{"id":"W4240491097","doi":"10.1101/738138","title":"Forensics and DNA Barcodes – Do Identification Errors Arise in the Lab or in the Sequence Libraries?","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Lepidoptera: Biology and Taxonomy","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"DNA barcoding; GenBank; Workflow; Identification (biology); Barcode; Taxonomy (biology); Data science; Sequence (biology); Information retrieval; Computer science; Biology; Evolutionary biology; Database; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06391659,0.001019152,0.002248819,0.003942106,0.002293373,0.007373444,0.003266081,0.006046365,0.005072882],"category_scores_gemma":[0.1684705,0.0007757055,0.0006601281,0.005113637,0.01247764,0.01208602,0.003552913,0.005793016,0.003457601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002548686,"about_ca_system_score_gemma":0.002265471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001605697,"about_ca_topic_score_gemma":0.00116226,"domain_scores_codex":[0.9315302,0.02860188,0.005181197,0.00864071,0.0239783,0.002067779],"domain_scores_gemma":[0.8317916,0.09489985,0.02443459,0.02494523,0.02239029,0.001538433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008437263,0.0004199739,0.07265104,0.003585428,0.0004706836,0.002845058,0.009036316,0.002399903,0.02669205,0.1731247,0.0551949,0.6527362],"study_design_scores_gemma":[0.00007315061,0.0004431064,0.05059612,0.007878721,0.0002502317,0.009912512,0.009256515,0.01296391,0.1066576,0.3665171,0.4349077,0.0005434026],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2071717,0.1157288,0.4340677,0.1876853,0.01636762,0.000397832,0.001847967,0.002154362,0.03457873],"genre_scores_gemma":[0.711727,0.03621355,0.1807368,0.0455953,0.006177327,0.0003952396,0.002047595,0.002281143,0.01482604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06391659,"threshold_uncertainty_score":0.3380272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02295119989697971,"score_gpt":0.2365313090072384,"score_spread":0.2135801091102587,"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."}}