{"id":"W4412446467","doi":"10.1109/noms57970.2025.11073580","title":"Performance Observations from Split Federated Learning on Heterogeneous Devices & Networks","year":2025,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Royal University","funders":"","keywords":"Computer science; Computer network; Distributed computing","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":[0.003683829,0.0007839088,0.0009298358,0.0005851795,0.0009418929,0.001019249,0.001236647,0.0008850351,0.001391664],"category_scores_gemma":[0.008668398,0.0002349386,0.0003415361,0.0006673644,0.001169565,0.00224032,0.001752765,0.001057218,0.0003240059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001588345,"about_ca_system_score_gemma":0.0009430561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007350651,"about_ca_topic_score_gemma":0.005575009,"domain_scores_codex":[0.9984257,0.0004548697,0.00008488102,0.0003194882,0.0002442151,0.0004708406],"domain_scores_gemma":[0.9960829,0.001823409,0.0002120891,0.0009708641,0.0005626829,0.0003479566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001671802,0.0005351911,0.009304957,0.0001226628,0.0001067966,0.0001729869,0.0001346044,0.8967994,0.003386716,0.003820985,0.006705046,0.07723875],"study_design_scores_gemma":[0.00004322805,0.0002546279,0.00163208,0.000017032,0.00001240797,0.00007405014,0.0001158619,0.9900901,0.004264953,0.003005227,0.0004771432,0.00001323179],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9412315,0.0007790783,0.04708844,0.000918148,0.0001659621,0.00008798485,0.0004221594,0.002776224,0.006530578],"genre_scores_gemma":[0.9942538,0.00006423083,0.004747691,0.00008469838,0.000006079985,0.00001812009,0.0002927764,0.00002311329,0.0005095481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007350651,"threshold_uncertainty_score":0.0194822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04610095862056498,"score_gpt":0.2731272546033113,"score_spread":0.2270262959827463,"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."}}