{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001065776,0.0001310972,0.0001232473,0.0002336511,0.0004567744,0.0001940308,0.0009118265,0.00003252217,0.00000268547],"category_scores_gemma":[0.00002604759,0.0001261526,0.00001844623,0.001659456,0.0001238069,0.0001485436,0.00004783591,0.000300717,0.000005118722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005412544,"about_ca_system_score_gemma":0.00003671749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004981036,"about_ca_topic_score_gemma":0.00004574216,"domain_scores_codex":[0.998528,0.00001627634,0.0001882144,0.000495359,0.0003265169,0.0004456489],"domain_scores_gemma":[0.9991633,0.000123777,0.00003653745,0.0005247117,0.00004468402,0.0001069632],"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":[0.000001138375,0.00001258136,0.0002497099,0.000006246103,0.000005626951,0.000005038474,0.000196541,0.9584479,0.0002570681,0.00005632332,0.0000263272,0.04073552],"study_design_scores_gemma":[0.0001101388,0.00005343021,0.0005845701,0.00009378907,0.000005104058,0.000008976924,0.00001617118,0.9976764,0.0003342823,0.00002718139,0.0009408392,0.0001490749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09026311,0.00006425672,0.9085119,0.0001875841,0.0004752419,0.00005983529,5.155334e-7,0.0001514961,0.0002860206],"genre_scores_gemma":[0.9805461,0.00001679535,0.01916554,0.0001194168,0.00008819504,0.000002481042,3.294944e-7,0.00000783251,0.00005329006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.890283,"threshold_uncertainty_score":0.5144355,"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."}}