{"id":"W1993809841","doi":"10.1016/j.jclinepi.2004.11.026","title":"The problem of imperfect reference standards","year":2005,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Gold standard (test); Imperfect; Class (philosophy); Latent class model; Standard error; Statistics; Scopus; Computer science; Econometrics; Mathematics; MEDLINE; Artificial intelligence; Philosophy; Linguistics; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1203473,0.0006996989,0.00295638,0.002425304,0.005081879,0.006610998,0.005503879,0.06983295,0.003999642],"category_scores_gemma":[0.4294289,0.001568726,0.001473682,0.002434527,0.01882117,0.01235051,0.005274788,0.06153297,0.002595903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006447302,"about_ca_system_score_gemma":0.007702525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009724223,"about_ca_topic_score_gemma":0.01259608,"domain_scores_codex":[0.8649081,0.08366036,0.0125363,0.008089771,0.02842839,0.002376932],"domain_scores_gemma":[0.4737705,0.4634338,0.01057105,0.01408884,0.03282035,0.005315377],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001336196,0.0000471867,0.002534272,0.000264388,0.00009275954,0.002350582,0.001981505,0.0004565595,0.0001362576,0.1511722,0.7724724,0.06835827],"study_design_scores_gemma":[0.0002691433,0.00009563907,0.002809485,0.00150984,0.00009868947,0.007039781,0.001937501,0.003440125,0.0004370034,0.4175035,0.5646502,0.0002090913],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0003920656,0.001347979,0.002456928,0.9902164,0.003424396,0.000007866902,0.00003388057,0.00002348504,0.002096979],"genre_scores_gemma":[0.01781455,0.001252084,0.007689761,0.9528022,0.01861797,0.00007979719,0.00003287716,0.00005306603,0.001657679],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.8796527,"threshold_uncertainty_score":0.6364648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6177846126145073,"score_gpt":0.5901486659943236,"score_spread":0.02763594662018376,"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."}}