{"id":"W4412707418","doi":"10.1101/2025.07.21.665927","title":"Megabarcoding dark taxa – Assessing the utility of mass DNA barcoding for phorid fly species discovery","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Forest Insect Ecology and Management","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Phoridae; DNA barcoding; Biology; Taxon; Identification (biology); Evolutionary biology; Zoology; Ecology","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":[0.006939482,0.0005979129,0.0006007723,0.003745526,0.0009262176,0.001926595,0.00138093,0.001356539,0.00208519],"category_scores_gemma":[0.01651728,0.0004353479,0.0006884017,0.001587147,0.000818633,0.001845072,0.002065038,0.0009089061,0.001486833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004280848,"about_ca_system_score_gemma":0.0005429307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001573176,"about_ca_topic_score_gemma":0.004438015,"domain_scores_codex":[0.9960327,0.001047643,0.0002846653,0.001180848,0.00115336,0.0003008317],"domain_scores_gemma":[0.988619,0.005686741,0.002100925,0.00100155,0.001975963,0.0006158067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008961876,0.0001999571,0.6876138,0.00159253,0.0008811751,0.0004798946,0.001537235,0.004230205,0.1541009,0.001905769,0.003712238,0.1428501],"study_design_scores_gemma":[0.00008226551,0.001795315,0.7056785,0.0007592215,0.001273067,0.002415331,0.003396335,0.1114948,0.1423685,0.005267956,0.02520928,0.0002595272],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9243737,0.003895755,0.05712658,0.0005463153,0.0001777961,0.0002992201,0.008182743,0.001043223,0.004354762],"genre_scores_gemma":[0.862773,0.0006841971,0.1286563,0.0002991651,0.00005188249,0.0002413969,0.006385412,0.0001543995,0.0007544176],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006939482,"threshold_uncertainty_score":0.03669995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01804617121596902,"score_gpt":0.2375549370989772,"score_spread":0.2195087658830082,"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."}}