{"id":"W4402350363","doi":"10.1109/ojcoms.2024.3456549","title":"LLM-Based Edge Intelligence: A Comprehensive Survey on Architectures, Applications, Security and Trustworthiness","year":2024,"lang":"en","type":"article","venue":"IEEE Open Journal of the Communications Society","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Trustworthiness; Computer science; Enhanced Data Rates for GSM Evolution; Computer security; Data science; Artificial intelligence","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":[],"category_scores_codex":[0.001628059,0.000148374,0.000225667,0.00005926268,0.0007391617,0.0007623083,0.0063985,0.00006584633,0.000001182347],"category_scores_gemma":[0.00005013443,0.0001029142,0.0002105104,0.0008151798,0.0002540912,0.000196247,0.001467299,0.0008842811,0.000006473296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008731812,"about_ca_system_score_gemma":0.0003594505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009155115,"about_ca_topic_score_gemma":0.0000199524,"domain_scores_codex":[0.99836,0.000588409,0.0004276978,0.0002030252,0.0002503652,0.000170445],"domain_scores_gemma":[0.9961252,0.001513197,0.0002583525,0.001677239,0.0003417079,0.00008429758],"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":[0.0001278726,0.002150547,0.006698177,0.0004857052,0.001274411,0.00001397151,0.04935525,0.01480712,0.0007917164,0.02577172,0.3547764,0.5437471],"study_design_scores_gemma":[0.0008508356,0.0003211282,0.0253922,0.001436317,0.0001194615,0.0002795025,0.0004395116,0.6101114,0.001894087,0.05723445,0.3010644,0.0008566981],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05766835,0.01488442,0.8755865,0.04013034,0.008255536,0.001797198,0.00002090207,0.0001563604,0.001500399],"genre_scores_gemma":[0.9588152,0.0003998531,0.03904345,0.00127082,0.0003725892,0.000020814,0.000004518613,0.00001703184,0.00005571826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9011468,"threshold_uncertainty_score":0.9989774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06906899056876745,"score_gpt":0.3487732989765265,"score_spread":0.2797043084077591,"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."}}