{"id":"W2792728919","doi":"10.1109/tnse.2018.2816951","title":"Mitigating Bottlenecks in Wide Area Data Analytics via Machine Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Huawei Technologies","keywords":"Bottleneck; Computer science; Scheduling (production processes); Locality; Petabyte; Distributed database; Distributed computing; SPARK (programming language); Exponential growth; Execution time; Analytics; Database; Data mining; Big data; Mathematical optimization; Embedded system","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":[0.004578817,0.00169193,0.001676823,0.001899057,0.001133049,0.001846248,0.002643005,0.001039669,0.0009431959],"category_scores_gemma":[0.01428587,0.0007524234,0.0006312486,0.002019993,0.001266247,0.004756206,0.002111631,0.002291056,0.0005075558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001393107,"about_ca_system_score_gemma":0.003483472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009600896,"about_ca_topic_score_gemma":0.008981621,"domain_scores_codex":[0.9975631,0.000792812,0.0001572881,0.0006271817,0.0005284531,0.0003310424],"domain_scores_gemma":[0.9915878,0.004772609,0.000838074,0.0009424165,0.001491573,0.0003675595],"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":[0.000695751,0.0008748221,0.01292113,0.0003122468,0.0002073411,0.0001324844,0.0002635332,0.6796325,0.008675323,0.004522122,0.009843971,0.2819187],"study_design_scores_gemma":[0.00001160685,0.00004425049,0.0004592424,0.000005568889,0.00001133196,0.000009032883,0.00003335987,0.9936236,0.001492345,0.003743283,0.0005587119,0.000007765534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1485211,0.003538145,0.8283471,0.002450182,0.0002119921,0.0002303935,0.0004354942,0.01366724,0.002598285],"genre_scores_gemma":[0.800414,0.000971663,0.1949785,0.0005452991,0.0002114172,0.0001767628,0.0008607763,0.0002694278,0.001571962],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009600896,"threshold_uncertainty_score":0.0242154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02029286560122316,"score_gpt":0.2215525736593145,"score_spread":0.2012597080580913,"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."}}