{"id":"W2808957904","doi":"10.1101/353904","title":"Over 2.5 million COI sequences in GenBank and growing","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Ontario Forest Research Institute; Natural Resources Canada","funders":"","keywords":"GenBank; Barcode; Usability; Biology; DNA barcoding; Annotation; Evolutionary biology; Information retrieval; Computer science; Bioinformatics; Genetics; Gene","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004630221,0.000468744,0.0004038363,0.0001260126,0.0002379688,0.00009966927,0.0004895487,0.0003712862,0.0004163761],"category_scores_gemma":[0.00005537758,0.0005067335,0.0000749013,0.0002879078,0.0008717812,0.0003731834,0.002386862,0.0004656889,0.0003866671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007423665,"about_ca_system_score_gemma":0.00001634385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006338042,"about_ca_topic_score_gemma":0.00002433362,"domain_scores_codex":[0.9974304,0.0001022582,0.0003412505,0.001130958,0.0004722409,0.0005228199],"domain_scores_gemma":[0.9989415,0.00004564977,0.0002081384,0.000619248,0.00001214025,0.0001733109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009679484,0.00005104359,0.7805141,0.00005976416,0.00003201623,0.00004898614,0.0000351105,0.00008021792,0.2183185,0.000009324979,0.0008400548,0.000001227218],"study_design_scores_gemma":[0.0002878219,0.00004305554,0.9566355,0.0001598654,0.00004215684,1.479439e-8,0.00001056544,0.0001687993,0.03909947,0.000004992169,0.002936268,0.0006114788],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978824,0.0005912483,0.00001885663,0.0001742899,0.000616041,0.0004447891,0.00009561593,0.0001042693,0.00007244143],"genre_scores_gemma":[0.993145,0.001150616,0.005156278,0.0003343955,0.0001164054,0.00004499072,1.965334e-7,0.000041775,0.00001027435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.179219,"threshold_uncertainty_score":0.9997385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0126975722614055,"score_gpt":0.2019542162686835,"score_spread":0.189256644007278,"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."}}