{"id":"W3201575135","doi":"10.1016/j.rser.2021.111605","title":"Value-added diagnostics for the assessment and validation of integrated assessment models","year":2021,"lang":"en","type":"article","venue":"Renewable and Sustainable Energy Reviews","topic":"Environmental Impact and Sustainability","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"Australian Research Council; Massachusetts Institute of Technology; National Science Foundation","keywords":"Value (mathematics); Model validation; Engineering; Biochemical engineering; Computer science; Data science; Machine learning","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":[0.03464894,0.002180747,0.001146569,0.002631769,0.0007498311,0.004554332,0.003306207,0.002063323,0.00233747],"category_scores_gemma":[0.1159073,0.001233565,0.001547056,0.001833418,0.001661094,0.005420965,0.003924876,0.002975935,0.0003448581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003220889,"about_ca_system_score_gemma":0.003859255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01438906,"about_ca_topic_score_gemma":0.007780974,"domain_scores_codex":[0.9895439,0.005918053,0.001116159,0.0008997881,0.002090047,0.000432004],"domain_scores_gemma":[0.9251203,0.0473786,0.005709344,0.01050516,0.01036282,0.0009237307],"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":[0.0004284883,0.0002521616,0.02691184,0.0002079015,0.0003394866,0.0001556748,0.0002212558,0.9267932,0.002185844,0.01585947,0.001571653,0.02507299],"study_design_scores_gemma":[0.00007733087,0.0001543281,0.002516769,0.0001225505,0.00005584854,0.00002904402,0.00009293512,0.9823248,0.00309213,0.009654199,0.001833712,0.00004643019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4268225,0.000621651,0.5464098,0.001526641,0.000313699,0.0008332567,0.005768876,0.005113505,0.0125901],"genre_scores_gemma":[0.8342055,0.00009859967,0.162043,0.000205096,0.00002343632,0.0004369578,0.002340304,0.0002524481,0.0003946876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03464894,"threshold_uncertainty_score":0.1832433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02026477571164305,"score_gpt":0.2894868551908096,"score_spread":0.2692220794791666,"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."}}