{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002275861,0.0001536996,0.0002037571,0.0002252654,0.00009413321,0.00005527325,0.0003797885,0.00006522561,0.000007264222],"category_scores_gemma":[0.0001008297,0.0001490373,0.0000912738,0.0004292115,0.000007314476,0.00004785812,0.000009920716,0.0002253705,0.00001976209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355109,"about_ca_system_score_gemma":0.00002652778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004962248,"about_ca_topic_score_gemma":8.902796e-7,"domain_scores_codex":[0.9984806,0.00007136673,0.0002916612,0.0005739875,0.0002800031,0.0003023967],"domain_scores_gemma":[0.9987148,0.000559558,0.00005752099,0.0005644802,0.00006140577,0.00004223841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000680316,0.00003941885,0.0002149322,0.00005871033,0.00001156574,5.541682e-7,0.0002262923,0.9150657,0.0001066128,0.0001751629,0.000005726971,0.08408849],"study_design_scores_gemma":[0.0004586491,0.0001134994,0.002688666,0.0001185784,0.000007620431,0.0000047035,0.00001317058,0.9918884,0.003810075,0.00001585345,0.0006975029,0.0001832933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4146281,0.00002341922,0.5836865,0.00003866043,0.0009667381,0.0003623936,4.467314e-7,0.0002676773,0.00002599738],"genre_scores_gemma":[0.7764046,0.000002116761,0.2233159,0.00003372277,0.00006164775,0.00004009936,5.134095e-7,0.00001248821,0.0001288489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3617764,"threshold_uncertainty_score":0.6077564,"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."}}