{"id":"W4412714336","doi":"10.1016/j.matcom.2025.07.054","title":"Mesh-based segmentation for automated margin line generation on incisors receiving crown treatment","year":2025,"lang":"en","type":"article","venue":"Mathematics and Computers in Simulation","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"InterDigital (Canada); Mila - Quebec Artificial Intelligence Institute; Polytechnique Montréal","funders":"MEDTEQ+; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; King Fahd University of Petroleum and Minerals","keywords":"Margin (machine learning); Crown (dentistry); Segmentation; Computer science; Line (geometry); Orthodontics; Medicine; Mathematics; Artificial intelligence; Geometry; Machine learning","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":[0.0001584939,0.0001257215,0.0001566782,0.0002791729,0.0001062232,0.0001177195,0.00004410746,0.00004993056,0.000004985044],"category_scores_gemma":[0.00002593341,0.0001197697,0.00005554042,0.0002246476,0.00001574233,0.0000946265,0.00001138817,0.00003446674,0.000002064242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001160258,"about_ca_system_score_gemma":0.00001378952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009717835,"about_ca_topic_score_gemma":0.00001633192,"domain_scores_codex":[0.9992704,0.00002856591,0.0002989202,0.0001917252,0.000100464,0.0001099016],"domain_scores_gemma":[0.9994231,0.0003056834,0.00009718494,0.0001201651,0.00003438981,0.00001951704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001228905,0.0006379437,0.004435671,0.0003192157,0.00008063779,0.000006185353,0.001115039,0.8999215,0.003361779,0.004067752,0.0003909866,0.08554045],"study_design_scores_gemma":[0.001575647,0.0001008901,0.004483653,0.0001706213,0.00002678898,7.121545e-7,0.00007207032,0.9904872,0.001904456,0.001023689,0.00005458453,0.00009966333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5892125,0.00002680415,0.4098072,0.00004392217,0.0002671297,0.0004214201,0.000006718006,0.00008607702,0.0001281937],"genre_scores_gemma":[0.9449939,0.000004845113,0.05461543,0.0001267274,0.00003550003,0.00004675099,0.0001077979,0.00001007935,0.00005901348],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3557813,"threshold_uncertainty_score":0.4884068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0281893125362525,"score_gpt":0.3240920620045928,"score_spread":0.2959027494683403,"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."}}