{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009366008,0.0005876272,0.0008623181,0.008689263,0.001357897,0.003610123,0.001651078,0.001212097,0.005540635],"category_scores_gemma":[0.02340463,0.0004546575,0.0007121775,0.01863106,0.001107945,0.003915798,0.002255859,0.002275243,0.004745995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001559917,"about_ca_system_score_gemma":0.002665249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005991355,"about_ca_topic_score_gemma":0.008572357,"domain_scores_codex":[0.9929387,0.00103313,0.0009185286,0.001811272,0.002974251,0.0003241345],"domain_scores_gemma":[0.9676844,0.007301689,0.007996666,0.003983901,0.01117393,0.001859387],"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":[0.0009291873,0.0001497046,0.1250903,0.008716484,0.0003732255,0.002274145,0.005833407,0.001147612,0.1002461,0.01184508,0.09346997,0.6499248],"study_design_scores_gemma":[0.00002485393,0.0001963373,0.1316207,0.002885529,0.0002375587,0.002930194,0.002487634,0.002098726,0.01799586,0.003939297,0.8354235,0.0001596461],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4608864,0.1451264,0.09792534,0.02778499,0.007163348,0.0006371055,0.1872403,0.01087077,0.06236543],"genre_scores_gemma":[0.3517255,0.05818529,0.2360476,0.009879874,0.003103957,0.0006122572,0.3187253,0.00228103,0.01943935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009366008,"threshold_uncertainty_score":0.04953277,"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."}}