{"id":"W4412667156","doi":"10.1002/jdd.14002","title":"Reliability and Performance of Four Large Language Models in Orthodontic Knowledge Assessment","year":2025,"lang":"en","type":"article","venue":"Journal of Dental Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reliability (semiconductor); Consistency (knowledge bases); Computer science; Variable (mathematics); Artificial intelligence; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05552956,0.001177185,0.001133187,0.002187976,0.0005613161,0.002995432,0.00140945,0.00157836,0.001112872],"category_scores_gemma":[0.2460002,0.0005385733,0.001613866,0.001412384,0.001277568,0.003044622,0.002924323,0.001675757,0.0007331487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001600128,"about_ca_system_score_gemma":0.001362896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00626681,"about_ca_topic_score_gemma":0.004787245,"domain_scores_codex":[0.9537171,0.03397718,0.003534084,0.003434501,0.004782065,0.000554998],"domain_scores_gemma":[0.665745,0.2980962,0.008992054,0.01063412,0.01507072,0.00146185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01572892,0.002547957,0.446963,0.001504468,0.002651347,0.0003207862,0.009735639,0.09638398,0.003591707,0.001960969,0.004659547,0.4139515],"study_design_scores_gemma":[0.0007940857,0.005826759,0.1795551,0.0007016117,0.001770514,0.0005621368,0.003550074,0.7862076,0.008625927,0.007205728,0.004713629,0.0004867727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9704739,0.0007636954,0.02361001,0.0004151797,0.0001326454,0.000446542,0.0005711632,0.0006976298,0.002889145],"genre_scores_gemma":[0.9855337,0.0001665512,0.01282965,0.00007681149,0.00002433277,0.0002310084,0.0006397024,0.00006082916,0.0004375485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05552956,"threshold_uncertainty_score":0.2936719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06505396844585527,"score_gpt":0.4589016383013232,"score_spread":0.3938476698554679,"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."}}