{"id":"W4415565078","doi":"10.1002/ase.70145","title":"A preliminary comparison of bellringer performance across three visual modalities for the assessment of anatomy knowledge","year":2025,"lang":"en","type":"article","venue":"Anatomical Sciences Education","topic":"Augmented Reality Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McMaster University","funders":"McMaster University","keywords":"Modalities; Modality (human–computer interaction); Educational measurement; Test (biology); Presentation (obstetrics); Entry Level; Virtual reality; Point (geometry); Reliability (semiconductor)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005768954,0.000454298,0.0003682288,0.001465957,0.0003020882,0.0009351639,0.0004906997,0.0005726143,0.003227856],"category_scores_gemma":[0.01869573,0.0001787233,0.0006911597,0.0005014622,0.000575895,0.001338594,0.001530351,0.0005234411,0.0008862385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003283519,"about_ca_system_score_gemma":0.0004670107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007353208,"about_ca_topic_score_gemma":0.002102809,"domain_scores_codex":[0.9964036,0.000939443,0.0004717275,0.0004864892,0.001375921,0.0003228892],"domain_scores_gemma":[0.9827712,0.008924787,0.002413214,0.001002036,0.003455277,0.00143349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00433235,0.00260542,0.8037429,0.0003714771,0.0001797738,0.0002397604,0.004952148,0.0007730282,0.03418675,0.0005228974,0.000683766,0.1474099],"study_design_scores_gemma":[0.00005671032,0.01181799,0.9689248,0.00007232997,0.00008240962,0.0004430752,0.001766901,0.002757007,0.01191907,0.0003502377,0.00176139,0.0000480969],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953564,0.00008761407,0.001691499,0.00002955491,0.00001369023,0.0001236903,0.0000911981,0.00002404241,0.002582347],"genre_scores_gemma":[0.9942949,0.0001026937,0.003965979,0.00003020386,0.00001020428,0.0001385105,0.0001609271,0.00001305458,0.001283424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005768954,"threshold_uncertainty_score":0.03050953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03288757913493687,"score_gpt":0.4450221458041341,"score_spread":0.4121345666691972,"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."}}