{"id":"W4409410640","doi":"10.1038/s44287-025-00169-3","title":"Enhancing generative AI reliability via agentic AI in 6G-enabled edge computing","year":2025,"lang":"en","type":"article","venue":"Nature Reviews Electrical Engineering","topic":"Modular Robots and Swarm Intelligence","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Generative grammar; Reliability (semiconductor); Artificial intelligence; Enhanced Data Rates for GSM Evolution; Computer science; Generative model; Machine learning; Cognitive science; Psychology; Power (physics); 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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007759082,0.0003916721,0.0007672165,0.0003432574,0.00006597617,0.00006339563,0.0003141798,0.0004095347,0.00002212487],"category_scores_gemma":[0.0006574312,0.0003610399,0.0001877738,0.001856655,0.00001251412,0.0001484577,0.00006121508,0.002335238,0.00002641919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004627597,"about_ca_system_score_gemma":0.00004021739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009879573,"about_ca_topic_score_gemma":0.00001186556,"domain_scores_codex":[0.9977704,0.0000838197,0.000832496,0.0004640355,0.0001923727,0.0006568619],"domain_scores_gemma":[0.9991999,0.0001706576,0.00004288081,0.0004004118,0.00007882466,0.0001073823],"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":[0.000009188716,0.00008731005,0.0002282495,0.002132487,0.00008507814,0.00004075544,0.0002151368,0.7410071,0.07996885,0.003055358,0.002140019,0.1710304],"study_design_scores_gemma":[0.0001591942,0.00001889571,0.0004300025,0.0005949595,0.00002844756,0.000006548268,0.000001275029,0.9301075,0.0341154,0.0001951387,0.03394561,0.000396996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007366147,0.07840742,0.9117537,0.0001657685,0.0008297444,0.000714044,6.802348e-7,0.0003292354,0.0004333225],"genre_scores_gemma":[0.9854782,0.003980802,0.009244556,0.0008524979,0.0002164403,0.00005932963,0.000009148558,0.00005564441,0.0001033332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9781121,"threshold_uncertainty_score":0.9999664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005535461921663012,"score_gpt":0.2577097568243971,"score_spread":0.2521742949027341,"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."}}