{"id":"W2890132602","doi":"10.1007/s40273-018-0711-9","title":"Trusting the Results of Model-Based Economic Analyses: Is there a Pragmatic Validation Solution?","year":2018,"lang":"en","type":"article","venue":"PharmacoEconomics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Timeline; Transparency (behavior); Computer science; Risk analysis (engineering); Management science; Field (mathematics); Data aggregator; Health administration; Data science; Component (thermodynamics); Psychological intervention; Process management; Public health; Business; Medicine; Economics; Computer security","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01312855,0.0003011641,0.0009587505,0.0003411641,0.000400927,0.0001226791,0.0006674445,0.0001400546,0.0009436253],"category_scores_gemma":[0.000890961,0.0003245369,0.0002776886,0.0001581956,0.0002702501,0.0006569616,0.00008558979,0.0002085963,0.002484532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008159138,"about_ca_system_score_gemma":0.0004547192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008920879,"about_ca_topic_score_gemma":0.0001090321,"domain_scores_codex":[0.9933156,0.0003280434,0.005090938,0.0007080325,0.00007267849,0.0004847331],"domain_scores_gemma":[0.9930879,0.001218749,0.00452207,0.0008985577,0.0001119986,0.0001607025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008105508,0.0006805053,0.02029432,0.001503525,0.001737239,0.000001235705,0.01942433,0.4869671,0.0009649947,0.09655125,0.3688214,0.002243522],"study_design_scores_gemma":[0.001984924,0.00006530969,0.0004515573,0.00004426828,0.00004946693,0.000001852652,0.0003481084,0.9701523,0.002387863,0.009948373,0.0142119,0.0003541039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8296893,0.001285974,0.06990471,0.06457634,0.00181102,0.001991173,0.003397482,0.0001597191,0.02718426],"genre_scores_gemma":[0.9839379,0.00009531772,0.005290884,0.009325977,0.0007462998,0.0001015404,0.00008419843,0.00005820513,0.0003596943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4831851,"threshold_uncertainty_score":0.9999697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4402854882852356,"score_gpt":0.5135493975386651,"score_spread":0.07326390925342957,"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."}}