{"id":"W3017342212","doi":"10.1371/journal.pone.0231814","title":"BOLD and GenBank revisited – Do identification errors arise in the lab or in the sequence libraries?","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Lepidoptera: Biology and Taxonomy","field":"Biochemistry, Genetics and Molecular Biology","cited_by":157,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science; Canada Foundation for Innovation","keywords":"GenBank; DNA barcoding; Workflow; Identification (biology); Taxonomy (biology); Barcode; Biology; Data science; Computer science; Evolutionary biology; Information retrieval; Sequence (biology); Inference; Sequence database; DNA sequencing; Computational biology; Data mining; Ecology; Artificial intelligence; DNA; Database; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1393736,0.001154382,0.002752983,0.009731544,0.002784598,0.009396521,0.004131264,0.004595325,0.004901615],"category_scores_gemma":[0.332052,0.001205374,0.0009327271,0.01628894,0.01043118,0.01770123,0.00539034,0.009092733,0.006051846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003588627,"about_ca_system_score_gemma":0.005392224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004358536,"about_ca_topic_score_gemma":0.005167035,"domain_scores_codex":[0.8445478,0.07343356,0.02753103,0.01510856,0.03625862,0.003120395],"domain_scores_gemma":[0.6680089,0.1733571,0.04866884,0.04862009,0.05643919,0.004906006],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001915462,0.0002829642,0.03643721,0.006355874,0.0006242783,0.003035718,0.02338842,0.001008417,0.0151232,0.1424436,0.1738729,0.595512],"study_design_scores_gemma":[0.0000861187,0.0003083964,0.03642826,0.007278503,0.0002839291,0.004674447,0.010156,0.003845404,0.01529659,0.06648834,0.8545986,0.0005553871],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.09961318,0.08782611,0.2574468,0.4068263,0.08798202,0.0006726548,0.009232644,0.006247995,0.04415232],"genre_scores_gemma":[0.3590515,0.04354366,0.3205621,0.2199799,0.01719577,0.001253552,0.01103482,0.008621397,0.01875723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8606264,"threshold_uncertainty_score":0.7370868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07052865175778676,"score_gpt":0.2491634981657609,"score_spread":0.1786348464079741,"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."}}