{"id":"W4319772631","doi":"10.31234/osf.io/cbvjr","title":"Word length and frequency effects on text reading are highly similar in 12 alphabetic languages","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Word lists by frequency; Eye movement; Computer science; Linguistics; Word (group theory); Fixation (population genetics); Universality (dynamical systems); Reading (process); Word length; Natural language processing; Artificial intelligence; Population","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":[0.0009940573,0.0003427281,0.0005254491,0.001230459,0.0003092675,0.001031655,0.0002407016,0.0003953586,0.004526869],"category_scores_gemma":[0.008863234,0.0001974241,0.0004211024,0.0007060294,0.0007413621,0.0005471702,0.0009253787,0.0004319627,0.0004549619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002409459,"about_ca_system_score_gemma":0.0002015279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002653973,"about_ca_topic_score_gemma":0.003994799,"domain_scores_codex":[0.9990692,0.0003022874,0.0001375423,0.0002648472,0.0001486767,0.00007759164],"domain_scores_gemma":[0.9824392,0.01422638,0.001551337,0.0008818305,0.0004960164,0.0004053067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.009239618,0.0007374362,0.5590943,0.0008489758,0.0007799118,0.001249831,0.007828486,0.002248373,0.3314689,0.0005573515,0.0006122722,0.08533454],"study_design_scores_gemma":[0.0000295281,0.0003349399,0.9907665,0.00001102482,0.00007039744,0.0002872929,0.0008208858,0.000971953,0.006139995,0.0002250596,0.0003187767,0.00002367024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9992591,0.00004779486,0.000115687,0.000007472702,0.000001229854,0.000002129277,0.0001386258,0.00001288569,0.0004151301],"genre_scores_gemma":[0.9990289,0.00002935568,0.0002526023,0.000008502716,0.000002160393,0.000009131264,0.0003414083,0.00003086802,0.0002970785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004526869,"threshold_uncertainty_score":0.01514393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01004198226088323,"score_gpt":0.2707311990417138,"score_spread":0.2606892167808306,"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."}}