{"id":"W4220918826","doi":"10.5194/egusphere-egu22-8396","title":"Rate my Hydrograph: Evaluating the Conformity of Expert Judgment and Quantitative Metrics","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hydrograph; Intuition; Computer science; Operations research; Psychology; Mathematics; Surface runoff; Ecology","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":[0.0911504,0.001433554,0.001204551,0.008530592,0.001396631,0.004260273,0.002255952,0.003997209,0.003090053],"category_scores_gemma":[0.42578,0.0004549846,0.001311722,0.004018888,0.002889234,0.005382502,0.004137411,0.002192565,0.001247882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00292524,"about_ca_system_score_gemma":0.001430043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00415642,"about_ca_topic_score_gemma":0.005008214,"domain_scores_codex":[0.9072604,0.05582113,0.008368553,0.01066838,0.01665334,0.001228296],"domain_scores_gemma":[0.4433564,0.4515367,0.03939327,0.02486146,0.03538721,0.00546499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004643574,0.001744115,0.4679446,0.002303377,0.002648341,0.0006615224,0.01852517,0.07944962,0.003860265,0.01485434,0.0524406,0.3509245],"study_design_scores_gemma":[0.0009166742,0.004250339,0.2326757,0.001181706,0.0005772418,0.0009146977,0.008983623,0.6103233,0.007849428,0.0962521,0.03526402,0.0008112587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.770748,0.003332035,0.1817045,0.003897264,0.001079579,0.002839784,0.004247646,0.002111616,0.03003966],"genre_scores_gemma":[0.9325532,0.0002593847,0.06128439,0.0008453922,0.0002531835,0.001130967,0.002316054,0.0002478384,0.001109548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0911504,"threshold_uncertainty_score":0.4820551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07664413679270558,"score_gpt":0.3413232146818654,"score_spread":0.2646790778891598,"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."}}