{"id":"W2500329317","doi":"10.1007/978-3-642-53974-9","title":"Specifying Big Data Benchmarks","year":2013,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Computer science; Data science; Data mining","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":["open_science"],"category_scores_codex":[0.003103808,0.0003927769,0.0005530333,0.001086699,0.0003847372,0.001670222,0.01920922,0.0004687006,0.0003508261],"category_scores_gemma":[0.002327959,0.0002833227,0.00007523939,0.002669248,0.001567051,0.0007833193,0.01002362,0.001092454,0.0006431459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002206646,"about_ca_system_score_gemma":0.0009847508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005505683,"about_ca_topic_score_gemma":0.0002396814,"domain_scores_codex":[0.9934953,0.00004632563,0.0008525438,0.002663703,0.002268456,0.0006737152],"domain_scores_gemma":[0.989029,0.0021923,0.0004649986,0.00783459,0.000333923,0.0001452003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[6.629687e-7,0.00001466968,0.00005690151,0.000003887534,0.00000245134,0.000006849042,0.00003940011,0.0006094511,0.00002501309,0.0006576912,0.0470916,0.9514914],"study_design_scores_gemma":[0.000106227,0.00003853083,0.0003886461,0.0001169378,0.00000626084,0.00002580545,0.000001580109,0.09403338,0.000177496,0.4794177,0.4251724,0.0005150259],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008709445,0.0005418055,0.9837289,0.002854422,0.002140265,0.0004424792,0.0001710282,0.0001080951,0.009925847],"genre_scores_gemma":[0.07925711,0.0005026052,0.8969992,0.00505194,0.006653193,0.00008956078,0.001163227,0.0001056796,0.01017743],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9509764,"threshold_uncertainty_score":0.9999619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2982924050768856,"score_gpt":0.3712392572861838,"score_spread":0.07294685220929825,"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."}}