{"id":"W4225286402","doi":"10.21203/rs.3.rs-1465079/v1","title":"Features of a FAIR vocabulary","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Engineering and Physical Sciences Research Council; European Commission; EOSC-Life; European Molecular Biology Laboratory","keywords":"Vocabulary; Computer science; Controlled vocabulary; Fair use; Information retrieval; Artificial intelligence; Natural language processing; Linguistics","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":[0.001138688,0.0001717311,0.0002712981,0.0001809598,0.0001315514,0.00002448944,0.0007817444,0.0005128234,0.0002448465],"category_scores_gemma":[0.0008386394,0.0001534215,0.000209287,0.0001844368,0.0004454938,5.742187e-7,0.003545056,0.001255923,0.000005901133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003600312,"about_ca_system_score_gemma":0.0004942736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001726716,"about_ca_topic_score_gemma":0.00003024125,"domain_scores_codex":[0.9975058,0.0004854984,0.0002234384,0.0005691919,0.0007939672,0.0004220685],"domain_scores_gemma":[0.9986267,0.00008240189,0.00008168755,0.000865954,0.000229159,0.000114106],"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":[0.001204966,0.00109465,0.01033952,0.005451357,0.0009269569,0.0002657595,0.001307757,0.0002668576,0.1741523,0.001093115,0.5155685,0.2883282],"study_design_scores_gemma":[0.000870845,0.00289054,0.07214732,0.000517101,0.00003411269,0.0000315751,0.003430429,0.00003330953,0.05653684,0.003021931,0.8597555,0.0007305345],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9040183,0.05657289,0.0005577534,0.002193177,0.001004168,0.001379428,0.0009388054,0.0001102283,0.03322523],"genre_scores_gemma":[0.9916651,0.001393119,0.001252795,0.00004949804,0.0003454653,0.0001922823,0.0008366965,0.00003432625,0.004230742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.344187,"threshold_uncertainty_score":0.6256345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05636369689694107,"score_gpt":0.4119136454336711,"score_spread":0.35554994853673,"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."}}