{"id":"W4402619319","doi":"10.1007/978-3-031-70242-6_32","title":"Intelligent Conversational Agent for Medical Information","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Pfizer (Canada)","funders":"","keywords":"Computer science; Intelligent agent; Human–computer interaction; Artificial intelligence; World Wide Web","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":[0.0006900606,0.0004990372,0.0004465554,0.0004720188,0.0004966335,0.001277619,0.0008609092,0.001020024,0.01073615],"category_scores_gemma":[0.001444593,0.0002251195,0.0004363691,0.0003491231,0.0002271256,0.001187535,0.001072621,0.0009358801,0.004544776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003694769,"about_ca_system_score_gemma":0.0004929702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006446,"about_ca_topic_score_gemma":0.0009236222,"domain_scores_codex":[0.999712,0.0001268214,0.00001630389,0.00004167046,0.00007857379,0.00002452337],"domain_scores_gemma":[0.9996563,0.0002128846,0.00001592019,0.00003018439,0.00005051995,0.00003412192],"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":[0.0004216989,0.000354426,0.0008553214,0.0007834445,0.000117361,0.0008616312,0.001321359,0.01997342,0.02814552,0.1203069,0.1270069,0.6998519],"study_design_scores_gemma":[0.00007388566,0.0002138681,0.0008262588,0.0002251681,0.0001726611,0.001570995,0.0004398028,0.5103592,0.02025965,0.09442575,0.3713586,0.00007420449],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01054273,0.00698416,0.9041908,0.002574334,0.0007787627,0.0002023533,0.0006782155,0.005545171,0.06850342],"genre_scores_gemma":[0.2410439,0.004120236,0.6509607,0.0009355831,0.0005894771,0.0004090729,0.002019092,0.00054331,0.09937871],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01073615,"threshold_uncertainty_score":0.03591597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02413304293007301,"score_gpt":0.2646927494440479,"score_spread":0.2405597065139749,"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."}}