{"id":"W4379058118","doi":"10.1016/j.geoderma.2023.116553","title":"Divergence metrics for determining optimal training sample size in digital soil mapping","year":2023,"lang":"en","type":"article","venue":"Geoderma","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Ministry of Agriculture, Food and Rural Affairs","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Agriculture, Food and Rural Affairs","keywords":"Sample size determination; Statistics; Covariate; Mathematics; Divergence (linguistics); Sample (material); Sampling (signal processing); Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002818044,0.0001240984,0.0001499518,0.00009507182,0.0001603077,0.00008153617,0.0001984147,0.00004757481,0.0001482366],"category_scores_gemma":[0.001655608,0.0001360785,0.00005177307,0.00076538,0.00005771282,0.0002382251,0.0002741413,0.00008249553,0.0001431026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006605306,"about_ca_system_score_gemma":0.00001464208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001644712,"about_ca_topic_score_gemma":0.00006479867,"domain_scores_codex":[0.9986961,0.000008119107,0.0002357584,0.0003140536,0.0002168033,0.0005291681],"domain_scores_gemma":[0.9985825,0.001130717,0.00006149028,0.000132237,0.000008021317,0.00008501152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001751586,0.00004175397,0.4792293,0.00005259358,0.00001996528,0.00009587823,0.0101023,0.09801896,0.00141289,0.0001438151,0.002716096,0.4081489],"study_design_scores_gemma":[0.000784479,0.00005950691,0.3371841,0.0000445465,0.000009148152,0.00001091113,0.003840036,0.6419809,0.0001611592,0.005221601,0.01020945,0.0004940817],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9519304,0.0000083241,0.0460123,0.00008242574,0.0002087565,0.0001770232,0.0001146524,0.00009257731,0.001373518],"genre_scores_gemma":[0.9824679,0.000009119421,0.01699012,0.0001238533,0.00004060397,0.00004802163,0.00002917898,0.00001752363,0.0002735976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.543962,"threshold_uncertainty_score":0.554912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04843698902770568,"score_gpt":0.2588117446673414,"score_spread":0.2103747556396357,"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."}}