{"id":"W4303986904","doi":"10.3897/bdj.10.e86089","title":"The disambiguation of people names in biological collections","year":2022,"lang":"en","type":"article","venue":"Biodiversity Data Journal","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada; McGill University","funders":"Horizon 2020 Framework Programme; Fonds Wetenschappelijk Onderzoek; Vlaamse regering; European Commission; Vlaamse Overheid; European Cooperation in Science and Technology; National Science Foundation","keywords":"Computer science; Information retrieval; Natural language processing; World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003119037,0.00004181933,0.00005464453,0.00004186526,0.0009460107,0.00002605204,0.0004812269,0.00003237094,0.0001501386],"category_scores_gemma":[0.00007482584,0.00003400177,0.00003239472,0.0001802448,0.0000518639,0.000005299692,0.0007172214,0.000115134,0.000001689717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000016394,"about_ca_system_score_gemma":0.0000525892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007507139,"about_ca_topic_score_gemma":0.0001737638,"domain_scores_codex":[0.9994339,0.000127449,0.0001034342,0.0001146539,0.0001335048,0.00008707341],"domain_scores_gemma":[0.99962,0.00001406136,0.00009069048,0.000212517,0.00003556524,0.00002717153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003088027,0.00009820496,0.8107805,0.000002849552,0.0000660795,0.000004206429,0.0003874925,0.001126562,0.006626186,0.00005574301,0.1784794,0.002064022],"study_design_scores_gemma":[0.0009758857,0.0003041973,0.5397975,0.000001686509,0.0000255232,0.0001170466,0.005732,0.000108144,0.0006402832,0.0001937341,0.4519647,0.0001392501],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978228,0.0002601213,0.0001849135,0.0004797053,0.0002735451,0.00005918976,0.0007983743,0.0000016337,0.0001197602],"genre_scores_gemma":[0.9986526,0.0002833004,0.0001746981,0.00006369888,0.0000356174,5.095114e-7,0.0006148395,8.813504e-7,0.0001738733],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2734853,"threshold_uncertainty_score":0.7276045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04375251760692121,"score_gpt":0.2528607193802292,"score_spread":0.2091082017733081,"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."}}