{"id":"W4398774261","doi":"10.21203/rs.3.rs-4411399/v1","title":"Machine learning applied to global scale species distribution models (SDMs)","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Fisheries and Oceans Canada","funders":"","keywords":"Scale (ratio); Distribution (mathematics); Computer science; Artificial intelligence; Environmental science; Geography; Mathematics; Cartography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00112769,0.000339877,0.0003280576,0.00007650461,0.0004265926,0.0004758435,0.0007216915,0.0003206665,0.04105336],"category_scores_gemma":[0.0001143934,0.0003211391,0.0001850334,0.001077494,0.0003297044,0.00006212059,0.007504108,0.001704911,0.01508587],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005585577,"about_ca_system_score_gemma":0.00006292892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001279417,"about_ca_topic_score_gemma":0.001508717,"domain_scores_codex":[0.9955304,0.0001919464,0.0003173917,0.001057268,0.001918175,0.0009848308],"domain_scores_gemma":[0.9987429,0.00005984196,0.00005298273,0.0006040717,0.00007601212,0.0004642134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007740007,0.001252141,0.03892244,0.002936507,0.0002121815,0.0002439974,0.003601033,0.09028479,0.005831987,0.2451497,0.5824836,0.02830761],"study_design_scores_gemma":[0.0009143975,0.000479079,0.1000953,0.0009018136,0.00008357927,0.00002286949,0.01014912,0.03698307,0.001942684,0.1221703,0.72398,0.002277781],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2806832,0.0008757296,0.001768401,0.003602735,0.0005211302,0.002041719,0.01028652,0.0005536316,0.6996669],"genre_scores_gemma":[0.9902796,0.0003518277,0.00005260856,0.00005411889,0.0001666598,0.0003219155,0.003808744,0.00003514815,0.004929403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7095963,"threshold_uncertainty_score":0.9999241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0777150413071329,"score_gpt":0.3565355193900849,"score_spread":0.278820478082952,"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."}}