{"id":"W2013618133","doi":"10.1118/1.3244113","title":"Poster — Wed Eve—09: Quest for a “Gold Standard” for Breast Density Evaluation","year":2009,"lang":"en","type":"article","venue":"Medical Physics","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Gold standard (test); Thresholding; Breast density; Kappa; Cohen's kappa; Population; Statistics; Standard error; Mathematics; Sample (material); Artificial intelligence; Standard deviation; Computer science; Pattern recognition (psychology); Breast cancer; Medicine; Image (mathematics); Mammography; Physics","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":[0.0006378554,0.0001554185,0.0003113153,0.00004602278,0.00006423042,0.00003668895,0.00008936896,0.00008747702,0.00003064848],"category_scores_gemma":[0.0003273496,0.0001270396,0.0002538832,0.0001801743,0.00008823882,0.0001810406,0.00001331391,0.0001368515,0.000006748738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007332072,"about_ca_system_score_gemma":0.0002645642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003584642,"about_ca_topic_score_gemma":0.000002153473,"domain_scores_codex":[0.9982979,0.00002031116,0.0002298707,0.0002720113,0.0008674452,0.0003124474],"domain_scores_gemma":[0.9988608,0.0001223227,0.00006385834,0.0002069704,0.0004547133,0.0002913569],"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":[0.001008882,0.0004128228,0.002110945,0.000103618,0.00007401665,0.000007347081,0.00009103509,5.426605e-7,0.0003353085,0.001208272,0.009726027,0.9849212],"study_design_scores_gemma":[0.05695981,0.007756411,0.5181078,0.003465423,0.003623659,0.00161251,0.000178742,0.01893933,0.02094608,0.3378868,0.02835963,0.002163768],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.661711,0.0004796227,0.2306793,0.06633309,0.001256933,0.007343668,0.0008183228,0.0005724933,0.03080552],"genre_scores_gemma":[0.9948701,0.000003102818,0.0003502433,0.003348472,0.001026178,0.00004979429,0.0002051466,0.00001805369,0.0001288855],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9827574,"threshold_uncertainty_score":0.5180525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01960685277398226,"score_gpt":0.3157823844826234,"score_spread":0.2961755317086411,"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."}}