{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001122185,0.0001824629,0.0003749264,0.00005713736,0.0006094255,0.00007636998,0.0001744486,0.00003840254,0.00001765521],"category_scores_gemma":[0.0001415627,0.0001120166,0.00006128539,0.0003421414,0.00199181,0.0005341074,0.001322241,0.0001661367,0.000003330691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005259226,"about_ca_system_score_gemma":0.000004126345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007600935,"about_ca_topic_score_gemma":0.000002963465,"domain_scores_codex":[0.9984627,0.0003369298,0.0003268811,0.0003766919,0.0002312993,0.0002655265],"domain_scores_gemma":[0.9990039,0.0005607316,0.0001625267,0.0002157322,0.00000388594,0.0000532205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005287219,0.0000258251,0.9786946,0.00004215704,0.0001962084,0.000008191931,0.00401842,0.0002075489,0.01511984,0.000965976,0.00008946812,0.0005789658],"study_design_scores_gemma":[0.001857412,0.00002106004,0.9532998,0.00006289596,0.0003988793,0.00006290657,0.02975771,0.00477457,0.003707465,0.002113415,0.003553061,0.000390834],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950719,0.002846651,0.00001239164,0.001107351,0.00007921603,0.0002640747,0.000008764062,0.00002417846,0.0005854323],"genre_scores_gemma":[0.9852644,0.01040506,0.003753878,0.0001202349,0.00001784066,0.00001297583,0.000002011619,0.00001210432,0.0004114539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02573929,"threshold_uncertainty_score":0.7338907,"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."}}