{"id":"W3009357978","doi":"10.1038/s41597-019-0320-2","title":"A reference library for Canadian invertebrates with 1.5 million barcodes, voucher specimens, and DNA samples","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":110,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; Public Health Agency of Canada; University of Guelph","funders":"Nature Conservancy of Canada; Canada First Research Excellence Fund; Ontario Genomics; Ontario Ministry of Research, Innovation and Science; Government of Canada; Churchill Northern Studies Centre; University of Guelph; Ministry of Environment; Canada Foundation for Innovation; Parks Canada; Genome Canada; Gordon and Betty Moore Foundation; Natural Sciences and Engineering Research Council of Canada; Smithsonian Institution","keywords":"GenBank; Biodiversity; Barcode; Biology; DNA barcoding; Taxonomic rank; Global biodiversity; Taxonomy (biology); Environmental DNA; DNA sequencing; Zoology; Ecology; Geography; Taxon; DNA; Genetics; Computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000235287,0.0001393928,0.0001181279,0.00005603751,0.0004224607,0.0002070442,0.000796811,0.00004247911,0.004107488],"category_scores_gemma":[0.00001802735,0.0001130427,0.00001097945,0.000202664,0.0006829987,0.001052593,0.001201188,0.00006477034,0.001326457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007874436,"about_ca_system_score_gemma":0.00001969422,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.007195609,"about_ca_topic_score_gemma":0.03242068,"domain_scores_codex":[0.9984357,0.00002100333,0.00009990401,0.0008556594,0.0002436463,0.0003441351],"domain_scores_gemma":[0.9988022,0.00004108894,0.00004144433,0.0009186469,0.000003062069,0.0001934903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001532881,0.00002266995,0.6159312,0.00001665477,0.00001609994,0.000002636804,0.000191834,0.000005291706,0.005101939,0.00007776079,0.3773867,0.001231932],"study_design_scores_gemma":[0.0003079165,0.00006467175,0.341422,0.00002344283,0.00001978692,0.000003088931,0.0004788871,0.0003625504,0.002314377,0.0002402402,0.6545052,0.0002578587],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9820855,0.0001785669,0.00001671442,0.0007731002,0.000232578,0.0006388479,0.009826171,0.00004098349,0.006207598],"genre_scores_gemma":[0.9210315,0.000128276,0.04378881,0.0008847432,0.00003543806,0.00001967983,0.00905841,0.00003936656,0.02501379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2771185,"threshold_uncertainty_score":0.9994511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03989836595563699,"score_gpt":0.2084597603429137,"score_spread":0.1685613943872767,"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."}}