{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02966989,0.0004641278,0.002306738,0.0002606704,0.0004613148,0.0004099089,0.001366871,0.0003336655,0.00007248513],"category_scores_gemma":[0.001468363,0.0003469427,0.0003132243,0.0004064349,0.0002839657,0.001000719,0.000246984,0.002275734,0.002092916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007112295,"about_ca_system_score_gemma":0.0008495508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007348542,"about_ca_topic_score_gemma":0.00002120295,"domain_scores_codex":[0.9910551,0.0007830356,0.005883592,0.0008129952,0.0004064996,0.001058786],"domain_scores_gemma":[0.9898695,0.0029042,0.005184712,0.001789896,0.000135017,0.0001167045],"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":[0.00001871063,0.00001492207,0.000235063,0.003392097,0.0001195551,0.000001115014,0.00537976,0.0006400878,1.97079e-8,0.01290471,0.9765161,0.0007778674],"study_design_scores_gemma":[0.0004473756,0.0005860162,0.0004125133,0.001364574,0.00002135699,0.00003060639,0.000726115,0.1025209,6.462951e-7,0.09794047,0.7953719,0.0005775602],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.009653286,0.006442514,0.000356004,0.9609346,0.001495606,0.001657007,0.003333982,0.0001271431,0.01599981],"genre_scores_gemma":[0.06471296,0.0005517623,0.0003684209,0.9215277,0.00598065,0.0002496847,0.0003813863,0.0001259604,0.006101472],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.1811442,"threshold_uncertainty_score":0.9998983,"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."}}