{"id":"W4321616577","doi":"10.3897/mbmg.7.98539","title":"Maximizing the reliability and the number of species assignments in metabarcoding studies using a curated regional library and a public repository","year":2023,"lang":"en","type":"article","venue":"Metabarcoding and Metagenomics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fisheries and Oceans Canada","funders":"","keywords":"Barcode; Ranking (information retrieval); Reliability (semiconductor); Taxon; Global biodiversity; Biology; Taxonomic rank; Biodiversity; Computer science; Information retrieval; Computational biology; Ecology; Data mining","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":[0.03393447,0.001635837,0.002092809,0.006044811,0.001684713,0.003319781,0.001811643,0.00177113,0.001112084],"category_scores_gemma":[0.0879463,0.001336559,0.002441544,0.005545369,0.001283551,0.003372896,0.003647742,0.00108139,0.001303058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023169,"about_ca_system_score_gemma":0.002578352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00275499,"about_ca_topic_score_gemma":0.007385704,"domain_scores_codex":[0.9674284,0.01276688,0.00426973,0.008952507,0.005551078,0.001031306],"domain_scores_gemma":[0.9454188,0.0245152,0.009476736,0.008915764,0.01091573,0.0007578909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002124951,0.0007163167,0.2337703,0.005061764,0.002530037,0.0007071454,0.003667693,0.02660316,0.4595855,0.004309199,0.003534534,0.2573894],"study_design_scores_gemma":[0.0002797746,0.001956078,0.2849532,0.001180448,0.003737747,0.001619549,0.001720927,0.1349795,0.5221321,0.008998483,0.03773989,0.0007022963],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5590497,0.003137543,0.4242771,0.0004009935,0.0001245811,0.0007798548,0.004255561,0.004235172,0.003739507],"genre_scores_gemma":[0.4360292,0.0007855629,0.5523272,0.0002162079,0.00006637855,0.0008879799,0.00774289,0.0009225049,0.001022183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03393447,"threshold_uncertainty_score":0.1794648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07443458005975473,"score_gpt":0.2615095638282685,"score_spread":0.1870749837685137,"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."}}