{"id":"W3011301218","doi":"10.1101/2020.03.18.997700","title":"Improving the accessibility and transferability of machine learning algorithms for identification of animals in camera trap images: MLWIC2","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Identification and Quantification in Food","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Ministry of Natural Resources and Forestry","funders":"Rocky Mountain Research Station; National Wildlife Research Center; University of Georgia Research Foundation; California Department of Fish and Wildlife; U.S. Department of Energy; U.S. Fish and Wildlife Service; U.S. Department of Agriculture; Wisconsin Department of Natural Resources; Washington Department of Fish and Wildlife; Idaho Department of Fish and Game; University of Georgia; U.S. Forest Service; Massachusetts Department of Fish and Game","keywords":"Transferability; Trap (plumbing); Identification (biology); Camera trap; Computer science; Artificial intelligence; Algorithm; Computer vision; Machine learning; Pattern recognition (psychology); Geography; Biology; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001589544,0.0002516917,0.0003973402,0.00009429257,0.00009775589,0.00007597151,0.0004422955,0.0002831393,0.000004808542],"category_scores_gemma":[0.0008418046,0.0002389101,0.0001468051,0.0002380935,0.000259449,0.0000130294,0.0001569937,0.0003230245,5.32297e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000299086,"about_ca_system_score_gemma":0.000236645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008643654,"about_ca_topic_score_gemma":0.000007537064,"domain_scores_codex":[0.997551,0.0002473445,0.000983002,0.0008492579,0.0001800779,0.0001893134],"domain_scores_gemma":[0.9977775,0.00006662287,0.0007015759,0.0008270282,0.0005591671,0.00006815996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008284978,0.00009266673,0.006089358,0.0008860807,0.00005418638,1.49151e-7,0.00003547985,0.00004094506,0.9925371,0.0001338937,0.000007998139,0.00003933293],"study_design_scores_gemma":[0.0003626152,0.00006489999,0.1530105,0.00003842239,0.00005692966,7.249298e-9,0.00001714596,0.002922646,0.8431761,0.00000393674,0.0001557125,0.0001910955],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.962055,0.001586717,0.03413824,0.000308056,0.0001858426,0.0011142,0.0005853297,0.00002566231,9.838601e-7],"genre_scores_gemma":[0.9977926,0.0002920047,0.001549856,0.00002023993,0.00007329834,0.0002222047,0.000005954766,0.00004116606,0.000002650003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.149361,"threshold_uncertainty_score":0.9742473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02452709696204013,"score_gpt":0.2698395170745896,"score_spread":0.2453124201125495,"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."}}