{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002662889,0.0001821179,0.0001777958,0.00005482947,0.0005270461,0.0007151173,0.000419172,0.00004132338,0.000002520648],"category_scores_gemma":[0.0004612386,0.0001740035,0.00001332002,0.0003715503,0.00007929531,0.0005256501,0.001013586,0.000238025,0.000008766805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001150846,"about_ca_system_score_gemma":0.00003488227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572964,"about_ca_topic_score_gemma":6.502243e-7,"domain_scores_codex":[0.9983183,0.0001315957,0.0002535623,0.000798363,0.0002580312,0.0002401106],"domain_scores_gemma":[0.9990231,0.0002690004,0.0001668795,0.0002079432,0.00008339594,0.0002497055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001432272,0.0001209675,0.00105409,0.0002017718,0.00003602809,0.00005475313,0.06486453,0.02848702,0.0001136468,0.00325233,0.001757737,0.8999139],"study_design_scores_gemma":[0.0005210044,0.0003326724,0.001451747,0.0001033,0.00001557439,0.0000286463,0.005698121,0.9629698,0.00001603421,0.00006326706,0.02852528,0.0002745125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2329146,0.001185853,0.7492255,0.01549104,0.0001556418,0.0002776212,0.00000546881,0.0002009182,0.0005433155],"genre_scores_gemma":[0.9801219,0.00005355211,0.01671289,0.002980695,0.00006746671,0.00001343067,0.00002317343,0.000007302528,0.0000195853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9344828,"threshold_uncertainty_score":0.7095658,"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."}}