{"id":"W1989914796","doi":"10.1111/j.1467-7687.2009.00886.x","title":"Testing the limits of statistical learning for word segmentation","year":2009,"lang":"en","type":"article","venue":"Developmental Science","topic":"Language Development and Disorders","field":"Psychology","cited_by":166,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute on Deafness and Other Communication Disorders","keywords":"Text segmentation; Syllable; Word (group theory); Speech segmentation; Language acquisition; Artificial intelligence; Constructed language; Natural language processing; Language development; Psychology; Natural language; Computer science; Segmentation; Linguistics; Speech recognition; Developmental psychology","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":[0.0005906885,0.00007803531,0.00007684428,0.00006720503,0.0003387002,0.00003626358,0.0002432769,0.00002124328,0.0001718863],"category_scores_gemma":[0.0004304909,0.00005540604,0.00001371461,0.0005859822,0.0002121252,0.0001165992,0.00002430534,0.00006311953,0.00003274852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000053463,"about_ca_system_score_gemma":0.0001476557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001833267,"about_ca_topic_score_gemma":0.000004428021,"domain_scores_codex":[0.9990242,0.00002261677,0.0001944656,0.0002197638,0.0002535036,0.0002855161],"domain_scores_gemma":[0.9994922,0.0002481402,0.00007982144,0.00006087037,0.00007125639,0.00004767576],"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":[0.00005304965,0.00008646594,0.03773905,0.000006341671,0.00001050632,0.000003906468,0.01444182,0.00002274033,0.05372654,0.009164494,0.0009487002,0.8837964],"study_design_scores_gemma":[0.0005050005,0.0001132902,0.9832243,0.00001468182,0.000006094992,0.00001200655,0.008210339,0.0001753969,0.005620183,0.001092649,0.0008662443,0.0001598038],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9498575,0.00004579313,0.01421341,0.0002800642,0.0002785775,0.0004078046,0.000002888133,0.0000495381,0.03486442],"genre_scores_gemma":[0.952964,5.753802e-7,0.04629622,0.0002950593,0.00001466528,0.00002241494,0.00001039397,0.000003828889,0.0003928096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9454853,"threshold_uncertainty_score":0.2605042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04891558377427276,"score_gpt":0.3471157618175959,"score_spread":0.2982001780433232,"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."}}