{"id":"W2016901333","doi":"10.1145/2479440.2482677","title":"Issues in big data testing and benchmarking","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Institute of Innovation and Technology; University of Toronto; Deutsche Forschungsgemeinschaft; International Business Machines Corporation","keywords":"Benchmarking; Computer science; Big data; Scalability; Data science; Relational database; Data modeling; Data management; Database; Massively parallel; Volume (thermodynamics); Data mining; Parallel computing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003194124,0.00004695758,0.00009509349,0.0001185312,0.00004558514,0.0005087979,0.0007695333,0.00001507815,0.0006588392],"category_scores_gemma":[0.004234131,0.00003154753,0.000004367981,0.0003762416,0.00003632893,0.0008166657,0.001488008,0.00003976208,0.0003838026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000352825,"about_ca_system_score_gemma":0.000006883172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005389053,"about_ca_topic_score_gemma":0.001303761,"domain_scores_codex":[0.9988028,0.00007428546,0.0002756779,0.0003498731,0.0003736639,0.0001236881],"domain_scores_gemma":[0.9978954,0.001170344,0.00004782279,0.0008078864,0.00003985065,0.00003874981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[3.528153e-7,0.00001111517,0.03166856,0.000002310511,0.000001238867,0.000001545509,0.00009276077,0.000001867437,0.00003148697,0.00147686,0.07933876,0.8873731],"study_design_scores_gemma":[0.0002582163,0.00003602059,0.4342675,0.00003406349,0.000003501518,0.000002349289,0.003857486,0.03757051,0.00003237227,0.1165404,0.4071856,0.0002119471],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6598023,0.0005224365,0.01577477,0.0216204,0.00101154,0.0007831951,0.00004680978,0.0001267301,0.3003118],"genre_scores_gemma":[0.9498727,0.00003197428,0.04119305,0.001489803,0.0001635996,0.000006833458,0.00001722642,0.000003885553,0.007220962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8871612,"threshold_uncertainty_score":0.8146672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6107454406852676,"score_gpt":0.4649125596602122,"score_spread":0.1458328810250554,"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."}}