{"id":"W4406970892","doi":"10.2139/ssrn.5104822","title":"A Two-Sided Client-Server Matching Mechanism for Resilient Federated Learning","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Matching (statistics); Client–server model; Mechanism (biology); Computer network; Server; Mathematics; Physics","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":[0.009517275,0.0007430129,0.002872915,0.001761669,0.002646728,0.004141295,0.008336231,0.004927401,0.007388152],"category_scores_gemma":[0.0168887,0.0009845368,0.001529907,0.00283272,0.002372638,0.009185978,0.01051184,0.003896103,0.002718462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002237965,"about_ca_system_score_gemma":0.003817264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001547075,"about_ca_topic_score_gemma":0.001242971,"domain_scores_codex":[0.9897057,0.002836263,0.0009333932,0.001807657,0.003056054,0.001660878],"domain_scores_gemma":[0.9790621,0.003959085,0.001025851,0.01326505,0.001727439,0.0009605524],"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":[0.005375449,0.001695625,0.003140758,0.0003335924,0.0004168852,0.0005386279,0.0006253898,0.1692065,0.02895948,0.2813755,0.02206684,0.4862654],"study_design_scores_gemma":[0.0001743723,0.0002503572,0.0003112865,0.00002662365,0.00006891675,0.000344784,0.00007881266,0.8457479,0.01721905,0.1314756,0.004210367,0.00009194839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02517657,0.0001730258,0.9668701,0.0005344403,0.0001371471,0.0002261225,0.0002141142,0.004499823,0.002168522],"genre_scores_gemma":[0.6920856,0.0001145697,0.2986878,0.000402336,0.0001236986,0.0002801151,0.0004658079,0.0002357191,0.007604314],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009517275,"threshold_uncertainty_score":0.05033273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01991017550840816,"score_gpt":0.292032968012812,"score_spread":0.2721227925044039,"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."}}