{"id":"W4379874857","doi":"10.1371/journal.pone.0286620","title":"Interrogating 1000 insect genomes for NUMTs: A risk assessment for estimates of species richness","year":2023,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Canada Research Chairs; Government of Canada; Ontario Genomics; Genome Canada","keywords":"Species richness; Biology; Indel; Amplicon; DNA barcoding; Mitochondrial DNA; Genome; Evolutionary biology; Barcode; Phylogenetic tree; Phylogenetics; Genetics; Gene; Ecology; Polymerase chain reaction","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002580726,0.0001384742,0.0002547255,0.00004517868,0.0002632958,0.00001702813,0.0002333994,0.00003915117,0.0002707081],"category_scores_gemma":[0.0001304969,0.0001342843,0.00008783526,0.000166126,0.0002388694,0.0001315516,0.0004279045,0.00006005665,0.0001173906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002128483,"about_ca_system_score_gemma":0.000002355436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003739429,"about_ca_topic_score_gemma":0.00003134546,"domain_scores_codex":[0.9989167,0.00001797674,0.0002168943,0.0002815648,0.0002965955,0.0002702132],"domain_scores_gemma":[0.9992066,0.0004053226,0.0001618528,0.0001757415,0.00001004451,0.00004045398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002568402,0.0004426437,0.9397786,0.0001670182,0.0002204328,6.684119e-7,0.001368451,0.0002020349,0.05616396,0.00002563846,0.0008805771,0.0007243436],"study_design_scores_gemma":[0.0007701492,0.0004739946,0.8799732,0.0001014015,0.0002697898,2.252176e-7,0.003151941,0.004895478,0.1086334,0.00100801,0.0004430546,0.000279381],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966379,0.00004563668,0.0006020272,0.0001947691,0.00004047514,0.0008202191,0.0004032643,0.00008189317,0.001173827],"genre_scores_gemma":[0.8666754,0.0002232078,0.1319916,0.00003704632,0.00003244375,0.0002328856,0.00005558357,0.0000198778,0.0007319173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1313896,"threshold_uncertainty_score":0.5475954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06761399588525092,"score_gpt":0.2531413775599322,"score_spread":0.1855273816746813,"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."}}