{"id":"W4409838775","doi":"10.1101/2025.04.22.650100","title":"Automating the Curation of DNA Barcode Databases for Vascular Plants","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Barcode; Data curation; Database; Computer science; World Wide Web; Operating system","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":[0.01073078,0.001280619,0.001469835,0.00598806,0.001921596,0.005100343,0.002467029,0.0011035,0.004325259],"category_scores_gemma":[0.02630003,0.001212702,0.001461062,0.003681808,0.0008606841,0.002145037,0.003889445,0.002561324,0.009345422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001338083,"about_ca_system_score_gemma":0.004268301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003941878,"about_ca_topic_score_gemma":0.005048015,"domain_scores_codex":[0.9940084,0.001276244,0.0007438685,0.001660311,0.001939706,0.0003713565],"domain_scores_gemma":[0.9797899,0.00698509,0.002189023,0.005409773,0.004874308,0.0007519006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005974149,0.0003125232,0.010987,0.002734052,0.000278519,0.0008949223,0.003273724,0.004234256,0.3264009,0.009551777,0.05971549,0.5810194],"study_design_scores_gemma":[0.0001222891,0.0002367551,0.02765944,0.0010566,0.0002305805,0.002106237,0.001547753,0.05756717,0.4975173,0.02564185,0.385885,0.0004289903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0280563,0.001151304,0.9156204,0.0007980973,0.0003543419,0.0009915339,0.009459085,0.04132834,0.002240678],"genre_scores_gemma":[0.03705537,0.0006978695,0.9350612,0.0003533999,0.00009447651,0.0006528046,0.01889107,0.004751535,0.002442352],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01073078,"threshold_uncertainty_score":0.05675054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01671226892888942,"score_gpt":0.2409338317547196,"score_spread":0.2242215628258302,"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."}}