{"id":"W4385953436","doi":"10.31234/osf.io/vpx57","title":"Predicting age of acquisition for children’s early vocabulary in five languages using language model surprisal","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Language Development and Disorders","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Predictability; Concreteness; Age of Acquisition; Vocabulary; Computer science; Word (group theory); Word lists by frequency; Linguistics; Natural language processing; Noun; Predicate (mathematical logic); Artificial intelligence; Psychology; Cognitive psychology; Cognition; Mathematics; Sentence; Statistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004664652,0.0003135204,0.0004907887,0.0004543848,0.00004255834,0.00003626082,0.0003261436,0.0004945418,0.0001661493],"category_scores_gemma":[0.00007746265,0.0003154691,0.0001949838,0.0001714707,0.00005089047,0.00007026448,0.0003723251,0.000368651,0.00001551266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007410605,"about_ca_system_score_gemma":0.0001024535,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01259088,"about_ca_topic_score_gemma":0.001273851,"domain_scores_codex":[0.9980665,0.00008906284,0.0005607126,0.0006221906,0.000225519,0.0004360171],"domain_scores_gemma":[0.9990295,0.0001477867,0.00025784,0.0004555653,0.00005529367,0.00005408534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007975883,0.0006978473,0.6187817,0.000961902,0.00128171,0.0005285615,0.3017006,0.06202443,0.004160806,0.001447848,0.002544406,0.005072573],"study_design_scores_gemma":[0.0086118,0.0002420859,0.7825717,0.001397951,0.0004909064,0.00002195691,0.08479634,0.1102564,0.002479701,0.006501834,0.000002581067,0.002626756],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9775823,0.0006658693,0.01747372,0.00003771014,0.0004549669,0.001103078,0.0003747637,0.0002259376,0.002081681],"genre_scores_gemma":[0.9881975,0.00001069822,0.006853004,0.00009594112,0.0001960492,0.0001604816,0.00193934,0.00009364696,0.00245336],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2169043,"threshold_uncertainty_score":0.9999297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03382932446985801,"score_gpt":0.3443756611534295,"score_spread":0.3105463366835716,"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."}}