{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003998083,0.0004307827,0.0004108777,0.003971338,0.000694938,0.002538223,0.0006587129,0.0008554342,0.004423439],"category_scores_gemma":[0.03806905,0.0003363759,0.0005933967,0.004095969,0.001651442,0.006154079,0.002333647,0.001157753,0.0006548882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008477984,"about_ca_system_score_gemma":0.0006722654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00760258,"about_ca_topic_score_gemma":0.01475619,"domain_scores_codex":[0.9980921,0.000614846,0.0002194246,0.0006262544,0.0003544426,0.0000929173],"domain_scores_gemma":[0.9722343,0.02022456,0.004579921,0.001481165,0.0009794928,0.0005005627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007281533,0.0003269685,0.8257825,0.0007971239,0.0005609344,0.0003701443,0.01823604,0.0007544279,0.007285545,0.008594935,0.002250575,0.1343126],"study_design_scores_gemma":[0.00002346289,0.0002028523,0.9816839,0.0001636218,0.0001111099,0.000203083,0.003975681,0.002515357,0.0008333233,0.008443513,0.001788981,0.00005501728],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9824838,0.001365817,0.004701767,0.0003295269,0.00005726045,0.00007060796,0.0006719905,0.00002722006,0.01029203],"genre_scores_gemma":[0.9921367,0.0004060926,0.004839393,0.0001526635,0.00003751374,0.0001616823,0.001056817,0.00003773624,0.001171532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00760258,"threshold_uncertainty_score":0.02114415,"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."}}