{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01022465,0.000517594,0.0004201897,0.0007314783,0.0003158594,0.001422113,0.001001173,0.0007802329,0.001838462],"category_scores_gemma":[0.08118825,0.000658314,0.0004125457,0.000307551,0.002543668,0.003903308,0.002455084,0.001594103,0.0003714168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004940354,"about_ca_system_score_gemma":0.0007543312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001454305,"about_ca_topic_score_gemma":0.001242574,"domain_scores_codex":[0.9944484,0.002346196,0.0004086804,0.001234322,0.001286857,0.0002755891],"domain_scores_gemma":[0.8730674,0.1072818,0.007005899,0.008265387,0.002398308,0.001981164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003645456,0.00111882,0.4015726,0.0007793968,0.0005345754,0.001336202,0.01007218,0.03760273,0.2168778,0.03048888,0.0008799692,0.2950915],"study_design_scores_gemma":[0.0001455481,0.006045575,0.4248484,0.0001606057,0.0002360017,0.002372698,0.003320408,0.3471182,0.1426548,0.06868492,0.004193262,0.0002196118],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981235,0.0001820401,0.01546152,0.0001924649,0.00001108061,0.0000199662,0.00005587719,0.00007062603,0.002771423],"genre_scores_gemma":[0.9892548,0.000074128,0.01014337,0.00005936283,0.000008757321,0.00004664822,0.00007439061,0.00003144929,0.0003071011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01022465,"threshold_uncertainty_score":0.05407381,"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."}}