{"id":"W4409654546","doi":"10.1016/j.jsurg.2025.103504","title":"Mixed Reality for Remote Procedural Training and Assessment: A Feasibility Study","year":2025,"lang":"en","type":"article","venue":"Journal of surgical education","topic":"Augmented Reality Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Training (meteorology); Virtual reality; Computer science; Medicine; Psychology; Human–computer interaction; Geography","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":[0.001610407,0.00007916416,0.0002044758,0.0001154988,0.0001472068,0.0001096578,0.000303367,0.00004214231,0.000002021463],"category_scores_gemma":[0.0001668577,0.00006610998,0.00006849159,0.000360309,0.00003792351,0.000331778,0.00005911773,0.0001878992,1.703474e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001607072,"about_ca_system_score_gemma":0.001242286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002545551,"about_ca_topic_score_gemma":0.00001120575,"domain_scores_codex":[0.9988469,0.0001360945,0.0004895474,0.0002061538,0.0002004283,0.0001208534],"domain_scores_gemma":[0.998675,0.0002749983,0.0003153078,0.0002462209,0.0003929654,0.00009554194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000932156,0.003501681,0.005194717,0.000138936,0.0001290802,0.000003050323,0.003485256,0.00005336681,0.0001443352,0.1105867,0.004386132,0.8722835],"study_design_scores_gemma":[0.006977228,0.001415515,0.6237923,0.0003945222,0.0002797403,0.0004082431,0.01229929,0.08056399,0.0002109494,0.1919579,0.08117542,0.0005248963],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2820072,0.0001327831,0.6853321,0.02958559,0.0005134287,0.0009434248,0.000002417829,0.0000273682,0.001455653],"genre_scores_gemma":[0.9556751,0.00002569618,0.04392266,0.0001306097,0.00008876174,0.00002019323,0.000002176097,0.000002860014,0.0001319056],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8717586,"threshold_uncertainty_score":0.2695887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09570179192505565,"score_gpt":0.4169650281284432,"score_spread":0.3212632362033876,"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."}}