{"id":"W4413334435","doi":"10.1186/s12862-025-02425-4","title":"NCBITaxonomy.jl: rapid biological names finding and reconciliation","year":2025,"lang":"en","type":"article","venue":"BMC Ecology and Evolution","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université du Québec","funders":"Natural Sciences and Engineering Research Council of Canada; Courtois Foundation; Institut de Valorisation des Données; Compute Canada; National Science Foundation","keywords":"Workflow; Computer science; Standardization; Approximate string matching; Database; Information retrieval; Programming language; Data mining; Pattern matching","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":[],"consensus_categories":[],"category_scores_codex":[0.0001663998,0.00008103735,0.0001024497,0.00003806571,0.0001670421,0.000007807867,0.00003559123,0.0001708466,0.000004963616],"category_scores_gemma":[0.0001124253,0.00007482265,0.00002408504,0.00003549106,0.0001126369,9.11743e-7,0.00008987581,0.0000407818,0.000001779953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001550229,"about_ca_system_score_gemma":0.00004054055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007564927,"about_ca_topic_score_gemma":0.0001572454,"domain_scores_codex":[0.9994475,0.00005572779,0.0001145612,0.0002370582,0.00001406081,0.000131051],"domain_scores_gemma":[0.9997957,0.00003640696,0.00003810606,0.00007828644,0.00002885764,0.00002262799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006105522,0.00001579701,0.9472278,0.00001885414,0.0000399893,1.680951e-7,0.00002235845,0.00001271572,0.04764561,0.001726004,0.0006372153,0.002592455],"study_design_scores_gemma":[0.0003637585,0.0001897699,0.9849769,0.000004069104,0.00001524254,0.000005400988,0.0001164043,0.0001219775,0.001245505,0.00165793,0.01121616,0.00008683506],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912791,0.006238608,0.0010264,0.0001724891,0.0002130849,0.0001238384,0.000005473135,0.000004018436,0.0009369956],"genre_scores_gemma":[0.9971851,0.001409534,0.0008828389,0.000145424,0.00006565954,0.00002846894,0.00001616881,0.00000251385,0.0002643472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0464001,"threshold_uncertainty_score":0.3051179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02031407934474265,"score_gpt":0.2386917284939391,"score_spread":0.2183776491491965,"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."}}