{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.008713655,0.0009567355,0.00220394,0.000450781,0.0005628049,0.0008203926,0.01887922,0.0002864676,0.000004942132],"category_scores_gemma":[0.0003369547,0.0008525031,0.0004590183,0.00173411,0.00008575236,0.00005796845,0.03364382,0.0007106937,0.0002155408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002526442,"about_ca_system_score_gemma":0.000130506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009450457,"about_ca_topic_score_gemma":0.000002777575,"domain_scores_codex":[0.9909362,0.003247537,0.001398346,0.00249728,0.0008164645,0.001104126],"domain_scores_gemma":[0.9862868,0.001297209,0.001044733,0.01104563,0.00009264525,0.0002329556],"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":[1.958511e-7,0.0000672129,0.000005273828,0.005904925,0.0003614441,0.00007299351,0.00002173787,0.001643553,1.00125e-8,0.0007338016,0.003422581,0.9877663],"study_design_scores_gemma":[0.0001546453,0.00001900046,0.00003122205,0.006954567,0.000334941,0.00006690781,0.000004701441,0.2284476,4.481687e-8,0.0001273344,0.763057,0.0008020668],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.000008538816,0.4962381,0.5008382,0.0000383463,0.001353516,0.000507601,0.00003873969,0.0005735057,0.0004034431],"genre_scores_gemma":[0.0002457213,0.8109846,0.1849388,0.0001451403,0.001479803,0.00001227004,0.001383872,0.0002130259,0.0005968267],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9869642,"threshold_uncertainty_score":0.9993926,"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."}}