{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009865284,0.0007058097,0.0005207959,0.0006973689,0.0005235865,0.001995196,0.001364553,0.001557379,0.01866216],"category_scores_gemma":[0.0020274,0.000448747,0.0006698495,0.0003903124,0.0005960916,0.001985982,0.002235331,0.001239197,0.006161366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003824955,"about_ca_system_score_gemma":0.0006578994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000784358,"about_ca_topic_score_gemma":0.001621774,"domain_scores_codex":[0.9996239,0.0001318246,0.00002498881,0.00007453345,0.0001231372,0.00002165036],"domain_scores_gemma":[0.999378,0.0003606467,0.00003649196,0.00007780497,0.00006944891,0.00007760319],"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":[0.001185314,0.0003022326,0.001646663,0.001135518,0.0002102059,0.00159114,0.00119748,0.02110287,0.04720533,0.1023551,0.218365,0.6037032],"study_design_scores_gemma":[0.0001880648,0.0002288622,0.001293294,0.0002174734,0.0001830202,0.003013517,0.0003483209,0.332291,0.0322023,0.1446568,0.4852316,0.0001456874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006191688,0.000851273,0.9383856,0.001394703,0.0003608744,0.0002108643,0.001499193,0.02489686,0.02620895],"genre_scores_gemma":[0.09836306,0.0009553921,0.8623803,0.0009924653,0.0002990591,0.0003905642,0.002454195,0.002084186,0.03208066],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01866216,"threshold_uncertainty_score":0.06243116,"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."}}