{"id":"W2563956511","doi":"10.1002/2016wr019191","title":"The integrated hydrologic model intercomparison project, <scp>IH‐MIP2</scp>: A second set of benchmark results to diagnose integrated hydrology and feedbacks","year":2016,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Institut National de la Recherche Scientifique","funders":"Provincia autonoma di Bolzano - Alto Adige; Deutsche Forschungsgemeinschaft; National Science Foundation","keywords":"Surface runoff; Benchmark (surveying); Hydrology (agriculture); Environmental science; Hydrological modelling; Meteorology; Geotechnical engineering; Geology; Climatology; Geography","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":[0.003805572,0.0003263074,0.0004275671,0.0003254573,0.0006516138,0.00008558844,0.001032794,0.0002195124,0.0001418228],"category_scores_gemma":[0.0008042381,0.0001438025,0.00007352861,0.0005214737,0.002304039,0.0001830447,0.002480871,0.0005849039,0.0003850231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001362683,"about_ca_system_score_gemma":0.00001324818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001253374,"about_ca_topic_score_gemma":0.002937876,"domain_scores_codex":[0.9955757,0.001087737,0.0006046854,0.0008840704,0.0005626513,0.001285182],"domain_scores_gemma":[0.997756,0.001249965,0.00009707132,0.000645259,0.00006849401,0.0001832187],"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":[0.005198341,0.0006992967,0.2311797,0.0001532264,0.000877487,0.0002063383,0.1470836,0.005437972,0.1910601,0.0002315222,0.3944925,0.02337988],"study_design_scores_gemma":[0.002913231,0.002788723,0.01029182,0.0001377702,0.0000470115,0.00002209934,0.004778415,0.02366488,0.0527975,0.004576923,0.8976072,0.000374427],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822056,0.00009344247,0.00008655034,0.004807082,0.00005654253,0.0009456226,0.000066423,0.00005627312,0.01168247],"genre_scores_gemma":[0.9849609,0.0001855821,0.0001182773,0.0002215936,0.00003136759,0.000249455,0.00002151517,0.00002512842,0.01418623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5031146,"threshold_uncertainty_score":0.8489328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04023222057586415,"score_gpt":0.3044302423595266,"score_spread":0.2641980217836625,"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."}}