{"id":"W4367845327","doi":"10.31234/osf.io/rxw9b","title":"Quantifying informativeness of names in visual space","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Agencia Estatal de Investigación; Natural Sciences and Engineering Research Council of Canada; Ministerio de Ciencia e Innovación; Australian Research Council; European Commission","keywords":"Lexicon; Computer science; Natural language processing; Optimal distinctiveness theory; Artificial intelligence; Set (abstract data type); Entropy (arrow of time); Semantic similarity; Space (punctuation); Measure (data warehouse); Object (grammar); Information retrieval; Psychology; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002986209,0.0001486902,0.0002710504,0.0001057204,0.00001386458,0.00001144426,0.0002304321,0.0004683611,0.00001025439],"category_scores_gemma":[0.0002756084,0.000126086,0.00008970611,0.00008978081,0.0001349065,8.538545e-7,0.000816851,0.0002121789,0.00000910857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008761194,"about_ca_system_score_gemma":0.0001258119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002092481,"about_ca_topic_score_gemma":0.0002716453,"domain_scores_codex":[0.9991031,0.00004635981,0.0003040247,0.0002462541,0.0001222607,0.0001780541],"domain_scores_gemma":[0.9995294,0.00003425353,0.0001256262,0.0002317993,0.00004547934,0.00003345988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008843526,0.0007952512,0.2694012,0.007569251,0.001062414,0.00007910473,0.004591508,0.004703475,0.2600554,0.002225911,0.01562485,0.4330072],"study_design_scores_gemma":[0.002860054,0.001334621,0.1482292,0.002536215,0.00007693705,0.00001662839,0.01085573,0.005458348,0.7350934,0.001933776,0.08929978,0.002305349],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846678,0.0006353031,0.0127735,0.000287645,0.000427858,0.0001392494,0.00002167786,0.0000453683,0.001001565],"genre_scores_gemma":[0.9959807,0.0003703787,0.002706829,0.00003685359,0.00005609239,0.00001993886,0.0001457318,0.00001416178,0.0006692681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4750379,"threshold_uncertainty_score":0.5141636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07582923238812853,"score_gpt":0.3740497067090218,"score_spread":0.2982204743208933,"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."}}