{"id":"W2044936152","doi":"10.1145/2094114.2094118","title":"Parallel data processing with MapReduce","year":2012,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":555,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Abstraction; Data science; Big data; Volume (thermodynamics); Data processing; Simple (philosophy); Node (physics); Parallel processing; Database; Parallel computing; 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":[],"consensus_categories":[],"category_scores_codex":[0.000403816,0.0001483202,0.0001379464,0.00006136885,0.0001791368,0.0001648165,0.003304876,0.00003694976,0.000007931911],"category_scores_gemma":[0.00005153329,0.0001079984,0.00002202999,0.0003200393,0.00003425208,0.0001919256,0.002609532,0.0001400696,0.0000688943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002203139,"about_ca_system_score_gemma":0.00003473121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004018138,"about_ca_topic_score_gemma":0.000005416462,"domain_scores_codex":[0.9986069,0.0000469369,0.0001581619,0.0004552001,0.0002675683,0.0004651874],"domain_scores_gemma":[0.9972955,0.00006989136,0.00009860076,0.00237592,0.00003022723,0.0001298329],"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":[0.00001129884,0.0001446479,0.007321362,0.00003856555,0.00003129193,0.00000961901,0.0008456981,0.0005030078,0.00002980828,0.0009649448,0.009056501,0.9810433],"study_design_scores_gemma":[0.001355862,0.0003246156,0.01983501,0.0002980943,0.00007284473,0.0001536036,0.0003523018,0.5660803,0.0001982566,0.00217475,0.4078528,0.001301547],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2788881,0.0009860436,0.7055041,0.00408271,0.0008128721,0.0003006311,0.000001471734,0.0006852493,0.008738832],"genre_scores_gemma":[0.7494628,0.000003897678,0.2485778,0.0003107289,0.0003643327,0.000007493051,0.000003848704,0.0000139564,0.001255073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9797417,"threshold_uncertainty_score":0.6141337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05152052286016848,"score_gpt":0.2733963681575956,"score_spread":0.2218758452974271,"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."}}