{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002560115,0.0000775477,0.00009443769,0.00001629055,0.00004235423,0.00004342819,0.0002457087,0.00009553973,0.00001424244],"category_scores_gemma":[0.0002340184,0.0000451325,0.00001650397,0.0001488856,0.00008301144,0.00000907291,0.00005242629,0.0001378812,0.000009492403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003078232,"about_ca_system_score_gemma":0.00002666371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001142002,"about_ca_topic_score_gemma":0.00002113332,"domain_scores_codex":[0.9992657,0.0001850378,0.0001537012,0.0002203117,0.000063249,0.000112029],"domain_scores_gemma":[0.9996371,0.00004513302,0.00005404316,0.0002272339,0.00001555479,0.00002096208],"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":[0.001482626,0.001831627,0.3951549,0.0005060388,0.0003727828,0.0001524941,0.01257016,0.0000152757,0.5666783,0.003479353,0.003040382,0.01471609],"study_design_scores_gemma":[0.007467053,0.003543848,0.2286241,0.0007890587,0.0006590702,0.000114626,0.01007969,0.002636499,0.4461213,0.003766161,0.2935742,0.002624297],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877255,0.001193687,0.00003463217,0.008783902,0.000009142186,0.0003432143,0.00001673305,0.000005889643,0.001887315],"genre_scores_gemma":[0.9950667,0.0004134229,0.0002171061,0.004028871,0.00009471241,0.00005532445,0.00008514372,0.000004359809,0.00003434244],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2905339,"threshold_uncertainty_score":0.184045,"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."}}