{"id":"W4415543248","doi":"10.1007/978-3-031-92870-3_3","title":"Model Validation with a Set of Exhaustive 2D Multivariate, Continuous, and Categorical Examples","year":2025,"lang":"en","type":"book-chapter","venue":"Quantitative geology and geostatistics","topic":"Philosophy and History of Science","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Geoscience BC","funders":"","keywords":"Categorical variable; Cross-validation; Set (abstract data type); Workflow; Variogram; Model validation; Data set","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":[0.007639172,0.001533754,0.001470419,0.001742164,0.001190632,0.001700079,0.002069891,0.002350321,0.005302222],"category_scores_gemma":[0.03411425,0.0007414829,0.002404568,0.001918731,0.001133732,0.001490448,0.002037752,0.002391918,0.001321154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009093396,"about_ca_system_score_gemma":0.001395173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01355256,"about_ca_topic_score_gemma":0.02487206,"domain_scores_codex":[0.9954075,0.002919646,0.0003149431,0.0005769555,0.0006345857,0.0001462709],"domain_scores_gemma":[0.9590114,0.03409061,0.0004779363,0.003724721,0.002486069,0.0002091902],"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":[0.0009032827,0.0004786718,0.0108183,0.0008866593,0.0004406306,0.0003986454,0.0002515826,0.842004,0.001608649,0.007123543,0.02385683,0.1112292],"study_design_scores_gemma":[0.00009310208,0.0001072101,0.00254052,0.00007997356,0.00006476456,0.0001298377,0.0001176771,0.9830045,0.001321338,0.009679299,0.002822893,0.00003886354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4368249,0.004164455,0.5211754,0.001857147,0.0002702269,0.0002893649,0.01808444,0.003747014,0.01358711],"genre_scores_gemma":[0.6753442,0.0005942742,0.293135,0.0004722575,0.00007349642,0.0003777884,0.02560689,0.0004559823,0.003940023],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01355256,"threshold_uncertainty_score":0.04040027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08623605443398083,"score_gpt":0.2760913456915237,"score_spread":0.1898552912575429,"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."}}