{"id":"W4403684139","doi":"10.1002/hyp.15288","title":"Setting expectations for hydrologic model performance with an ensemble of simple benchmarks","year":2024,"lang":"en","type":"article","venue":"Hydrological Processes","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"National Oceanic and Atmospheric Administration","keywords":"Hydrological modelling; Simple (philosophy); Computer science; Hydrology (agriculture); Environmental science; Geology; Climatology; Geotechnical engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0002048397,0.0001611542,0.0001860651,0.00004144797,0.0002503832,0.00002143291,0.0002062242,0.00008446036,0.0003049191],"category_scores_gemma":[0.00006332238,0.0001038123,0.00003432855,0.0002502183,0.0003435641,0.0003815393,0.0001148672,0.0001057957,0.00002655554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001910901,"about_ca_system_score_gemma":0.00001431838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006973629,"about_ca_topic_score_gemma":0.00003316528,"domain_scores_codex":[0.9988701,0.00002316003,0.0001994399,0.0004325169,0.0001472575,0.0003275008],"domain_scores_gemma":[0.9995788,0.0001622884,0.00005368628,0.0001389626,0.00001613828,0.00005014069],"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":[0.0004486592,0.0003831446,0.04103833,0.0008975784,0.0001149633,0.00002057757,0.002755876,0.9427261,0.002430722,0.0009845759,0.002763054,0.005436414],"study_design_scores_gemma":[0.0002568987,0.002069494,0.0008947148,0.00002282782,0.00008343058,0.000008056401,0.0001703405,0.9679665,0.002941967,0.02432798,0.000999799,0.0002579884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9792412,0.000145238,0.01098738,0.0005974986,0.00001974858,0.0003141679,0.000008448739,0.000127391,0.008558953],"genre_scores_gemma":[0.995566,0.00004586493,0.003636122,0.0002593448,0.00002194146,0.0002149074,0.00004227159,0.00001091403,0.0002026452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04014361,"threshold_uncertainty_score":0.4233342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01862025629561084,"score_gpt":0.2527740476381288,"score_spread":0.234153791342518,"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."}}