{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001359605,0.000373731,0.0007298106,0.001256209,0.0002179604,0.0003374886,0.001637366,0.000241834,0.000007341179],"category_scores_gemma":[0.0003148985,0.0003733679,0.0001816899,0.001326857,0.0003003919,0.0002934721,0.004514256,0.0006037263,0.0000303344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009495268,"about_ca_system_score_gemma":0.00008326054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003852622,"about_ca_topic_score_gemma":0.001322737,"domain_scores_codex":[0.9967412,0.000175064,0.0008913278,0.001073376,0.0006104307,0.0005085478],"domain_scores_gemma":[0.9973063,0.0006469145,0.000567247,0.001083933,0.000257587,0.0001379568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001962276,0.0003781595,0.03751235,0.0006888009,0.0004712461,0.0001710886,0.0122518,0.03600976,0.003405441,0.89927,0.0006179536,0.009203793],"study_design_scores_gemma":[0.0001942346,0.0004682527,0.003762017,0.0004059073,0.00006764122,0.000007603466,0.001975467,0.7044999,0.07479334,0.2126963,0.0001797959,0.0009495636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4846163,0.0005555279,0.5068997,0.0004578721,0.0006523483,0.0006009752,0.000004592258,0.0004758839,0.00573676],"genre_scores_gemma":[0.940638,0.0001105826,0.05891261,0.00007169182,0.00002479741,0.00004611327,0.000009885397,0.00002499976,0.0001613215],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6865737,"threshold_uncertainty_score":0.9998719,"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."}}