{"id":"W2947494553","doi":"10.1111/jebm.12343","title":"Evaluating people's ability to assess treatment claims: Validating a test in Mandarin from Claim Evaluation Tools database","year":2019,"lang":"en","type":"article","venue":"Journal of Evidence-Based Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Hamilton Health Sciences; Impact","funders":"Ministry of Science and Technology of the People's Republic of China","keywords":"Mandarin Chinese; Test (biology); Database; Computer science; Psychology; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09162135,0.0003118034,0.001278847,0.001433295,0.0001218843,0.000238859,0.001063808,0.0001123582,0.003134311],"category_scores_gemma":[0.6151812,0.000171703,0.0001939765,0.003633749,0.00007639664,0.001248081,0.0001352852,0.0004733135,0.00005403132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009480509,"about_ca_system_score_gemma":0.001313654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007511951,"about_ca_topic_score_gemma":0.0002059729,"domain_scores_codex":[0.9865021,0.00348915,0.003077972,0.0008008554,0.005674278,0.000455705],"domain_scores_gemma":[0.7032561,0.2884846,0.003013672,0.00157885,0.003175138,0.000491623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000350269,0.0001623804,0.6041794,0.00002304528,0.00001604646,0.00002223937,0.0006405481,0.008866451,0.02892951,0.000006147823,0.000403825,0.3564002],"study_design_scores_gemma":[0.006854614,0.006841865,0.8889723,0.005872721,0.0002454261,0.00003329864,0.004577305,0.07928684,0.002605677,0.003968144,0.0004039529,0.0003378676],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9718843,0.001102313,0.01620343,0.007995904,0.001474499,0.001001543,0.00002161125,0.00001506225,0.0003013368],"genre_scores_gemma":[0.9336103,0.0000689669,0.06496891,0.0006085386,0.0006462821,0.00002784978,0.000009195249,0.00001481683,0.00004512838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5235599,"threshold_uncertainty_score":0.997777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9102972500589558,"score_gpt":0.6288915867040393,"score_spread":0.2814056633549165,"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."}}