{"id":"W2745161505","doi":"10.12705/664.9","title":"Building the “Plant Glossary”—A controlled botanical vocabulary using terms extracted from the Floras of North America and China","year":2017,"lang":"en","type":"article","venue":"Taxon","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"National Science Foundation","keywords":"Glossary; Categorization; Vocabulary; Taxon; Synonym (taxonomy); Computer science; Taxonomic rank; Natural language processing; Term (time); Set (abstract data type); Linguistics; Artificial intelligence; Interpretation (philosophy); Ecology; Biology","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":[0.007105765,0.0007732032,0.0008971487,0.02250206,0.002442354,0.003005976,0.001562495,0.000766322,0.003975964],"category_scores_gemma":[0.01949245,0.0006864449,0.001364665,0.01450107,0.001369067,0.006176132,0.004527033,0.001957237,0.001161823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003281411,"about_ca_system_score_gemma":0.008444892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04600971,"about_ca_topic_score_gemma":0.05664204,"domain_scores_codex":[0.9950386,0.0009985295,0.001788883,0.0008928875,0.00107158,0.0002094965],"domain_scores_gemma":[0.9844669,0.006099966,0.001542015,0.002707098,0.004688329,0.0004957972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003149247,0.0004244676,0.06389033,0.009524072,0.0005941226,0.001854351,0.04197261,0.007555096,0.09242376,0.09362417,0.1396776,0.5481445],"study_design_scores_gemma":[0.0001203374,0.0001661225,0.09691285,0.005120609,0.0006262528,0.0008118191,0.02106515,0.02947318,0.01811924,0.01884012,0.8083165,0.0004277759],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3176253,0.004042365,0.4422189,0.004925729,0.001004369,0.008296257,0.1671865,0.005804555,0.04889604],"genre_scores_gemma":[0.2295395,0.001415759,0.5475318,0.0006911934,0.0001549364,0.006363654,0.2083268,0.001354417,0.00462195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04600971,"threshold_uncertainty_score":0.09148383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02429857359007057,"score_gpt":0.2736396031255826,"score_spread":0.249341029535512,"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."}}