{"id":"W4402404799","doi":"10.1016/j.hydroa.2024.100185","title":"How much X is in XAI: Responsible use of “Explainable” artificial intelligence in hydrology and water resources","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrology X","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Australian Research Council; Westpac Scholars Trust; University of Melbourne","keywords":"Water resources; Hydrology (agriculture); Water resource management; Environmental science; Engineering; Geotechnical engineering; Ecology; Biology","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":[0.01678534,0.001297446,0.001500718,0.002018195,0.003182406,0.01368145,0.003043255,0.005639777,0.007422258],"category_scores_gemma":[0.03969816,0.0009731413,0.001991043,0.002313991,0.01896971,0.02973793,0.008964871,0.009541376,0.002285826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002611188,"about_ca_system_score_gemma":0.003567438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003581801,"about_ca_topic_score_gemma":0.002616243,"domain_scores_codex":[0.9923345,0.004128568,0.0004624242,0.001539388,0.001216029,0.0003189279],"domain_scores_gemma":[0.9772047,0.01380027,0.002003151,0.004697008,0.001557691,0.0007370188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001104061,0.00007050366,0.002561114,0.0003724759,0.0001819858,0.000304481,0.002619742,0.006096915,0.0009144815,0.8751459,0.02182075,0.08980117],"study_design_scores_gemma":[0.00001953413,0.00003010822,0.0005082122,0.0002832049,0.0000376121,0.00008644478,0.0003105636,0.01022138,0.0006482546,0.9393361,0.04846624,0.00005236975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01731217,0.03234018,0.60827,0.2715403,0.006166103,0.0001441971,0.0004386348,0.002442434,0.06134589],"genre_scores_gemma":[0.5671551,0.03125408,0.3129508,0.04277674,0.008513319,0.0005188092,0.0007102176,0.003149266,0.03297172],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01678534,"threshold_uncertainty_score":0.08877039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03787428450128096,"score_gpt":0.2622771441821071,"score_spread":0.2244028596808261,"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."}}