{"id":"W206771271","doi":"10.1007/978-3-642-53974-9_3","title":"Big Data Generation","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Computer science; Benchmarking; Pipeline (software); Benchmark (surveying); Generator (circuit theory); Focus (optics); Database; Pipeline transport; Data science; Data mining; Operating system; Engineering; Power (physics)","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001183763,0.0005281704,0.0005152723,0.0005506674,0.0002875317,0.001478947,0.008934531,0.0003334312,0.00002504642],"category_scores_gemma":[0.00008755794,0.0004747279,0.00008025565,0.0005680807,0.000333016,0.0008658963,0.003811511,0.0006528713,0.000413468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001860608,"about_ca_system_score_gemma":0.0006558343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000678456,"about_ca_topic_score_gemma":0.00006260939,"domain_scores_codex":[0.9953287,0.0000526577,0.0006284015,0.002256045,0.001059466,0.0006746762],"domain_scores_gemma":[0.9946806,0.0002404005,0.0003495863,0.00426007,0.0002729623,0.0001963741],"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":[6.731942e-7,0.00001857583,0.00001447916,0.00002527136,0.00001189257,0.00004093097,0.0001983312,0.0281563,0.0001062093,0.01388312,0.001584066,0.9559602],"study_design_scores_gemma":[0.0001514158,0.00006676489,0.00003008851,0.0001925973,0.000005048587,0.00007282347,3.128435e-8,0.9469733,0.0001080382,0.0243028,0.02750332,0.0005937432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003081223,0.0005987956,0.984473,0.0006294004,0.007031303,0.0003928293,0.00002259908,0.000239974,0.006581252],"genre_scores_gemma":[0.3960764,0.00008014057,0.5887445,0.002522553,0.008848283,0.00001666577,0.0003755022,0.00008547673,0.003250404],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9553664,"threshold_uncertainty_score":0.9997705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07375689493781114,"score_gpt":0.2628777619710696,"score_spread":0.1891208670332585,"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."}}