{"id":"W2065753274","doi":"10.1089/big.2013.1509","title":"Benchmarking Big Data Systems and the BigData Top100 List","year":2013,"lang":"en","type":"article","venue":"Big Data","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Benchmarking; Computer science; Data science; Benchmark (surveying); Comparability; Database transaction; Data mining; Database; Business; Marketing","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":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001513223,0.0001618399,0.0001974352,0.00006905323,0.0003356878,0.001475192,0.009510314,0.00004067376,0.000004853744],"category_scores_gemma":[0.0001336633,0.00009979089,0.00001639892,0.0003217164,0.0001424227,0.0001609463,0.02457158,0.0001511314,0.00007838614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001161312,"about_ca_system_score_gemma":0.00003245359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004226387,"about_ca_topic_score_gemma":0.00008623705,"domain_scores_codex":[0.9979465,0.0001685601,0.0002816362,0.0009220168,0.0003602325,0.0003210643],"domain_scores_gemma":[0.990815,0.0002815915,0.0001266423,0.00865311,0.00003272888,0.00009091321],"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":[0.000002925094,0.00003058045,0.000311061,0.00005498638,0.00005742482,0.00000946596,0.0002108656,0.00007978592,0.00001084389,0.006378716,0.1469235,0.8459299],"study_design_scores_gemma":[0.0003578523,0.000009861133,0.001222226,0.00006047591,0.00001525962,0.00001771441,0.00006699439,0.6519361,7.883644e-7,0.0001226811,0.3460527,0.00013733],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07738862,0.02024911,0.7994727,0.04038023,0.02630787,0.00410246,0.001264083,0.00142114,0.02941376],"genre_scores_gemma":[0.9893894,0.0001615003,0.003900659,0.0009812837,0.003275377,0.00002053731,0.0006060459,0.00002049032,0.001644733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9120008,"threshold_uncertainty_score":0.9995614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1267692910704791,"score_gpt":0.2606979585164022,"score_spread":0.1339286674459231,"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."}}