{"id":"W2063050588","doi":"10.3758/bf03195586","title":"Case-sensitive letter and bigram frequency counts from large-scale English corpora","year":2004,"lang":"en","type":"article","venue":"Behavior Research Methods, Instruments, & Computers","topic":"Reading and Literacy Development","field":"Psychology","cited_by":118,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bigram; Computer science; Speech recognition; Frequency; Natural language processing; Scale (ratio); Artificial intelligence; Statistics; Mathematics; Trigram","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":[0.001665558,0.0002463325,0.0003145151,0.0003249359,0.0002906286,0.0001869068,0.0002544938,0.0001779902,0.0003899555],"category_scores_gemma":[0.00006421836,0.0002399088,0.00007513835,0.0003449347,0.000261281,0.0001533432,0.0002191069,0.0007185846,0.0002615634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002387174,"about_ca_system_score_gemma":0.00008991725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001580781,"about_ca_topic_score_gemma":0.00002444101,"domain_scores_codex":[0.9966087,0.001029226,0.0003920133,0.0007278486,0.000495602,0.0007466265],"domain_scores_gemma":[0.9985354,0.0003290839,0.00009555463,0.0005189925,0.0002404083,0.0002805617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000110945,0.001142779,0.06353109,0.00003258001,0.0003165402,0.01072484,0.04451233,0.000002052869,0.002171487,0.003394017,0.02464396,0.8494174],"study_design_scores_gemma":[0.01673428,0.001465452,0.2908553,0.0009186522,0.000320804,0.005680607,0.0168055,0.0002049663,0.009760864,0.008553285,0.6451185,0.003581805],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813547,0.0001066423,0.01070875,0.0001725858,0.002887139,0.0005973655,0.0001429298,0.0001239325,0.003906016],"genre_scores_gemma":[0.5671065,0.00002999914,0.4303533,0.0006648439,0.0005318415,0.0001936887,0.0001479349,0.00006741485,0.0009044204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8458356,"threshold_uncertainty_score":0.9783199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1203234814297276,"score_gpt":0.4528343708533598,"score_spread":0.3325108894236322,"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."}}