{"id":"W4390022352","doi":"10.1016/j.jml.2023.104497","title":"Word length and frequency effects on text reading are highly similar in 12 alphabetic languages","year":2023,"lang":"en","type":"article","venue":"Journal of Memory and Language","topic":"Reading and Literacy Development","field":"Psychology","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Word lists by frequency; Linguistics; Eye movement; Psychology; Word (group theory); Reading (process); Fixation (population genetics); Word recognition; Word length; Orthographic projection; Natural language processing; Computer science; Cognitive psychology; 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":[],"consensus_categories":[],"category_scores_codex":[0.0007223117,0.0001361459,0.0002848848,0.0003758631,0.0000514538,0.00003509783,0.00009303522,0.00008402753,0.0000815817],"category_scores_gemma":[0.0001544751,0.0001045736,0.00004061286,0.0001724824,0.00002793046,0.00008995695,0.00002236882,0.0003273333,0.00003283683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002749647,"about_ca_system_score_gemma":0.00001261007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003453487,"about_ca_topic_score_gemma":0.00001375838,"domain_scores_codex":[0.9989717,0.0001774661,0.0002963812,0.0001668884,0.0001533509,0.0002341888],"domain_scores_gemma":[0.9990869,0.0004871723,0.0001779698,0.0001294029,0.00001642434,0.0001020981],"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":[0.000568792,0.0003033724,0.1121531,0.0006415434,0.0003915763,0.02965943,0.1932927,0.00002744891,0.01870983,0.0009043224,0.02638013,0.6169677],"study_design_scores_gemma":[0.003170245,0.0005337481,0.9597312,0.001724568,0.00006176383,0.0005931407,0.02640969,0.00001492138,0.003243002,0.0003202095,0.003810657,0.000386869],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9897196,0.003517557,0.000001743998,0.0007248631,0.0003977924,0.00008504734,0.000003083303,0.00002589644,0.005524358],"genre_scores_gemma":[0.9960536,0.0001501334,0.0001512699,0.0005759624,0.0002523046,0.000004470839,0.000002445221,0.00001728089,0.002792476],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.847578,"threshold_uncertainty_score":0.4264389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01126405886987521,"score_gpt":0.2954870216621641,"score_spread":0.2842229627922889,"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."}}