{"id":"W4382199008","doi":"10.1145/3606376.3593550","title":"Malcolm: Multi-agent Learning for Cooperative Load Management at Rack Scale","year":2023,"lang":"en","type":"article","venue":"ACM SIGMETRICS Performance Evaluation Review","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Server; Scalability; Distributed computing; Load balancing (electrical power); Latency (audio); Nash equilibrium; Scheduling (production processes); Load management; Mathematical optimization; Computer network; Operating system; Engineering","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":[0.001482427,0.0009503917,0.0009401843,0.0005175319,0.0007681447,0.001057641,0.002412549,0.001378136,0.00272089],"category_scores_gemma":[0.003698795,0.0003763893,0.0004715722,0.0005376147,0.00099219,0.001521391,0.002189389,0.001885966,0.0005808228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269094,"about_ca_system_score_gemma":0.001341569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005958125,"about_ca_topic_score_gemma":0.007327376,"domain_scores_codex":[0.9993635,0.0002435296,0.0000220537,0.0001193354,0.0001627539,0.00008888503],"domain_scores_gemma":[0.9986997,0.0007104955,0.0001393275,0.0001569635,0.0001896117,0.0001039605],"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":[0.00008844526,0.0001468164,0.0008334364,0.000105712,0.00006970409,0.00008642577,0.00004931611,0.885496,0.001116772,0.0138601,0.004628289,0.09351896],"study_design_scores_gemma":[0.00001474006,0.00001850716,0.00005823267,0.000003556212,0.000002723225,0.000007802122,0.000005284423,0.9948751,0.0002361768,0.003703019,0.001071937,0.00000279993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01963209,0.0008378624,0.9700091,0.001097952,0.0001459437,0.00016939,0.00009717163,0.002388619,0.005621965],"genre_scores_gemma":[0.6444885,0.0006569074,0.3453119,0.0006188418,0.0001563219,0.0005096191,0.0002386342,0.0001910591,0.007828264],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005958125,"threshold_uncertainty_score":0.0118469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0948412583542362,"score_gpt":0.3518979146421082,"score_spread":0.2570566562878721,"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."}}