{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007451196,0.00008545077,0.0001615691,0.00009108514,0.0004284715,0.00005762262,0.001135844,0.00004595164,0.000002705082],"category_scores_gemma":[0.00004282886,0.00006203391,0.0000618161,0.0009525999,0.0005582434,0.0002858207,0.0002614488,0.00008223496,9.970305e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008276678,"about_ca_system_score_gemma":0.0008949265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001430429,"about_ca_topic_score_gemma":0.00006320707,"domain_scores_codex":[0.9988877,0.00003733138,0.0003687878,0.0002774714,0.0002286513,0.0002000111],"domain_scores_gemma":[0.9986783,0.0005490856,0.0002034522,0.0003149794,0.0002211863,0.00003304436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008636795,0.0009761775,0.0653776,0.0001500653,0.00003186652,5.329849e-9,0.002414407,0.001292195,0.0005029616,0.6052944,0.0009947602,0.3229569],"study_design_scores_gemma":[0.0001079982,0.000125263,0.1534666,0.0000595561,0.00001417057,3.098519e-7,0.001156755,0.8331129,0.006226771,0.004707636,0.0009531425,0.0000689195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6262041,0.0004230162,0.3688149,0.002313162,0.0002806248,0.0004827502,0.000003997884,0.00002144506,0.001456006],"genre_scores_gemma":[0.992255,0.00001907631,0.007360134,0.00005232423,0.00002207775,0.0002087032,0.000003149533,0.000002126547,0.00007744422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8318207,"threshold_uncertainty_score":0.3295499,"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."}}