{"id":"W4413602327","doi":"10.1111/2041-210x.70144","title":"An active ensemble classifier for detecting animal sequences from global camera trap data","year":2025,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Assembly of First Nations; University of Guelph","funders":"H2020 European Research Council; Horizon 2020 Framework Programme; Biotieteiden ja Ympäristön Tutkimuksen Toimikunta; Grantová Agentura České Republiky","keywords":"Camera trap; Classifier (UML); Artificial intelligence; Trap (plumbing); Computer science; Pattern recognition (psychology); Ensemble learning; Geography; Biology; Ecology; Meteorology","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":[],"consensus_categories":[],"category_scores_codex":[0.0004895928,0.0000921979,0.000144723,0.00002633666,0.0001385906,0.000009350276,0.0001533115,0.0001870677,0.000001426689],"category_scores_gemma":[0.000230411,0.00009292711,0.00002134903,0.00006560124,0.00009932921,0.000002886419,0.0001270921,0.00005871281,1.581052e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003539012,"about_ca_system_score_gemma":0.00008007967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001659806,"about_ca_topic_score_gemma":0.00277535,"domain_scores_codex":[0.9990132,0.0002422197,0.0001427724,0.0004071378,0.0000183201,0.0001763589],"domain_scores_gemma":[0.9995608,0.0001062474,0.00004807332,0.0002278109,0.0000342965,0.00002279548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002969738,0.00003736054,0.155005,0.000008184239,0.00008493136,4.160658e-7,0.00005920481,0.00004783487,0.7834892,0.000344977,0.00007254665,0.06055333],"study_design_scores_gemma":[0.0005989121,0.0003904828,0.9204491,0.000005703095,0.00005343103,0.000002948916,0.00072606,0.004223127,0.05400452,0.0178549,0.001549746,0.0001410251],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9009547,0.001393565,0.09673971,0.0001216557,0.000281411,0.0001531885,0.0001152583,0.000002666884,0.0002378629],"genre_scores_gemma":[0.8681135,0.0001108396,0.1314884,0.0001010031,0.00008022662,0.00003101548,0.00005619978,0.000003265943,0.00001560211],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7654442,"threshold_uncertainty_score":0.3789458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04728257360786742,"score_gpt":0.3933588866153602,"score_spread":0.3460763130074928,"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."}}