{"id":"W4415593708","doi":"10.1109/mwc.2025.3600848","title":"Retrieval-Augmented Generation for GenAI-Enabled Semantic Communications","year":2025,"lang":"","type":"article","venue":"IEEE Wireless Communications","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Leverage (statistics); Domain (mathematical analysis); Generative grammar; Semantic technology; Adaptability; Face (sociological concept); Information and Communications Technology","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","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001616739,0.0006415287,0.0009120482,0.0006776128,0.004144983,0.001068297,0.01421377,0.0005060596,0.00001970815],"category_scores_gemma":[0.0005454021,0.0007143832,0.0004744655,0.002662037,0.001380897,0.0009253636,0.003369326,0.0008311049,0.0001109032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004434042,"about_ca_system_score_gemma":0.001259646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002735633,"about_ca_topic_score_gemma":0.001132438,"domain_scores_codex":[0.994528,0.001217747,0.001751844,0.001073,0.0004591602,0.0009702328],"domain_scores_gemma":[0.9766603,0.002381795,0.0007335642,0.01852842,0.001501403,0.000194568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001238461,0.003023425,0.001030097,0.000754647,0.001301936,0.000003390413,0.004133899,0.0003864846,0.07727492,0.7779638,0.03423778,0.09976576],"study_design_scores_gemma":[0.001823196,0.0001321914,0.000919032,0.0005858734,0.0004367895,0.000009670654,0.0004803674,0.9427139,0.01492892,0.005181759,0.03206015,0.0007281521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01344914,0.01910536,0.901234,0.05140442,0.003342812,0.003439323,0.000127473,0.0006299306,0.007267592],"genre_scores_gemma":[0.9132053,0.01706121,0.06302993,0.001611112,0.0001551934,0.0006281379,0.0002811362,0.00005048901,0.00397752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9423274,"threshold_uncertainty_score":0.9999687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08406372839126881,"score_gpt":0.3388700910127004,"score_spread":0.2548063626214316,"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."}}