{"id":"W4414417426","doi":"10.1007/978-3-032-06004-4_11","title":"AURA: A Multi-modal Medical Agent for Understanding, Reasoning and Annotation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Interpretability; Toolbox; Modular design; Segmentation; Set (abstract data type); Medical imaging; Relevance (law); Suite; Annotation","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"],"consensus_categories":[],"category_scores_codex":[0.001071002,0.0003360244,0.0003714952,0.0005538932,0.0003046082,0.0004191701,0.001535185,0.0003298051,0.00000514828],"category_scores_gemma":[0.0003763955,0.0003170727,0.00008090413,0.0002709714,0.0003504062,0.0003546269,0.0009736264,0.000500724,0.000001693907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000454906,"about_ca_system_score_gemma":0.0007700707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002242786,"about_ca_topic_score_gemma":0.000126934,"domain_scores_codex":[0.99692,0.00002416717,0.0004165256,0.001331443,0.000830655,0.0004771739],"domain_scores_gemma":[0.9982876,0.0006024354,0.00017163,0.0006521356,0.0001319742,0.0001541853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006278395,0.00001830574,0.00006376512,0.0001155193,0.0000152679,0.00004352817,0.001209755,0.008307735,0.00001778394,0.3049803,0.00004562728,0.6851761],"study_design_scores_gemma":[0.0003856142,0.00005729908,0.00002786877,0.0006346827,0.000006360936,0.00002676087,5.028058e-7,0.8779339,0.00004426606,0.1202151,0.0003839797,0.0002836901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003079576,0.0004341166,0.99518,0.001699917,0.001443668,0.0004552016,0.000003560989,0.0001170158,0.0006357261],"genre_scores_gemma":[0.0688475,0.00004772645,0.9286312,0.001743002,0.0002774979,0.00001793532,0.000004654646,0.00001795281,0.0004124672],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8696262,"threshold_uncertainty_score":0.9999281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04550989508030667,"score_gpt":0.2934982396036764,"score_spread":0.2479883445233698,"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."}}