{"id":"W4416193684","doi":"10.1080/23273798.2025.2585303","title":"Surprisal in reading: language models predict the N400 for L2 readers","year":2025,"lang":"en","type":"article","venue":"Language Cognition and Neuroscience","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Graduate Student Association, Fordham University; National Science Foundation of Sri Lanka; Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"N400; Language model; Semantics (computer science); Computational linguistics; Utterance","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":[0.0004406743,0.00008347689,0.0000861404,0.0001037798,0.0001733502,0.0001640878,0.0004165611,0.0000399753,0.000001356379],"category_scores_gemma":[0.0002843569,0.00006337051,0.00002819992,0.0005045771,0.0001476653,0.0004291511,0.00008961316,0.0001066966,0.000001086859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001371079,"about_ca_system_score_gemma":0.00004024462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000451883,"about_ca_topic_score_gemma":0.00005289838,"domain_scores_codex":[0.9990554,0.0000738372,0.0001538026,0.0003831545,0.0001364282,0.0001973329],"domain_scores_gemma":[0.9993188,0.0002612148,0.00004130913,0.0003059082,0.00003302595,0.00003968788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008943705,0.0003202914,0.0007879617,0.000178206,0.000005829035,0.00003648,0.04124745,0.0004583875,0.5842472,0.1764368,0.001162882,0.1950291],"study_design_scores_gemma":[0.001961762,0.0002442313,0.03067469,0.0001919224,0.00003145981,0.00005873175,0.008328537,0.7318202,0.1839887,0.03999786,0.002130424,0.0005714524],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.351287,0.0003022193,0.6389064,0.004862283,0.0003883662,0.0007723483,0.00002534324,0.0001980678,0.003257962],"genre_scores_gemma":[0.9965112,0.00003065651,0.0006717283,0.002337574,0.00001440827,0.00005999532,0.000004984514,0.000003007116,0.0003665074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7313619,"threshold_uncertainty_score":0.2584175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02908256521657047,"score_gpt":0.2939134694958276,"score_spread":0.2648309042792572,"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."}}