{"id":"W7125515560","doi":"10.1109/icft66708.2025.11336532","title":"STAR-Net: Advancing Conversational AI through Semantic Correlation and Contextual Response Optimization","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Correlation; Semantics (computer science); Feature (linguistics); Context (archaeology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003343897,0.001243038,0.001458372,0.001057887,0.001154047,0.002322584,0.002829668,0.001483728,0.009661689],"category_scores_gemma":[0.01066506,0.0007418296,0.001460471,0.001105032,0.001186953,0.004219517,0.003925323,0.00385571,0.003731513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009861201,"about_ca_system_score_gemma":0.002206267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00670797,"about_ca_topic_score_gemma":0.01135585,"domain_scores_codex":[0.9966115,0.001835751,0.0001276941,0.0006524148,0.0005913504,0.0001812447],"domain_scores_gemma":[0.9946656,0.003964891,0.0001299599,0.0005647912,0.0004577957,0.0002169352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001440244,0.0007960261,0.001664895,0.0009027533,0.0004282816,0.0002358716,0.001408709,0.1952979,0.0165144,0.1483915,0.04646747,0.5864519],"study_design_scores_gemma":[0.0000382707,0.00004386247,0.00006742671,0.00001758307,0.00003897241,0.00002322869,0.0000767161,0.9275606,0.002641586,0.06294919,0.006526197,0.00001632035],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004656292,0.0002810931,0.9847021,0.0004308357,0.0001556237,0.00007395057,0.0002665184,0.006300677,0.003133037],"genre_scores_gemma":[0.2231613,0.0004432804,0.7636214,0.0006962694,0.0003386021,0.0003256,0.001549519,0.002047055,0.007816968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009661689,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01345631533480501,"score_gpt":0.2639869250660548,"score_spread":0.2505306097312498,"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."}}