{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002922479,0.0001037725,0.00013896,0.00004000541,0.0001024828,0.00002865102,0.0002895537,0.00008075258,0.001073887],"category_scores_gemma":[0.0001047999,0.00006165294,0.00005781323,0.0001642962,0.0001580026,0.00005166721,0.0000365038,0.0001539542,0.001637375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002424114,"about_ca_system_score_gemma":0.00001662488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007098573,"about_ca_topic_score_gemma":0.00001210278,"domain_scores_codex":[0.9990034,0.0001275874,0.000262073,0.0002057104,0.0001056151,0.0002956728],"domain_scores_gemma":[0.9990317,0.0003245136,0.0001150054,0.0003931422,0.00009038477,0.00004520554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004394478,0.0002725539,0.3673165,0.00001100797,0.0002637687,0.00002524308,0.0128245,0.000001143665,0.002480459,0.05640133,0.06098743,0.4993722],"study_design_scores_gemma":[0.0002532911,0.00008427369,0.960929,0.0000115187,0.000007464627,0.00001865265,0.001241251,0.000002336451,0.0004866219,0.02055761,0.01627761,0.0001303339],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8548576,0.0005354425,0.0001001777,0.000764941,0.00098346,0.0002465125,0.000002149106,0.00006086256,0.1424488],"genre_scores_gemma":[0.9888257,0.00001783848,0.0007855911,0.0001820784,0.00005419712,0.0001478732,0.000003218378,0.00001057384,0.00997292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5936126,"threshold_uncertainty_score":0.9998392,"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."}}