{"id":"W3102626224","doi":"10.1007/s11042-023-15184-5","title":"FedSL: Federated split learning on distributed sequential data in recurrent neural networks","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Rehabilitation Institute; University Health Network","funders":"","keywords":"Computer science; Recurrent neural network; Raw data; Federated learning; Artificial neural network; Machine learning; Artificial intelligence; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003513914,0.0001436874,0.000148509,0.0001092674,0.0002663858,0.0003966023,0.007391471,0.0001054244,0.0000053656],"category_scores_gemma":[0.002604143,0.0001404738,0.00001705781,0.001120975,0.00007643844,0.0004360294,0.02545705,0.0004612079,0.00005327682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003938663,"about_ca_system_score_gemma":0.00002278867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003095143,"about_ca_topic_score_gemma":0.00002575691,"domain_scores_codex":[0.9984619,0.00006135627,0.0002504032,0.0006978546,0.0001738231,0.0003546594],"domain_scores_gemma":[0.995963,0.0003798674,0.00008173956,0.003470127,0.0000311569,0.00007412137],"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":[0.000006667004,0.00008340432,0.002504162,0.00001202491,0.00001228234,0.00001318084,0.00002599622,0.002433918,0.0001481771,0.001189081,0.03256412,0.961007],"study_design_scores_gemma":[0.000249809,0.0000199453,0.01049805,0.00001715197,0.000003026954,0.00000227981,0.00001522658,0.9753051,0.00004478763,0.002056961,0.0116393,0.0001483426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02896346,0.0002310518,0.9424251,0.02316565,0.0003370148,0.001205836,0.0008738099,0.002639103,0.0001589213],"genre_scores_gemma":[0.9489253,0.0004465489,0.04024686,0.000120224,0.0001856719,0.0006019683,0.009411522,0.00002528595,0.00003662818],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9728712,"threshold_uncertainty_score":0.997979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08524438029312226,"score_gpt":0.3237919710871843,"score_spread":0.238547590794062,"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."}}