{"id":"W4414672414","doi":"10.5194/hess-29-4761-2025","title":"Can causal discovery lead to a more robust prediction model for runoff signatures?","year":2025,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"United Nations University Institute for Water, Environment, and Health","funders":"Česká Zemědělská Univerzita v Praze; Ministerstvo Školství, Mládeže a Tělovýchovy","keywords":"Surface runoff; Bayesian network; Robustness (evolution); Bayesian probability; Random forest; Identification (biology); Lead (geology); Causal model","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":[0.006175731,0.0007834485,0.0009079523,0.001231887,0.0004889647,0.0009253906,0.001332872,0.001102214,0.001874448],"category_scores_gemma":[0.02732558,0.0006138058,0.0009727441,0.0008135359,0.0007602561,0.002317462,0.0008601541,0.001728577,0.0002696704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001146461,"about_ca_system_score_gemma":0.001597176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01701524,"about_ca_topic_score_gemma":0.01342779,"domain_scores_codex":[0.9986959,0.0007671892,0.00005569249,0.0002915046,0.0001051053,0.00008463268],"domain_scores_gemma":[0.9853784,0.01256285,0.0008018868,0.0005293224,0.0005643924,0.0001630493],"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":[0.0001220589,0.00007484318,0.01089287,0.00004450156,0.0001103427,0.00006875388,0.00005268477,0.9577704,0.0004705208,0.004566783,0.0004793356,0.02534694],"study_design_scores_gemma":[0.000007509008,0.000008959806,0.0003576406,0.000003917854,0.000009271972,0.000007956486,0.000004088897,0.9958761,0.00008899297,0.00357782,0.00005471447,0.000003020074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2997592,0.0003085422,0.695073,0.001781958,0.00005993611,0.00008271333,0.0003486937,0.001049084,0.001536882],"genre_scores_gemma":[0.9340276,0.0001071421,0.06464195,0.000161631,0.00002986387,0.00006348094,0.0003892464,0.00005644163,0.0005226541],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01701524,"threshold_uncertainty_score":0.03383243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01445069073343188,"score_gpt":0.2315655435402933,"score_spread":0.2171148528068614,"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."}}