{"id":"W3092468001","doi":"10.1111/2041-210x.13509","title":"Exploiting the full potential of Bayesian networks in predictive ecology","year":2020,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Forest Service; Ministry of Environment; Alberta Machine Intelligence Institute; Ministry of Environment - Saskatchewan; Alberta Environment and Parks; Alberta Agriculture and Forestry; Canadian Forest Service; Ontario Ministry of Natural Resources and Forestry; Natural Resources Canada; Ministry of Natural Resources","keywords":"Covariate; Missing data; Bayesian network; Computer science; Bayesian probability; Machine learning; Probabilistic logic; Artificial intelligence; Data mining; Statistics; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007492545,0.00006163829,0.0001326001,0.00002132742,0.00006621198,0.000002896845,0.00008781811,0.0001236401,0.002022016],"category_scores_gemma":[0.0002103249,0.00005184215,0.00002167266,0.000222724,0.0002689046,0.00006321778,0.0001340375,0.0001738008,0.000009211736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002057849,"about_ca_system_score_gemma":0.000005417253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007734309,"about_ca_topic_score_gemma":0.001360528,"domain_scores_codex":[0.998862,0.0005322452,0.0001956559,0.000173804,0.00004366191,0.0001926927],"domain_scores_gemma":[0.9996641,0.0001685742,0.00007187854,0.00005767278,0.0000044276,0.00003334851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001313857,0.0000557655,0.9826296,0.000005982449,0.000005294813,0.000004821899,0.0007120779,0.008859728,0.00334471,0.0008841894,0.0002308259,0.003135633],"study_design_scores_gemma":[0.0002840823,0.0001325336,0.9127051,0.000001872148,0.00000628338,0.000005092518,0.002456971,0.08327973,0.00007594463,0.0009122196,0.00009616555,0.00004404554],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8892623,0.00007026392,0.1069902,0.00146958,0.0001777451,0.0001606656,0.000004628228,0.00001073629,0.001853921],"genre_scores_gemma":[0.9970639,0.00006017085,0.002551887,0.0002573497,0.00002589152,0.00002616093,0.000005164,0.000003011261,0.000006511768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1078015,"threshold_uncertainty_score":0.9988903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02390493668453782,"score_gpt":0.2935166226047527,"score_spread":0.2696116859202149,"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."}}