{"id":"W2951013216","doi":"10.1038/s41598-018-22505-4","title":"Automated high throughput animal CO1 metabarcode classification","year":2018,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":177,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Ontario Forest Research Institute; Natural Resources Canada","funders":"Government of Canada","keywords":"Classifier (UML); Barcode; DNA barcoding; Biological classification; Biodiversity; Computer science; Taxonomic rank; Biota; Biology; Artificial intelligence; Machine learning; Data mining; Ecology; Evolutionary biology","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007653029,0.0001792404,0.0001658042,0.00005176661,0.001007167,0.0001445375,0.0002523502,0.00007056998,0.003442659],"category_scores_gemma":[0.00007247274,0.0001636324,0.00006910128,0.0004978314,0.00244977,0.0004415525,0.0005324624,0.00008342126,0.004952988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002726145,"about_ca_system_score_gemma":0.000007409937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002004452,"about_ca_topic_score_gemma":0.00006707996,"domain_scores_codex":[0.9974054,0.00005192591,0.0003467777,0.001014827,0.0007869259,0.0003941285],"domain_scores_gemma":[0.9987687,0.00001791911,0.0002457785,0.0008276961,0.00002028624,0.0001196278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001118757,0.0001407551,0.4597352,0.000004193724,0.00002654592,0.00009122845,0.000586961,0.00002542808,0.2956401,0.00006474625,0.2429248,0.0007488268],"study_design_scores_gemma":[0.0001109524,0.00008216731,0.8627644,0.000006566021,0.00003637051,0.00006265265,0.0002105025,0.0009324523,0.05809589,0.001024098,0.07640552,0.0002684816],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9828377,0.00002055787,0.00008210497,0.0003099293,0.003038293,0.0002750508,0.000007278786,0.0004003306,0.01302869],"genre_scores_gemma":[0.9881662,0.000004622259,0.008011117,0.00008965594,0.00006126286,0.0000118614,0.00004078322,0.00001191422,0.00360262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4030292,"threshold_uncertainty_score":0.9974684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02316163589301985,"score_gpt":0.246137571206475,"score_spread":0.2229759353134552,"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."}}