{"id":"W1604751532","doi":"10.1111/j.1467-9922.2010.00616.x","title":"Lexical Frequency Profiles and Zipf's Law","year":2010,"lang":"en","type":"article","venue":"Language Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Victoria","funders":"","keywords":"Zipf's law; Vocabulary; Word lists by frequency; Natural language processing; Artificial intelligence; Probabilistic logic; Word (group theory); Computer science; Homogeneous; Linguistics; Psychology; Statistics; Cognitive psychology; Statistical physics; Mathematics; Sentence","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":[0.0002524032,0.0001229525,0.0001195904,0.0000582085,0.0001851154,0.0002615129,0.0004952716,0.0001147055,0.00004791429],"category_scores_gemma":[0.000199514,0.0001024285,0.0000281561,0.0001615664,0.00009599837,0.0004676337,0.0002547578,0.0008572249,0.00002220057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007785206,"about_ca_system_score_gemma":0.00001930459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002379639,"about_ca_topic_score_gemma":0.00006208547,"domain_scores_codex":[0.9990912,0.0000515709,0.0001186574,0.0003201351,0.0001701187,0.0002483269],"domain_scores_gemma":[0.9994496,0.00007321249,0.00006112969,0.0002974137,0.00003600791,0.00008267211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001536633,0.00001398158,0.001642177,0.00002713049,0.000004837163,0.0001308655,0.002845672,4.092825e-7,0.2685791,0.6503707,0.000047912,0.07633577],"study_design_scores_gemma":[0.001225382,0.0005185026,0.003606632,0.0002976995,0.00003677623,0.001328023,0.001111474,0.01532897,0.7322808,0.2249637,0.01692644,0.002375565],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7226053,0.007285554,0.2347592,0.002527076,0.0005645267,0.0003690007,0.000002116074,0.005154656,0.02673257],"genre_scores_gemma":[0.6334503,0.000002116181,0.3658466,0.0003026089,0.00009002288,0.000006905596,0.000002029377,0.000009045977,0.0002904439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4637017,"threshold_uncertainty_score":0.4176914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00520636905561305,"score_gpt":0.2558624053061282,"score_spread":0.2506560362505151,"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."}}