{"id":"W3039365472","doi":"10.1017/s0266462320000422","title":"Assessment of technical errors and validation processes in economic models submitted by the company for NICE technology appraisals","year":2020,"lang":"en","type":"article","venue":"International Journal of Technology Assessment in Health Care","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Health Economics","funders":"","keywords":"Nice; Excellence; Documentation; Process (computing); Computer science; Medicine; Actuarial science; Operations management; Statistics; Mathematics; Engineering; Economics; 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":["metaresearch"],"category_scores_codex":[0.5429599,0.002292906,0.00303488,0.02292776,0.004536551,0.01788804,0.006188173,0.003822226,0.00998333],"category_scores_gemma":[0.8910357,0.002774909,0.005549699,0.01552949,0.004350541,0.009638267,0.01133376,0.005115962,0.005755478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0210275,"about_ca_system_score_gemma":0.05751315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009412558,"about_ca_topic_score_gemma":0.008586285,"domain_scores_codex":[0.3130856,0.3726805,0.143747,0.01133305,0.1536917,0.005462167],"domain_scores_gemma":[0.0522988,0.5188364,0.08059678,0.05761522,0.2871028,0.003550016],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002589216,0.0003544052,0.04689414,0.03424463,0.001909394,0.002797133,0.05258008,0.01664345,0.003539391,0.02756144,0.38343,0.4274567],"study_design_scores_gemma":[0.001097793,0.002100059,0.06118196,0.09759622,0.002115341,0.002228946,0.02286163,0.04035163,0.01155322,0.02889604,0.7281456,0.001871509],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2241528,0.03000412,0.2827829,0.2011718,0.01871196,0.03584978,0.03208403,0.01296543,0.1622772],"genre_scores_gemma":[0.6308458,0.014272,0.2782876,0.009959498,0.003394481,0.02529394,0.0174384,0.005463359,0.01504487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4570401,"threshold_uncertainty_score":0.5636119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.191506990341321,"score_gpt":0.489560139438057,"score_spread":0.298053149096736,"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."}}