{"id":"W4401806263","doi":"10.1109/iotm.001.2300274","title":"Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness","year":2024,"lang":"en","type":"article","venue":"IEEE Internet of Things Magazine","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Interpretability; Computer science; Robustness (evolution); Bridging (networking); Trustworthiness; Industrial Internet; Federated learning; Risk analysis (engineering); Computer security; Data science; Knowledge management; Distributed computing; Internet of Things; Artificial intelligence; Business","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":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002263109,0.0002584012,0.000404828,0.0003521962,0.00007467323,0.0007129589,0.008543837,0.000219339,0.00001416559],"category_scores_gemma":[0.01021744,0.0002028874,0.00007677972,0.0008938378,0.0002492027,0.0009842794,0.0194166,0.001581638,0.00001022324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00013009,"about_ca_system_score_gemma":0.0000820776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000291787,"about_ca_topic_score_gemma":0.00002764361,"domain_scores_codex":[0.9976134,0.0002310126,0.0006512828,0.0007495617,0.0003409668,0.0004137815],"domain_scores_gemma":[0.997008,0.000868813,0.0001963528,0.001799273,0.00007305176,0.00005445689],"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":[0.0001024415,0.00009394348,0.04132821,0.000475386,0.0002856365,0.0002095788,0.00353352,0.001735659,0.006812363,0.0009049692,0.04054398,0.9039743],"study_design_scores_gemma":[0.0003344627,0.0001010729,0.0009143587,0.0009347104,0.00001853896,0.00003335719,0.00005316396,0.9796954,0.01035873,0.005702845,0.001594682,0.0002586294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7008406,0.0005119304,0.2854642,0.01100847,0.0008850791,0.0002364528,0.000004629694,0.0007542457,0.0002944267],"genre_scores_gemma":[0.9913657,0.00002503164,0.008246392,0.00005918417,0.0001341833,0.00001223325,0.000005430163,0.0000227727,0.0001291002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9779598,"threshold_uncertainty_score":0.99812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04159522377933147,"score_gpt":0.276934217757444,"score_spread":0.2353389939781126,"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."}}