{"id":"W3098382762","doi":"10.3897/biss.4.58482","title":"Improving Taxonomic Name Finding in the Biodiversity Heritage Library","year":2020,"lang":"en","type":"article","venue":"Biodiversity Information Science and Standards","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"World Wide Web; Index (typography); Biodiversity; Realm; Computer science; Quarter (Canadian coin); Taxon; Geography; Library science; Information retrieval; History; Biology; Archaeology; Ecology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007856305,0.00007011079,0.00006578945,0.00004995126,0.0006100932,0.0003359251,0.0003885448,0.0000304848,0.004441105],"category_scores_gemma":[0.0001522315,0.00005571239,0.00002139964,0.0006189051,0.0004055744,0.004473052,0.0004009023,0.00008463271,0.0007319495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004032739,"about_ca_system_score_gemma":0.00006728115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001136535,"about_ca_topic_score_gemma":0.00001529605,"domain_scores_codex":[0.9987615,0.00001717477,0.000111117,0.0001291423,0.0007904265,0.0001906263],"domain_scores_gemma":[0.999703,0.00001347701,0.00006762386,0.00008365793,0.00003072607,0.0001015156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001297639,0.00003443378,0.5878971,0.00004187716,0.000003706505,0.00001089322,0.03079046,0.00003021052,0.0006580253,0.0008504264,0.3700878,0.009465274],"study_design_scores_gemma":[0.0007791689,0.0001125379,0.3280355,0.000002939809,0.000007395364,0.000003784748,0.07354053,0.0006165943,0.0005157784,0.000005506025,0.596129,0.0002512982],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.972501,0.000007492851,0.00007236741,0.00512876,0.00004924824,0.0001545699,0.001077427,0.0000347868,0.0209743],"genre_scores_gemma":[0.9951476,0.00003813723,0.00003358512,0.004750249,0.000003729097,0.00000103737,0.00002392379,2.833839e-7,0.000001498558],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2598616,"threshold_uncertainty_score":0.996469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02885904720582254,"score_gpt":0.2164791996118864,"score_spread":0.1876201524060638,"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."}}