{"id":"W4412405208","doi":"10.1109/otcon65728.2025.11070569","title":"AI-Associate: A Lightweight Architecture for Conversational Agents","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Architecture; Computer architecture; Human–computer interaction; Programming language; Art","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":[0.001267441,0.0006820158,0.0004151365,0.0005613032,0.001223236,0.001776317,0.002415093,0.001256966,0.006847762],"category_scores_gemma":[0.00269301,0.000551325,0.0004704361,0.0003321914,0.0009488532,0.003258592,0.003785484,0.002006167,0.002968872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006442515,"about_ca_system_score_gemma":0.001332517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002513758,"about_ca_topic_score_gemma":0.002910137,"domain_scores_codex":[0.9992894,0.0001978893,0.00005530512,0.0001305917,0.0002257935,0.0001010338],"domain_scores_gemma":[0.9990067,0.0002406624,0.00007095686,0.0002516079,0.0001853365,0.000244777],"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":[0.002306533,0.0008700875,0.005702819,0.001377604,0.0002916093,0.001335605,0.00723507,0.05491624,0.1447985,0.2755363,0.03623832,0.4693912],"study_design_scores_gemma":[0.00008969106,0.0004023924,0.001187273,0.0001142912,0.0001485377,0.0005549045,0.0007093405,0.7394453,0.03875003,0.07442852,0.1440258,0.0001439754],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01463041,0.0001569586,0.9632995,0.0002904396,0.000122126,0.0001822637,0.0000709993,0.01419962,0.007047824],"genre_scores_gemma":[0.4120101,0.0002720523,0.5608803,0.0004421684,0.0001302066,0.0006866506,0.0005714636,0.001251172,0.02375582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006847762,"threshold_uncertainty_score":0.02290809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01187602181140022,"score_gpt":0.2920805032408699,"score_spread":0.2802044814294697,"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."}}