{"id":"W4376209468","doi":"10.3897/bdj.11.e100677","title":"A workflow for expanding DNA barcode reference libraries through ‘museum harvesting’ of natural history collections","year":2023,"lang":"en","type":"article","venue":"Biodiversity Data Journal","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Ontario Ministry of Research, Innovation and Science; Ontario Genomics; Genome Canada; Gordon and Betty Moore Foundation; University of Guelph; Smithsonian Institution","keywords":"Barcode; DNA barcoding; Workflow; National Museum of Natural History; Biology; DNA sequencing; Biodiversity; Natural history; World Wide Web; Computational biology; Computer science; Evolutionary biology; Database; DNA; Ecology; Genetics","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002741231,0.0001655386,0.0002120419,0.0001013567,0.001328588,0.00006897109,0.001092245,0.00007281367,0.0009258346],"category_scores_gemma":[0.0002161311,0.0001664464,0.00008290977,0.0003973867,0.0006855592,0.00170684,0.002340054,0.0002445185,0.0003296009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005616035,"about_ca_system_score_gemma":0.00002220724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002912098,"about_ca_topic_score_gemma":0.00006093513,"domain_scores_codex":[0.9985694,0.00005816423,0.0002223868,0.0003868337,0.0004026743,0.0003605162],"domain_scores_gemma":[0.9990861,0.0001757855,0.0002219786,0.0004025272,0.00001289736,0.0001007026],"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":[0.00006939795,0.00005321328,0.1419281,0.00001571704,0.00006739159,0.00001559229,0.001074434,0.0000405502,0.003147713,0.000010408,0.8531925,0.0003849672],"study_design_scores_gemma":[0.001553652,0.0002295829,0.2924717,0.00007871718,0.0002138415,0.00005325831,0.004584961,0.0003015476,0.001880255,0.0004226331,0.6976214,0.0005884427],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9741955,0.001257001,0.0016886,0.002448892,0.003686639,0.0009632235,0.008298806,0.000369045,0.007092236],"genre_scores_gemma":[0.6034376,0.006968169,0.3457211,0.001961181,0.0006421783,0.00002653387,0.003863011,0.00007562987,0.03730465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.370758,"threshold_uncertainty_score":0.9999875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1169619299390061,"score_gpt":0.2666315987921832,"score_spread":0.1496696688531771,"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."}}