{"id":"W4380318953","doi":"10.1037/xge0001407","title":"Comparing word frequency, semantic diversity, and semantic distinctiveness in lexical organization.","year":2023,"lang":"en","type":"article","venue":"Journal of Experimental Psychology General","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Optimal distinctiveness theory; Lexical decision task; Variety (cybernetics); Context (archaeology); Word lists by frequency; Variance (accounting); Computer science; Natural language processing; Word (group theory); Lexical diversity; Linguistics; Contrast (vision); Psychology; Semantic similarity; Metric (unit); Artificial intelligence; Cognition; Social psychology; History","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":[0.0003842117,0.00009390267,0.000206958,0.0002119454,0.0002436565,0.00004144539,0.0004318114,0.00006433496,0.00001197021],"category_scores_gemma":[0.00003381661,0.00008790506,0.00003526958,0.000565901,0.00009755332,0.0003523121,0.0005089386,0.0001839917,0.00001146659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006289817,"about_ca_system_score_gemma":0.00002043695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003451873,"about_ca_topic_score_gemma":0.00001129067,"domain_scores_codex":[0.9989771,0.0001437348,0.0003145932,0.0002219005,0.0001687754,0.000173926],"domain_scores_gemma":[0.9995033,0.00004947465,0.0001341175,0.0001780632,0.00005919197,0.00007581566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000253877,0.0002671468,0.9235188,0.000007919421,0.00002152765,0.0001046879,0.00374317,0.0001262414,0.06503154,0.00615506,0.0002103692,0.0007881058],"study_design_scores_gemma":[0.0007353719,0.0001060512,0.9888718,0.00001468517,0.000004177322,0.0002430005,0.0001817621,0.00274624,0.003524677,0.003453661,0.00001373225,0.0001049058],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9772238,0.0001616031,0.0211401,0.0008078182,0.0004774738,0.00006031355,3.458483e-7,0.00002871668,0.00009984684],"genre_scores_gemma":[0.9978884,0.00002045812,0.001843784,0.0001518159,0.00006991676,0.000001005764,0.000001949854,0.000005454485,0.00001722696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06535289,"threshold_uncertainty_score":0.3584664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05729411256604949,"score_gpt":0.3309632280050827,"score_spread":0.2736691154390332,"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."}}