{"id":"W4406132022","doi":"10.1111/desc.13606","title":"Simulating Early Phonetic and Word Learning Without Linguistic Categories","year":2025,"lang":"en","type":"article","venue":"Developmental Science","topic":"Language Development and Disorders","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence de l'innovation de Défense; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; European Research Council; Canadian Institute for Advanced Research","keywords":"Linguistics; Psychology; Perception; Speech perception; Language acquisition; Text segmentation; Natural language processing; Phonotactics; Speech segmentation; Computer science; Artificial intelligence; Phonology; Segmentation","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000392363,0.0001381126,0.0001276301,0.0002096716,0.0005899371,0.0001502215,0.0002306693,0.00004190635,0.0002286861],"category_scores_gemma":[0.0003693686,0.0001267712,0.00001341846,0.0009018779,0.0004635713,0.0001177761,0.000195784,0.0001471045,0.0001052574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007868549,"about_ca_system_score_gemma":0.0002296152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002674088,"about_ca_topic_score_gemma":0.00003611347,"domain_scores_codex":[0.998713,0.00002689574,0.0002007592,0.0004203553,0.0002225992,0.0004163871],"domain_scores_gemma":[0.9996353,0.0000858018,0.00005067035,0.0000878388,0.00005647009,0.00008387346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002712552,0.00002749189,0.8858094,0.00001372617,0.00001977447,0.00002000899,0.04345028,0.000009050184,0.001676331,0.003676476,0.00006266741,0.06520771],"study_design_scores_gemma":[0.0005679044,0.00002071553,0.9861315,0.00004672342,0.000008343462,0.000008908802,0.008265114,0.0001535535,0.0005935729,0.0009413696,0.002980763,0.0002815511],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8917316,0.0002122724,0.0003634128,0.00004898735,0.0005512341,0.0001249988,2.754118e-7,0.00008730377,0.1068799],"genre_scores_gemma":[0.9878766,0.000003532856,0.003530549,0.0002110164,0.00001711883,0.00001639715,0.000002542169,0.00000751981,0.008334713],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1003221,"threshold_uncertainty_score":0.5169581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01043338721644637,"score_gpt":0.3005301602740816,"score_spread":0.2900967730576352,"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."}}