{"id":"W1984940311","doi":"10.3389/fgene.2011.00031","title":"Cost–Effective Prediction of Gender-Labeling Errors and Estimation of Gender-Labeling Error Rates in Candidate-Gene Association Studies","year":2011,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Cancer Agency; Simon Fraser University","funders":"Canadian Institutes of Health Research; Mitacs; Fondation pour la Recherche Médicale; Michael Smith Health Research BC","keywords":"Estimation; Computer science; Word error rate; Association (psychology); Statistics; Econometrics; Artificial intelligence; Psychology; Mathematics; Engineering","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":[0.000927919,0.0001690069,0.000400521,0.0001876073,0.00004636542,0.000003487139,0.00009910236,0.0002913815,0.000001673117],"category_scores_gemma":[0.0008151112,0.0001816326,0.00004769656,0.0001959175,0.00009000995,0.000007656111,0.0000819859,0.0001149933,2.749541e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001342715,"about_ca_system_score_gemma":0.00006533727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007873742,"about_ca_topic_score_gemma":0.0001084278,"domain_scores_codex":[0.9983973,0.0002541186,0.000621111,0.0003223292,0.0001308706,0.0002742976],"domain_scores_gemma":[0.9990662,0.00006599416,0.0004454714,0.0001840118,0.000196785,0.00004156647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006107845,0.00008117902,0.9578072,0.00007618097,0.0002230229,6.082414e-7,0.002454931,0.01385161,0.0211359,0.000005199128,0.0003999967,0.003903121],"study_design_scores_gemma":[0.001712576,0.0004001385,0.8491282,0.00005390363,0.0001452361,0.000002460654,0.004091117,0.03580388,0.106275,0.002062751,0.000063981,0.0002606827],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9736585,0.008256471,0.01690342,0.00001959106,0.0004452563,0.0005782659,0.00006808464,0.000005479048,0.00006495359],"genre_scores_gemma":[0.9268746,0.003661826,0.06918778,0.00002836919,0.00003370355,0.00007487413,0.0001019001,0.00001738543,0.00001961834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1086789,"threshold_uncertainty_score":0.740676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05134743811177404,"score_gpt":0.3068955860228937,"score_spread":0.2555481479111196,"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."}}