{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003869211,0.0009585092,0.0007949504,0.0009377183,0.000654231,0.002482784,0.001679033,0.001169251,0.005947313],"category_scores_gemma":[0.02393324,0.001007789,0.001421455,0.0007395588,0.0005567749,0.001343299,0.001513354,0.0007809042,0.001563561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001590603,"about_ca_system_score_gemma":0.002252596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01843394,"about_ca_topic_score_gemma":0.01848468,"domain_scores_codex":[0.9976599,0.001103912,0.0002076242,0.0003471342,0.0005780626,0.0001032802],"domain_scores_gemma":[0.9785401,0.01799595,0.0005692582,0.0007952541,0.001748821,0.0003507051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02027691,0.0014323,0.03078945,0.0008034772,0.0005601629,0.0008780092,0.003825362,0.385218,0.04240369,0.002495614,0.004800244,0.5065168],"study_design_scores_gemma":[0.0001650123,0.001964386,0.01099021,0.00006610683,0.0004199108,0.00039683,0.001453225,0.9540216,0.02613624,0.001212981,0.002978129,0.0001953627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.906047,0.000883796,0.08261015,0.0004144011,0.000196113,0.0003494796,0.000985751,0.004307021,0.004206332],"genre_scores_gemma":[0.9402406,0.0002629556,0.05549379,0.00009759421,0.00002028765,0.0001984691,0.001035913,0.0005775088,0.002072786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01843394,"threshold_uncertainty_score":0.03665328,"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."}}