{"id":"W4396750041","doi":"10.1101/2024.05.06.24306965","title":"ShapeMed-Knee: A Dataset and Neural Shape Model Benchmark for Modeling 3D Femurs","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health","keywords":"Benchmark (surveying); Computer science; Artificial neural network; 3d model; Artificial intelligence; Geology; Geodesy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004468648,0.0005813589,0.0007079084,0.0003296348,0.0001042768,0.0002743971,0.0004359011,0.0003669323,0.00003521724],"category_scores_gemma":[0.00005191131,0.0005737898,0.0002629943,0.0001543328,0.00003575299,0.00007886888,0.0007262499,0.001019008,0.00001589755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000606608,"about_ca_system_score_gemma":0.00005190092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003441447,"about_ca_topic_score_gemma":0.00002798631,"domain_scores_codex":[0.9976823,0.00002159423,0.000569853,0.000880456,0.0002885776,0.0005571647],"domain_scores_gemma":[0.9989015,0.00006213076,0.00004973747,0.0007166342,0.00006540626,0.0002045965],"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":[0.00000879547,0.00001030766,0.00005201549,0.001172899,0.0002548597,0.000009470354,0.000177575,0.990234,0.0001431061,0.00003316507,0.002560298,0.005343512],"study_design_scores_gemma":[0.0001863028,0.00001198525,0.000003533238,0.0002375214,0.0005321033,0.000004424515,0.00002369268,0.9930124,0.0000134227,0.005205663,0.0001804014,0.0005885094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6375807,0.008567641,0.3433011,0.0004278915,0.0008838681,0.0005596771,0.00750158,0.0008666714,0.0003108665],"genre_scores_gemma":[0.9859689,0.0004957985,0.00888846,0.0001218465,0.0004354235,0.0002421065,0.003591558,0.0001743383,0.00008159009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3483882,"threshold_uncertainty_score":0.9996713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03668290916117741,"score_gpt":0.2693473377753586,"score_spread":0.2326644286141812,"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."}}