{"id":"W4232597024","doi":"10.1101/701805","title":"A reference library for the identification of Canadian invertebrates: 1.5 million DNA barcodes, voucher specimens, and genomic samples","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada; Dalhousie University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Ontario Ministry of Research, Innovation and Science; Churchill Northern Studies Centre; Parks Canada; Ontario Genomics; Genome Canada; Gordon and Betty Moore Foundation; University of Guelph; Smithsonian Institution","keywords":"GenBank; Barcode; Biodiversity; Biology; DNA barcoding; Taxonomic rank; Genomics; Identification (biology); Geography; DNA sequencing; Global biodiversity; Evolutionary biology; Zoology; Genealogy; Genome; Ecology; Taxon; Genetics; History; Computer science; DNA; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002837072,0.0009985137,0.0009055996,0.01175317,0.00431031,0.002101547,0.00306216,0.001411827,0.01624137],"category_scores_gemma":[0.005959168,0.0007557001,0.0005535112,0.01224794,0.0008541429,0.0006592545,0.001460047,0.001299098,0.01080696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009496126,"about_ca_system_score_gemma":0.02835868,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6350703,"about_ca_topic_score_gemma":0.7957433,"domain_scores_codex":[0.9961715,0.000154945,0.0001822355,0.0005205348,0.002589097,0.0003816931],"domain_scores_gemma":[0.9946391,0.0002513715,0.0002995151,0.0007567824,0.003715923,0.0003373722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005711464,0.0003149369,0.01531193,0.001595149,0.0001429065,0.0007093911,0.001119109,0.002160017,0.2550972,0.01093367,0.215397,0.4966474],"study_design_scores_gemma":[0.0001166003,0.0001395465,0.07940958,0.000581543,0.0001905891,0.0008209287,0.0004635479,0.002683261,0.06409565,0.001791676,0.8495706,0.0001364039],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.09327041,0.007815234,0.2409986,0.002204791,0.001201419,0.003063578,0.5578158,0.01427106,0.07935905],"genre_scores_gemma":[0.05270286,0.003556547,0.3548958,0.0005638093,0.000152815,0.00114316,0.5462627,0.001735472,0.03898687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3649297,"threshold_uncertainty_score":0.7341576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02429478183659857,"score_gpt":0.1903497487577661,"score_spread":0.1660549669211676,"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."}}