{"id":"W4407366508","doi":"10.36227/techrxiv.173931080.06536297/v1","title":"Enhancing Generative AI Reliability via Agentic AI in 6G-Enabled Edge Computing","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Modular Robots and Swarm Intelligence","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Generative grammar; Reliability (semiconductor); Enhanced Data Rates for GSM Evolution; Computer science; Artificial intelligence; Generative model; Machine learning; Power (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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006195997,0.0004511275,0.0006454074,0.0002338018,0.00007799835,0.0001307584,0.0004369103,0.0003920962,0.000253145],"category_scores_gemma":[0.00009353623,0.0004517451,0.0001713258,0.0002685473,0.00003471935,0.00008361177,0.0006444482,0.001460786,0.00005188696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004123268,"about_ca_system_score_gemma":0.0001202221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006307101,"about_ca_topic_score_gemma":0.0006131377,"domain_scores_codex":[0.9976379,0.000114837,0.0008241992,0.0007182986,0.0002096371,0.0004951377],"domain_scores_gemma":[0.9988399,0.0001066375,0.00006007226,0.0007593144,0.0001443896,0.00008975057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003322841,0.00003763196,0.0003345477,0.001000244,0.00005789151,0.00001627338,0.001080263,0.9881577,0.002616965,0.0003017866,0.0006954633,0.005697909],"study_design_scores_gemma":[0.0001008803,0.000008730104,0.0004987179,0.0004816765,0.00002275063,0.000001350026,0.00004719771,0.9304122,0.0648554,0.002699998,0.0003886069,0.0004825197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06199104,0.0004131941,0.9278373,0.0001712575,0.002018685,0.0006172174,0.000006697114,0.0003934594,0.006551228],"genre_scores_gemma":[0.982472,0.00009299289,0.01519489,0.0005293402,0.0002012675,0.00004104273,0.00003932375,0.00003904425,0.001390096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.920481,"threshold_uncertainty_score":0.9997934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01391521522088513,"score_gpt":0.264905978970491,"score_spread":0.2509907637496058,"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."}}