{"id":"W2574764964","doi":"10.1111/joa.12576","title":"Rapid automated landmarking for morphometric analysis of three‐dimensional facial scans","year":2017,"lang":"en","type":"article","venue":"Journal of Anatomy","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotchkiss Brain Institute; Alberta Children's Hospital; Alberta Bone and Joint Health Institute; University of Calgary","funders":"National Institute of Dental and Craniofacial Research; National Institutes of Health","keywords":"Computer science; Computer graphics (images); Artificial intelligence; Computer vision; Pattern recognition (psychology); Information retrieval","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":[0.00090949,0.00009982081,0.000554713,0.0008733326,0.0002090845,0.00005349772,0.0003254607,0.00008916303,0.0003036043],"category_scores_gemma":[0.00126832,0.00007012507,0.0004660679,0.0005727299,0.00004955955,0.0001381699,0.00005078152,0.0001206444,0.000001086798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003579399,"about_ca_system_score_gemma":0.00006383021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002553961,"about_ca_topic_score_gemma":0.00001782309,"domain_scores_codex":[0.99879,0.00002963832,0.0005934574,0.0000988887,0.0003383517,0.0001497216],"domain_scores_gemma":[0.9973928,0.0004942531,0.00137796,0.0002509866,0.0004056307,0.00007833209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001255529,0.003792492,0.6704978,0.0005019354,0.03018241,0.0004023178,0.0003979953,0.003436438,0.009235827,0.1015161,0.093815,0.08496615],"study_design_scores_gemma":[0.0039105,0.0005760738,0.7572732,0.0001297509,0.004785077,0.0000592922,0.00006650807,0.2074791,0.001413187,0.01729732,0.006623748,0.0003862616],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793581,0.0001344135,0.01918719,0.0003013313,0.00021357,0.0001117993,0.00007007365,0.00001950104,0.0006040722],"genre_scores_gemma":[0.9599977,0.00001128699,0.03981687,0.00002558826,0.00009687308,0.000001561752,0.000004272436,0.000007909025,0.00003798058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2040426,"threshold_uncertainty_score":0.3324254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06954739222030414,"score_gpt":0.3522900776887317,"score_spread":0.2827426854684275,"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."}}