{"id":"W4322002798","doi":"10.5194/egusphere-egu23-12261","title":"Peeking Inside Hydrologists' Minds: Comparing Human Judgment and Quantitative Metrics of Hydrographs","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Metric (unit); Consistency (knowledge bases); Benchmarking; Set (abstract data type); Computer science; Hydrograph; Quality (philosophy); Similarity (geometry); Artificial intelligence; Scale (ratio); Data science; Preference; Machine learning; Psychology; Cognitive psychology; Mathematics; Statistics; Epistemology; Marketing; Ecology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04180418,0.0005500417,0.0005124723,0.002456992,0.001587932,0.004476267,0.0009884457,0.001693122,0.001577432],"category_scores_gemma":[0.1984131,0.0003289789,0.0004682363,0.001426148,0.004896696,0.004631722,0.003090465,0.001259011,0.0004790793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001758155,"about_ca_system_score_gemma":0.0008217789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006309702,"about_ca_topic_score_gemma":0.006193541,"domain_scores_codex":[0.9438405,0.04230032,0.001629664,0.004176138,0.007095673,0.0009577615],"domain_scores_gemma":[0.763469,0.1952859,0.01379771,0.0122203,0.01295812,0.002268964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001413692,0.0004188847,0.4573059,0.001099521,0.0007960696,0.0004757631,0.2505364,0.008210499,0.008861171,0.01357836,0.01271305,0.2445907],"study_design_scores_gemma":[0.0001942033,0.001414037,0.6039617,0.0009807402,0.0002815898,0.0007516039,0.2060522,0.08068703,0.01040875,0.06780238,0.02664229,0.0008234626],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9626344,0.0004969236,0.02407553,0.001443026,0.00009099994,0.00008823995,0.0001473705,0.0001209987,0.01090251],"genre_scores_gemma":[0.9941877,0.00007068925,0.004820896,0.0003664141,0.00002823303,0.0000459094,0.00009660287,0.00003810185,0.0003454708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04180418,"threshold_uncertainty_score":0.2210843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1945003812986814,"score_gpt":0.3616460499875889,"score_spread":0.1671456686889075,"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."}}