{"id":"W4401210868","doi":"10.1109/mnet.2024.3436670","title":"Toward Effective Retrieval Augmented Generative Services in 6G Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Network","topic":"Advanced Wireless Communication Technologies","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Windsor","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Generative grammar; Computer network; Information retrieval; Multimedia; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001532537,0.0001973102,0.0002146193,0.0001020634,0.00004797875,0.00006035055,0.0003275971,0.0001827017,0.000007725277],"category_scores_gemma":[0.000009069369,0.0001974578,0.00004266632,0.001180582,0.00005001446,0.0001868848,0.00005934983,0.0005654152,0.00003892408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001948892,"about_ca_system_score_gemma":0.00000876758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006537825,"about_ca_topic_score_gemma":0.00005657382,"domain_scores_codex":[0.9990361,0.00005878095,0.0002316273,0.0002238205,0.0001038657,0.0003457793],"domain_scores_gemma":[0.9992943,0.0002552077,0.0000221154,0.000365508,0.00002957144,0.00003330408],"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":[0.00001795927,0.00000576506,0.00009319525,0.00006542563,0.0000522398,0.00001956632,0.0002676611,0.9832088,0.0004084945,0.0003910659,0.002416637,0.01305323],"study_design_scores_gemma":[0.0002075033,0.00003893162,0.0007264023,0.0004544203,0.00001003048,0.000004528987,0.0001332665,0.9794375,0.005588314,0.003155982,0.009950866,0.0002922857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2552796,0.1166546,0.5862143,0.0005964246,0.01817276,0.00213817,0.00002289941,0.01313483,0.007786354],"genre_scores_gemma":[0.9959877,0.001484798,0.001403588,0.00005311532,0.0008612585,0.000100863,0.00001787539,0.00005313892,0.000037672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7407081,"threshold_uncertainty_score":0.8052096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.010964504022135,"score_gpt":0.2437281632927417,"score_spread":0.2327636592706067,"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."}}