{"id":"W1999976944","doi":"10.2298/psi1304497s","title":"The subjective frequency of word n-grams","year":2013,"lang":"en","type":"article","venue":"Psihologija","topic":"Reading and Literacy Development","field":"Psychology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Word lists by frequency; n-gram; Frequency; Word (group theory); Lexical decision task; Task (project management); Psychology; Respondent; Statistics; Probabilistic logic; Mathematics; Natural language processing; Speech recognition; Artificial intelligence; Computer science; Language model; Cognition; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002878489,0.0003791543,0.0003373131,0.0008300636,0.0001704754,0.001023239,0.0002496218,0.0005765312,0.003146347],"category_scores_gemma":[0.03212768,0.0001997722,0.0003522908,0.0004999473,0.0005056464,0.0008576886,0.0006756185,0.0006346185,0.0006864867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001896919,"about_ca_system_score_gemma":0.0001097896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006966946,"about_ca_topic_score_gemma":0.0009238683,"domain_scores_codex":[0.9979681,0.0006749656,0.0002669906,0.0003218385,0.0007021973,0.00006595958],"domain_scores_gemma":[0.9745456,0.01475836,0.00531536,0.001707731,0.002739964,0.000932917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002010817,0.0003464116,0.7732099,0.0006781737,0.0003991833,0.0003517225,0.01336554,0.002030924,0.1171421,0.002036279,0.001467597,0.08696135],"study_design_scores_gemma":[0.00002979836,0.001240217,0.9789518,0.000054847,0.00008037414,0.0005309167,0.00310414,0.003293252,0.008548805,0.001667834,0.002394466,0.0001035873],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9884259,0.0001759362,0.00613959,0.00004188508,0.00003194676,0.00007404364,0.0002919192,0.00006335028,0.004755491],"genre_scores_gemma":[0.9923202,0.0001732362,0.005313764,0.00006978529,0.00002667749,0.00008391887,0.0004744752,0.00003277133,0.00150502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003146347,"threshold_uncertainty_score":0.01522309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01966253594007396,"score_gpt":0.2950997893380989,"score_spread":0.275437253398025,"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."}}