{"id":"W4412565123","doi":"10.1016/j.jdent.2025.105998","title":"Performance comparison of large language models in treatment planning for the restoration of endodontically treated teeth over time","year":2025,"lang":"en","type":"article","venue":"Journal of Dentistry","topic":"Dental Research and COVID-19","field":"Dentistry","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Dentistry; Computer science; Medicine; Orthodontics","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":[0.0004344892,0.00009515869,0.000324763,0.0001746765,0.00005229497,0.0000311619,0.0002377908,0.00007287212,0.00005764228],"category_scores_gemma":[0.00021976,0.00006617844,0.0001503698,0.0002042002,0.00004235405,0.0001936949,0.00004042281,0.0001575234,0.000003673076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001804552,"about_ca_system_score_gemma":0.0001875298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007713346,"about_ca_topic_score_gemma":0.0001087136,"domain_scores_codex":[0.9986709,0.00007015131,0.0006120883,0.00009099054,0.000374574,0.000181303],"domain_scores_gemma":[0.9988316,0.0004569824,0.0003649776,0.0001723445,0.0001243844,0.00004965299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006799393,0.00257667,0.8431292,0.0008467396,0.0008958477,0.0005872477,0.002309684,0.009931801,0.1039624,0.001373012,0.01334836,0.01423965],"study_design_scores_gemma":[0.01762301,0.001923785,0.625946,0.001346379,0.0004606186,0.0001912475,0.002941983,0.2387289,0.1088369,0.0007866361,0.0009368982,0.0002776336],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937382,0.001391982,0.003840277,0.00003550657,0.0001530406,0.000198517,0.00005742968,0.000004054457,0.0005809443],"genre_scores_gemma":[0.9971853,0.00003280951,0.0001667496,0.00001692274,0.00003054223,0.000007301884,0.00001150706,0.000007197568,0.00254162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2287971,"threshold_uncertainty_score":0.2698679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04458927469216716,"score_gpt":0.4105299398347069,"score_spread":0.3659406651425398,"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."}}