{"id":"W4309625182","doi":"10.1038/s41597-022-01812-6","title":"An expert curated global legume checklist improves the accuracy of occurrence, biodiversity and taxonomic data","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Plant and Fungal Species Descriptions","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Université de Montréal; Royal Botanical Gardens, Kew","keywords":"Checklist; Taxon; Taxonomic rank; Biodiversity; Biology; Global biodiversity; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03744607,0.001181548,0.001294337,0.03477034,0.003001625,0.004624002,0.003176166,0.001282259,0.02062194],"category_scores_gemma":[0.09313104,0.0006708474,0.0009711611,0.01603439,0.001076794,0.004090332,0.005743454,0.002043664,0.0121245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003361061,"about_ca_system_score_gemma":0.015389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01658953,"about_ca_topic_score_gemma":0.0330466,"domain_scores_codex":[0.9762824,0.00817543,0.004790342,0.001933929,0.007859303,0.0009585097],"domain_scores_gemma":[0.8426625,0.02074204,0.01668039,0.02231004,0.09196902,0.005636064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003301286,0.0001984583,0.0437904,0.004586087,0.000165872,0.0009948527,0.005515058,0.0008676983,0.02378821,0.0067437,0.4790177,0.4340018],"study_design_scores_gemma":[0.00005029865,0.00009266198,0.05994301,0.002386066,0.0001073233,0.0006247087,0.00183868,0.00109634,0.003687263,0.002366114,0.9276642,0.0001432826],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1365082,0.008145636,0.277292,0.01759504,0.01005926,0.009152693,0.4025517,0.01962121,0.1190743],"genre_scores_gemma":[0.09178317,0.002475652,0.5891775,0.003336525,0.0009655341,0.004259035,0.286642,0.004157688,0.0172029],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03744607,"threshold_uncertainty_score":0.1980361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06531958014189927,"score_gpt":0.2958452711767843,"score_spread":0.2305256910348851,"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."}}