{"id":"W2946359821","doi":"10.1111/joa.12973","title":"The effect of automated landmark identification on morphometric analyses","year":2019,"lang":"en","type":"article","venue":"Journal of Anatomy","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Toronto; Hospital for Sick Children; Alberta Bone and Joint Health Institute; University of Calgary","funders":"National Institute of Dental and Craniofacial Research; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Compute Canada","keywords":"Landmark; Identification (biology); Computer science; Artificial intelligence; Computational biology; Data science; Natural language processing; Information retrieval; Pattern recognition (psychology); Biology; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03429782,0.002018831,0.001862617,0.002440571,0.001823338,0.003058807,0.002113205,0.001709279,0.003614541],"category_scores_gemma":[0.1326484,0.001596286,0.001820068,0.003263209,0.00227954,0.001910328,0.003487132,0.002051287,0.002004301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001355362,"about_ca_system_score_gemma":0.001351075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003837484,"about_ca_topic_score_gemma":0.005708938,"domain_scores_codex":[0.9482186,0.02576276,0.004283028,0.009289095,0.01115472,0.001291759],"domain_scores_gemma":[0.7928944,0.1439395,0.01155726,0.03410698,0.01683997,0.0006619716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005837625,0.0006855674,0.06911898,0.002179059,0.001436185,0.0004850042,0.003362249,0.07854913,0.2395487,0.006510301,0.007136695,0.5851504],"study_design_scores_gemma":[0.0003610077,0.004296493,0.3032897,0.0003860509,0.001217585,0.001346817,0.001283685,0.3613941,0.2766051,0.01276924,0.03611169,0.0009386049],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4002879,0.001452958,0.5806969,0.0005248202,0.0007423022,0.001007318,0.001652974,0.009944168,0.00369069],"genre_scores_gemma":[0.5169981,0.0004547979,0.46999,0.0006523849,0.0001455175,0.001661058,0.002010006,0.005552067,0.002536122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03429782,"threshold_uncertainty_score":0.1813863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03050145859222506,"score_gpt":0.3756485519749069,"score_spread":0.3451470933826818,"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."}}