{"id":"W2735413012","doi":"10.1109/icdcs.2017.131","title":"Optimizing Shuffle in Wide-Area Data Analytics","year":2017,"lang":"en","type":"article","venue":"","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; SPARK (programming language); Big data; Analytics; Distributed computing; Aggregate (composite); Data analysis; Raw data; Baseline (sea); Database; Computer network; Real-time computing; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002700723,0.001147713,0.000850494,0.0009177978,0.001540582,0.001453236,0.002045301,0.000533601,0.001146229],"category_scores_gemma":[0.005053672,0.000570347,0.0005066487,0.001332184,0.001039083,0.003369329,0.002066302,0.0008359812,0.000588163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001267086,"about_ca_system_score_gemma":0.003509267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006468296,"about_ca_topic_score_gemma":0.009847531,"domain_scores_codex":[0.9982542,0.00037813,0.000109375,0.0004049979,0.0004444488,0.0004088394],"domain_scores_gemma":[0.9970307,0.0009936935,0.0002825002,0.0008394025,0.0005092453,0.0003443686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002816424,0.001230338,0.02183912,0.0003717976,0.0001943434,0.0004752013,0.001067346,0.5939318,0.06081622,0.01362231,0.01257631,0.2910588],"study_design_scores_gemma":[0.0001075182,0.0003711047,0.002712856,0.00001221428,0.00003672826,0.0001027156,0.0003268652,0.9516436,0.0296726,0.01062376,0.004346226,0.00004374573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5031894,0.001105637,0.4780143,0.0006182376,0.0001739587,0.0003609451,0.0004654959,0.01146128,0.004610735],"genre_scores_gemma":[0.8764712,0.0002187448,0.119941,0.0001178238,0.0000444943,0.0001250249,0.0006452912,0.0003097999,0.002126565],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006468296,"threshold_uncertainty_score":0.01428294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0895041517372397,"score_gpt":0.2953768015755207,"score_spread":0.205872649838281,"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."}}