{"id":"W2083854694","doi":"10.1145/2503009","title":"Distributed data management using MapReduce","year":2014,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; USable; Implementation; Interface (matter); Cluster analysis; Distributed database; Analytics; Big data; Database; Data management; Computation; Distributed computing; Data science; Data mining; Software engineering; World Wide Web; Parallel computing; Artificial intelligence; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001357439,0.0006842228,0.0009828686,0.002487056,0.0007054359,0.002332674,0.003187863,0.0007768373,0.002677029],"category_scores_gemma":[0.001989893,0.0004136474,0.0008106704,0.005938223,0.0005661813,0.003803797,0.002273357,0.001523572,0.003171247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009016087,"about_ca_system_score_gemma":0.002150485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001985881,"about_ca_topic_score_gemma":0.001546384,"domain_scores_codex":[0.9984674,0.0001890842,0.0001079337,0.0002362494,0.0008799144,0.0001193513],"domain_scores_gemma":[0.9990605,0.0002510835,0.00007467673,0.0001857783,0.0003597538,0.00006818784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004655625,0.0001298215,0.0005581231,0.003951783,0.0001403659,0.0002053159,0.0001904052,0.006655778,0.004123963,0.04889261,0.08467063,0.8504346],"study_design_scores_gemma":[0.00003101767,0.00007272061,0.000776931,0.0006207619,0.00005767219,0.001012454,0.0001931424,0.0154535,0.0039027,0.0448751,0.9329413,0.00006258544],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.005503327,0.3766645,0.5398743,0.005979334,0.002418052,0.0008886681,0.0009511641,0.005550843,0.06216987],"genre_scores_gemma":[0.1222819,0.5402882,0.3029024,0.003772364,0.003927086,0.0009500381,0.004699127,0.0005886653,0.02059031],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.003187863,"threshold_uncertainty_score":0.008955538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1412193676821104,"score_gpt":0.3638292794721453,"score_spread":0.2226099117900348,"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."}}