{"id":"W2020251668","doi":"10.1080/00045608.2014.910072","title":"Predicting Functional Role and Occurrence of Whitebark Pine ( <i>Pinus albicaulis</i> ) at Alpine Treelines: Model Accuracy and Variable Importance","year":2014,"lang":"en","type":"article","venue":"Annals of the Association of American Geographers","topic":"Forest ecology and management","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Parks Canada; National Science Foundation","keywords":"Variable (mathematics); Tree (set theory); Random forest; Keystone species; Ecology; Geography; Computer science; Mathematics; Artificial intelligence; Biology; Habitat","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006094613,0.00009395438,0.0002157625,0.00003300123,0.00009180969,0.00000409902,0.0001465067,0.00003676796,0.00006832757],"category_scores_gemma":[0.0004062585,0.00007812717,0.00006247767,0.000349968,0.0004125892,0.0001321717,0.000212351,0.00006143197,8.645001e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001915487,"about_ca_system_score_gemma":0.000008714233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004890658,"about_ca_topic_score_gemma":0.0002690204,"domain_scores_codex":[0.9990088,0.00006913758,0.0003018422,0.0001887517,0.000263864,0.0001675601],"domain_scores_gemma":[0.9985909,0.0001726644,0.0009666574,0.0001795973,0.00004656763,0.00004362901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003316408,0.00005206629,0.9725266,0.00001159051,0.00007192093,1.855555e-8,0.0001153006,0.01880037,0.0007478581,0.0002308793,0.00597582,0.001434476],"study_design_scores_gemma":[0.000315369,0.0001412493,0.9790401,0.00001484064,0.00005195399,3.95009e-7,0.0001477897,0.01582601,0.0005459813,0.002527976,0.001298033,0.00009030757],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955766,0.00007867059,0.0005332286,0.001193396,0.00004567854,0.0001449573,0.00004297964,0.000009928688,0.002374617],"genre_scores_gemma":[0.9982152,0.0001935324,0.0007017356,0.0006468558,0.000008843257,0.000008194137,0.000009149147,0.000004175105,0.0002123239],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006513564,"threshold_uncertainty_score":0.3185933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007760817247963454,"score_gpt":0.2196859521686856,"score_spread":0.2119251349207221,"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."}}