{"id":"W4410421527","doi":"10.1016/j.inffus.2025.103290","title":"Multimodal graph representation learning for robust surgical workflow recognition with adversarial feature disentanglement","year":2025,"lang":"en","type":"article","venue":"Information Fusion","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"General Research Fund of Shanghai Normal University; Basic and Applied Basic Research Foundation of Guangdong Province; Research Grants Council, University Grants Committee; University Grants Committee; National Natural Science Foundation of China","keywords":"Workflow; Computer science; Adversarial system; Feature (linguistics); Artificial intelligence; Representation (politics); Graph; Feature learning; Pattern recognition (psychology); Machine learning; Theoretical computer science; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0002294801,0.0001057747,0.0001391197,0.0002500804,0.0002952441,0.00005251032,0.00003577112,0.000130848,0.00009710258],"category_scores_gemma":[0.0001999954,0.00008746338,0.00007087185,0.000407927,0.00002908233,0.000544761,0.00001527775,0.0001899858,0.00003534343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001353871,"about_ca_system_score_gemma":0.000135278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001621901,"about_ca_topic_score_gemma":0.00003845432,"domain_scores_codex":[0.9990539,0.000036079,0.0003682558,0.0001367565,0.0002300683,0.000174922],"domain_scores_gemma":[0.9990702,0.0001407319,0.0001510325,0.0001196861,0.0004465423,0.00007175668],"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":[0.003875348,0.000113648,0.02102206,0.0002338602,0.00003815415,0.000002180964,0.002285313,0.004737129,0.00009054834,0.0001610332,0.005981313,0.9614594],"study_design_scores_gemma":[0.0116,0.004700353,0.07864918,0.004832234,0.001117925,0.0001710365,0.05571121,0.4263146,0.04860777,0.005919931,0.3607591,0.001616661],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8049045,0.00006744052,0.1687049,0.01240858,0.001864806,0.003481137,0.00002135827,0.0002676217,0.008279608],"genre_scores_gemma":[0.9824907,0.0001143337,0.01193219,0.0006035775,0.0004091505,0.0002561515,0.003433309,0.000009966629,0.0007506691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9598427,"threshold_uncertainty_score":0.3566653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06745328815614876,"score_gpt":0.3692231138346696,"score_spread":0.3017698256785208,"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."}}