{"id":"W3027455131","doi":"10.1002/cpe.5823","title":"Mary, Hugo, and Hugo*: Learning to schedule distributed data‐parallel processing jobs on shared clusters","year":2020,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung","keywords":"Computer science; SPARK (programming language); Yarn; Scheduling (production processes); Distributed computing; Schedule; Resource (disambiguation); Throughput; Cluster (spacecraft); Computer cluster; Job scheduler; Operating system; Computer network; Wireless","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002047412,0.0005627281,0.0006582657,0.0002959156,0.0005090808,0.000548214,0.0008518156,0.0004232948,0.0008498163],"category_scores_gemma":[0.006176483,0.0002974762,0.0002615242,0.0003534674,0.0006509527,0.0008403643,0.0008060325,0.001074968,0.0001812798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009413851,"about_ca_system_score_gemma":0.001861779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01400061,"about_ca_topic_score_gemma":0.008372848,"domain_scores_codex":[0.9995387,0.0001662074,0.00001902362,0.00009484401,0.0001067862,0.00007442844],"domain_scores_gemma":[0.9969398,0.001783867,0.000177641,0.0003194926,0.0003818014,0.0003974254],"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":[0.0003439164,0.0002888404,0.004689401,0.00004710336,0.00004642791,0.00005364014,0.00009224634,0.9036264,0.004952979,0.002290379,0.003429558,0.08013909],"study_design_scores_gemma":[0.00002994057,0.0000499413,0.0002500804,0.000001389035,0.000005113812,0.00000513586,0.00001725499,0.9969348,0.001374902,0.001067065,0.0002601913,0.000004198432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5796608,0.000346277,0.4098642,0.002163728,0.0001833534,0.0001909249,0.00006639533,0.003606981,0.003917306],"genre_scores_gemma":[0.8938203,0.00008560917,0.1040097,0.0001646813,0.00003975368,0.00008680353,0.00008239842,0.000105447,0.001605264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01400061,"threshold_uncertainty_score":0.02783829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0516348108275705,"score_gpt":0.3270838313335077,"score_spread":0.2754490205059372,"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."}}