{"id":"W4409626647","doi":"10.32942/x2dg9k","title":"BOLDistilled: Comprehensive but compact DNA barcode reference libraries","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Government of Canada; Ontario Genomics; Genome Canada","keywords":"Barcode; DNA barcoding; Computer science; Biology; Evolutionary biology; Operating system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004068582,0.001657444,0.001492768,0.004278903,0.001484594,0.004387574,0.003987586,0.001972558,0.0168918],"category_scores_gemma":[0.01546925,0.002331135,0.001941657,0.003603673,0.0008205348,0.002580732,0.003871031,0.003496725,0.02393573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001157578,"about_ca_system_score_gemma":0.002444741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001924533,"about_ca_topic_score_gemma":0.004238811,"domain_scores_codex":[0.9962451,0.000632945,0.0004389368,0.0009740349,0.001370912,0.0003380748],"domain_scores_gemma":[0.9935666,0.001440846,0.0007900169,0.001896867,0.001870634,0.0004350074],"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":[0.00196515,0.0005645532,0.006650765,0.002588313,0.0003649853,0.001148562,0.001800123,0.01521368,0.4663796,0.0304196,0.1233721,0.3495326],"study_design_scores_gemma":[0.0002290646,0.0005412375,0.004179277,0.0004489514,0.0002305846,0.001138656,0.0002238578,0.03196778,0.4734997,0.0106296,0.4765027,0.0004087929],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.02867903,0.001129141,0.8530896,0.0006564279,0.0006195347,0.001397404,0.05479699,0.04903053,0.01060136],"genre_scores_gemma":[0.02938953,0.000596988,0.8495612,0.0005460978,0.0001070416,0.001414838,0.09827184,0.009217783,0.01089467],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.0168918,"threshold_uncertainty_score":0.05650872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03924047314248855,"score_gpt":0.2455753096631494,"score_spread":0.2063348365206609,"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."}}