{"id":"W1965307478","doi":"10.1111/j.1467-7687.2009.00824.x","title":"The secret is in the sound: from unsegmented speech to lexical categories","year":2009,"lang":"en","type":"article","venue":"Developmental Science","topic":"Language Development and Disorders","field":"Psychology","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Linguistics; Part of speech; Psychology; Noun; Natural language processing; Language acquisition; Word (group theory); Lexical item; Computer science; Artificial intelligence; Speech recognition","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":[],"consensus_categories":[],"category_scores_codex":[0.0008480905,0.0001491075,0.0001011116,0.00009060086,0.0006103084,0.0002458105,0.00109796,0.00004509573,0.0006431368],"category_scores_gemma":[0.00007804499,0.00008374465,0.00002499683,0.001279305,0.0003312429,0.000154815,0.00009917669,0.0001472189,0.0007056246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001321435,"about_ca_system_score_gemma":0.000184196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006157922,"about_ca_topic_score_gemma":0.0007979608,"domain_scores_codex":[0.9981353,0.00005626088,0.0002399925,0.0004148228,0.0005869916,0.0005666273],"domain_scores_gemma":[0.999464,0.0001207188,0.00003882037,0.0002481904,0.00003050912,0.00009773255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.000328817,0.0004662004,0.1381242,0.000002055095,0.00004322714,0.0002668597,0.4446509,0.000001689515,0.005514724,0.02850742,0.08749269,0.2946012],"study_design_scores_gemma":[0.0005601158,0.00006425861,0.8992131,0.000008746761,0.000003396724,0.00002739723,0.05025276,0.00000630704,0.002037454,0.01251272,0.03497881,0.0003349216],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9452778,0.0001059068,0.0001505808,0.007597352,0.0004379947,0.0003038663,0.000005319984,0.00003523072,0.04608599],"genre_scores_gemma":[0.9853168,0.000005822154,0.001446869,0.01206142,0.00003410762,0.00002885748,0.00001253783,0.000004771427,0.001088807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7610888,"threshold_uncertainty_score":0.9069613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0191425064127709,"score_gpt":0.312696380891055,"score_spread":0.2935538744782841,"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."}}