029899],"domain_codex":"methods","domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002339442,0.001247925,0.01630017,0.04670658,0.005118477,0.0005655116,0.02113101,0.01157537,0.005476195,0.5790975,0.01941468,0.2910271],"study_design_scores_gemma":[0.003133638,0.00392736,0.01253862,0.04735649,0.003480658,0.0006072983,0.007540326,0.01575399,0.01726339,0.7236571,0.1639336,0.0008074436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004031004,0.007672615,0.9380499,0.01155971,0.002305764,0.02683922,0.001010613,0.0005012344,0.0080299],"genre_scores_gemma":[0.06762575,0.002877395,0.8318626,0.005546292,0.00118432,0.08903112,0.0004950855,0.0003363969,0.00104095],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2969096,"threshold_uncertainty_score":0.3661424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08977160147076024,"score_gpt":0.2994208042629967,"score_spread":0.2096492027922364,"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."}}