{"id":"W4288052088","doi":"10.22541/au.165893766.64488370/v1","title":"Interrogating 1000 Insect Genomes for NUMTs: A Risk Assessment for Species Scans","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Guelph","funders":"Canada Research Chairs; Government of Canada; Ontario Genomics; Genome Canada","keywords":"Biology; Genome; Mitochondrial DNA; Evolutionary biology; Indel; Phylogenetic tree; Phylogenetics; DNA barcoding; Genetics; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02124166,0.0009262357,0.0009712443,0.005660048,0.001259672,0.002237641,0.001293961,0.002314481,0.001798741],"category_scores_gemma":[0.07402722,0.0005843836,0.002128644,0.003687737,0.001004507,0.002639236,0.002726188,0.001926575,0.0004266786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000526232,"about_ca_system_score_gemma":0.0004080515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00157484,"about_ca_topic_score_gemma":0.001763599,"domain_scores_codex":[0.9857967,0.006409393,0.001021668,0.00357735,0.002801916,0.0003928193],"domain_scores_gemma":[0.9063101,0.07522161,0.01066552,0.004328427,0.002508113,0.0009661366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006498732,0.00006462993,0.8995196,0.000595243,0.002001306,0.001237398,0.001050095,0.005814603,0.008042079,0.002504775,0.001940089,0.07658021],"study_design_scores_gemma":[0.0001061332,0.001276406,0.7473662,0.000828483,0.003671632,0.01492103,0.003263345,0.16514,0.0131375,0.02158604,0.02847916,0.0002239471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8866358,0.007481168,0.09365486,0.001680223,0.0001368844,0.0003204877,0.004847505,0.001222599,0.004020444],"genre_scores_gemma":[0.9276451,0.001156344,0.06619989,0.0004893632,0.00009413253,0.0002305101,0.003269746,0.0001874777,0.0007274932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02124166,"threshold_uncertainty_score":0.112338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03860875957428452,"score_gpt":0.2701768682089449,"score_spread":0.2315681086346604,"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."}}