{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003164354,0.0003558512,0.00034327,0.0001726814,0.00004771657,0.0000654508,0.0002876463,0.0005272151,0.00001339358],"category_scores_gemma":[0.0005951587,0.0003216885,0.00007968084,0.00007035612,0.00004761392,0.0000026913,0.0006488079,0.0006486717,0.00004440559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003395496,"about_ca_system_score_gemma":0.00004278885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001620773,"about_ca_topic_score_gemma":0.0002683177,"domain_scores_codex":[0.998546,0.0001151755,0.000329131,0.0005107743,0.0001718972,0.0003270239],"domain_scores_gemma":[0.9989616,0.0001155354,0.0001931453,0.0006172055,0.00002830583,0.00008426624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004483802,0.0005612945,0.6149103,0.01915354,0.001500555,0.0009346717,0.00407065,0.01195965,0.1462265,0.003441322,0.07774588,0.1190472],"study_design_scores_gemma":[0.006936608,0.003052326,0.6925538,0.01035737,0.0004520861,0.00009878529,0.002555401,0.01426999,0.2210247,0.006369051,0.03467683,0.007653048],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825162,0.0008080406,0.0002823741,0.00120631,0.0004245905,0.0006131741,0.00003413306,0.0001359068,0.01397932],"genre_scores_gemma":[0.9901536,0.0006491906,0.004581217,0.0008744392,0.0002836209,0.00006432279,0.0003653498,0.00007558309,0.002952642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1113942,"threshold_uncertainty_score":0.9999235,"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."}}