{"id":"W4403666784","doi":"10.1016/s2589-7500(24)00199-7","title":"Fairly evaluating the performance of normative models – Authors' reply","year":2024,"lang":"en","type":"letter","venue":"The Lancet Digital Health","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Normative; Psychology; Epistemology; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.02360122,0.001023312,0.002039033,0.001318456,0.003175435,0.005731434,0.004807329,0.04558944,0.006743329],"category_scores_gemma":[0.2182783,0.001017286,0.001609142,0.001520255,0.008176108,0.01012835,0.003473263,0.06440011,0.006498916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005284822,"about_ca_system_score_gemma":0.007036889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007877691,"about_ca_topic_score_gemma":0.007944106,"domain_scores_codex":[0.9847894,0.006315003,0.00189888,0.002229249,0.003930145,0.0008372896],"domain_scores_gemma":[0.8409943,0.1238959,0.004454779,0.005024417,0.02203058,0.003599938],"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":[0.00003704158,0.0000105076,0.0002690566,0.00006359356,0.0000202483,0.0001499582,0.0002340013,0.00008945137,0.00003500665,0.004732227,0.9899572,0.004401702],"study_design_scores_gemma":[0.0001884225,0.00006241331,0.001390486,0.0011471,0.00008120963,0.00126381,0.001413771,0.001414147,0.0005712904,0.06865445,0.9235033,0.0003096761],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.00009266042,0.0005970099,0.0001267636,0.990171,0.008691013,0.000003514128,0.00004618056,0.00001873412,0.0002530222],"genre_scores_gemma":[0.002235175,0.0004863286,0.0003440696,0.9788181,0.01710963,0.00003329406,0.00002216359,0.00003788673,0.0009134007],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.04558944,"threshold_uncertainty_score":0.1248167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5086227845375636,"score_gpt":0.4583939479901067,"score_spread":0.05022883654745691,"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."}}