{"id":"W4220825957","doi":"10.5194/egusphere-egu22-10908","title":"Large Sample, High Dimension Hydrology Dataset Validation: Getting Bit By Bytes","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Geospatial analysis; Structural basin; Byte; Dimension (graph theory); Data mining; Scale (ratio); Computer science; Data set; Hydrology (agriculture); Set (abstract data type); Sample (material); Database; Cartography; Mathematics; Geography; Geology; Artificial intelligence","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":[0.005994321,0.001615012,0.001024859,0.002584067,0.0009443352,0.002488998,0.002162083,0.001409,0.01358693],"category_scores_gemma":[0.03670153,0.0005268009,0.001305257,0.00286733,0.0007254204,0.002695445,0.002264517,0.00239398,0.0104207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007689628,"about_ca_system_score_gemma":0.001638649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00402472,"about_ca_topic_score_gemma":0.005234549,"domain_scores_codex":[0.9969696,0.0006050389,0.0005539879,0.000769766,0.0008881909,0.0002134905],"domain_scores_gemma":[0.9882691,0.004069131,0.0004541141,0.003831969,0.003172394,0.0002032834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00191328,0.0009512349,0.0145538,0.0009284764,0.0004720307,0.0003998573,0.0002793078,0.03249279,0.005166557,0.005936148,0.4805237,0.4563828],"study_design_scores_gemma":[0.001739775,0.0007709549,0.02202366,0.0007156398,0.0001973842,0.0003885567,0.0009163602,0.7905846,0.02123657,0.03427104,0.1269891,0.0001663267],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2436934,0.004420945,0.2070225,0.00508572,0.005933585,0.00287034,0.3969783,0.1165945,0.01740074],"genre_scores_gemma":[0.2337008,0.0006512462,0.3287362,0.001014117,0.0003941687,0.002717627,0.4230642,0.003058143,0.0066635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01358693,"threshold_uncertainty_score":0.04545283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01290906353119339,"score_gpt":0.2457473229336391,"score_spread":0.2328382594024457,"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."}}