{"id":"W4311079977","doi":"10.1145/3570611","title":"Malcolm: Multi-agent Learning for Cooperative Load Management at Rack Scale","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Scalability; Server; Load balancing (electrical power); Distributed computing; Latency (audio); Scheduling (production processes); Nash equilibrium; Price of anarchy; Load management; Throughput; Mathematical optimization; Computer network; Operating system; Engineering","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":[0.001092094,0.00101801,0.0009542906,0.00048042,0.0008206145,0.0009106034,0.002301717,0.001380616,0.002783105],"category_scores_gemma":[0.003043395,0.0003703508,0.0004218449,0.0004534923,0.0009535459,0.001426676,0.001971938,0.001530789,0.0005675518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001105437,"about_ca_system_score_gemma":0.001365762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005322833,"about_ca_topic_score_gemma":0.006711333,"domain_scores_codex":[0.9994796,0.0001559567,0.00001622201,0.0001290341,0.0001232789,0.00009597061],"domain_scores_gemma":[0.9988185,0.000567047,0.0001466876,0.0001692922,0.0001655575,0.0001329323],"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":[0.0001305629,0.0001782737,0.000957038,0.00005801344,0.00005189966,0.00009117679,0.00005594688,0.9228342,0.00199271,0.007218664,0.003333515,0.06309804],"study_design_scores_gemma":[0.00001509086,0.00001819562,0.00004378448,0.000001317802,0.000001968567,0.000005320009,0.000005085667,0.9971734,0.0002646206,0.002016941,0.0004518191,0.000002425742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04550326,0.0003814134,0.9455054,0.000800918,0.0001174068,0.0001674005,0.00008871837,0.002779507,0.004655995],"genre_scores_gemma":[0.7595623,0.0001804769,0.2334488,0.0004513148,0.00009035494,0.0003147793,0.000180008,0.0001620657,0.005609897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005322833,"threshold_uncertainty_score":0.0105837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03638996529677906,"score_gpt":0.2476713601500177,"score_spread":0.2112813948532386,"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."}}