{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002801104,0.000416877,0.0006920175,0.004712564,0.0005875194,0.002918428,0.0006630411,0.001191915,0.0009632118],"category_scores_gemma":[0.02947403,0.000464389,0.0005937492,0.003171103,0.00269974,0.006154604,0.002102978,0.000893595,0.0002026194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008765207,"about_ca_system_score_gemma":0.0002862983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009000984,"about_ca_topic_score_gemma":0.0007725386,"domain_scores_codex":[0.9979195,0.0007176958,0.000162256,0.0005455942,0.00051676,0.0001381721],"domain_scores_gemma":[0.9800817,0.01450576,0.002634284,0.001517599,0.000932336,0.0003282112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001870946,0.0002182529,0.1257615,0.0009735169,0.0007034363,0.00112174,0.006659078,0.1652356,0.1334872,0.2473338,0.002350574,0.3142842],"study_design_scores_gemma":[0.00003274472,0.0002183841,0.08664522,0.000105433,0.000237615,0.001495705,0.00139663,0.3993848,0.02574784,0.4817159,0.00284969,0.0001701161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5943253,0.0008386418,0.3988598,0.000456153,0.00002248553,0.00003257826,0.0004810641,0.0003874319,0.004596607],"genre_scores_gemma":[0.9816988,0.0001894615,0.01737252,0.00006073304,0.00004082567,0.00002350641,0.000283825,0.00005141366,0.0002789881],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004712564,"threshold_uncertainty_score":0.01481384,"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."}}