{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4066053,0.0003375238,0.005066293,0.0001965362,0.0001625862,0.00005470199,0.003603839,0.001667972,0.0006589983],"category_scores_gemma":[0.368562,0.0001447485,0.002248474,0.0002853352,0.001341084,0.0001464489,0.0002691212,0.007253008,0.00006718456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001316253,"about_ca_system_score_gemma":0.001561294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001462561,"about_ca_topic_score_gemma":0.00002544061,"domain_scores_codex":[0.9091976,0.04728952,0.03396215,0.001077757,0.007348223,0.001124708],"domain_scores_gemma":[0.6394899,0.3294434,0.02369653,0.00154827,0.005571944,0.0002498728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002227408,0.00005616806,0.01258578,0.00002214784,0.0001537736,0.00001916623,0.00001287683,0.0001219,0.000001918022,0.0003970875,0.8622344,0.1241721],"study_design_scores_gemma":[0.0004307559,0.001350881,0.007224698,0.0001635586,0.0000755478,0.00003324467,0.00002189281,0.00003554542,0.000002918413,0.111399,0.8791392,0.000122656],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0032896,0.002716842,0.002238554,0.9835168,0.002601878,0.0002845121,0.00006105661,0.000005414522,0.005285361],"genre_scores_gemma":[0.01194279,0.01705781,0.01941457,0.9202157,0.02614942,0.00001328291,0.000007650794,0.00004651521,0.005152217],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.2821539,"threshold_uncertainty_score":0.9996281,"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."}}