{"id":"W4406022307","doi":"10.1109/lra.2025.3535184","title":"From Decision to Action in Surgical Autonomy: Multi-Modal Large Language Models for Robot-Assisted Blood Suction","year":2025,"lang":"en","type":"preprint","venue":"IEEE Robotics and Automation Letters","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alberta Innovates; Canada Foundation for Innovation","keywords":"Robot; Artificial intelligence; Robotics; Autonomy; Computer science; Modal; Agency (philosophy); Automation; Human–computer interaction; Engineering; Political science; Sociology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003412434,0.0002330276,0.0004180056,0.0004096616,0.0001133452,0.00008481126,0.00008427069,0.0003811312,0.000009718192],"category_scores_gemma":[0.00009849297,0.0002424265,0.0001144941,0.0001936464,0.00001991441,0.0001301406,0.0000575445,0.000385055,0.00000528105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003768997,"about_ca_system_score_gemma":0.0003016566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001719047,"about_ca_topic_score_gemma":0.0004646278,"domain_scores_codex":[0.9982345,0.00006663783,0.0006704151,0.0005467137,0.0002006573,0.0002810834],"domain_scores_gemma":[0.9989336,0.0002972233,0.0001817996,0.0003042255,0.0001460694,0.0001371165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003012691,0.0005581478,0.001183862,0.0005773755,0.00009580455,0.00002420465,0.006244468,0.7972208,0.005666442,0.0001501767,0.0005740338,0.1874034],"study_design_scores_gemma":[0.0005429714,0.00006477341,0.009284885,0.001041854,0.0001797952,0.000009133611,0.0005469021,0.9837446,0.003402584,0.0006890526,0.000223421,0.0002700298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5731109,0.00009847402,0.4177969,0.006375678,0.001541844,0.0009216543,0.00006585907,0.00008292594,0.000005701781],"genre_scores_gemma":[0.9129944,0.00007501784,0.08412687,0.001143089,0.0007089149,0.0001975352,0.0006252119,0.0000235809,0.0001053971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3398834,"threshold_uncertainty_score":0.9885866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1224581416049329,"score_gpt":0.4246243530809851,"score_spread":0.3021662114760522,"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."}}