{"id":"W4366827604","doi":"10.3897/bdj.11.e100904","title":"Enhancing DNA barcode reference libraries by harvesting terrestrial arthropods at the Smithsonian's National Museum of Natural History","year":2023,"lang":"en","type":"article","venue":"Biodiversity Data Journal","topic":"Lepidoptera: Biology and Taxonomy","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Genomics; Genome Canada; Gordon and Betty Moore Foundation; Canada First Research Excellence Fund; Ontario Ministry of Research, Innovation and Science; U.S. Department of Agriculture; University of Guelph; Smithsonian Institution","keywords":"Barcode; GenBank; Biodiversity; Sanger sequencing; DNA barcoding; National Museum of Natural History; Biology; DNA sequencing; Taxon; Sequence (biology); Natural history; Ecology; Geography; Computer science; DNA","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":[],"consensus_categories":[],"category_scores_codex":[0.0004586247,0.000121413,0.0001238027,0.00005147002,0.0004021018,0.00003549778,0.0007363529,0.0001262372,0.0001109095],"category_scores_gemma":[0.000437679,0.00009364792,0.00005961979,0.00006693016,0.0003788585,0.00005314788,0.0009789023,0.0002547491,0.00004416036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006990767,"about_ca_system_score_gemma":0.0003066523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006959608,"about_ca_topic_score_gemma":0.0001366433,"domain_scores_codex":[0.9989609,0.0001461368,0.0002081979,0.0002730731,0.0001902048,0.0002214722],"domain_scores_gemma":[0.9992532,0.00008025282,0.0002243878,0.0003114321,0.00006339184,0.00006729762],"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":[0.0003844775,0.00004825848,0.03877903,0.00001603399,0.0002469998,0.00002103126,0.0001904515,0.000006992107,0.06670316,0.00002047645,0.8889804,0.004602696],"study_design_scores_gemma":[0.0006188875,0.00009082989,0.003920517,0.00001976366,0.00002991059,0.00005983867,0.0001756321,0.00003098874,0.01573607,0.00001375727,0.9791348,0.0001690028],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841877,0.003371267,0.0003697945,0.003537789,0.002190377,0.0001793093,0.003234721,0.00003753084,0.002891487],"genre_scores_gemma":[0.9953949,0.000350402,0.0006034236,0.0003898232,0.0004394467,0.000001023341,0.00199683,0.000004751751,0.0008193929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0901544,"threshold_uncertainty_score":0.3818851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05960109353813276,"score_gpt":0.2502321594045084,"score_spread":0.1906310658663756,"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."}}