{"id":"W1972260496","doi":"10.3115/1596324.1596340","title":"An incremental bayesian model for learning syntactic categories","year":2008,"lang":"en","type":"article","venue":"","topic":"Language Development and Disorders","field":"Psychology","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Bootstrapping (finance); Computer science; Artificial intelligence; Utterance; Natural language processing; Ambiguity; Bayesian probability; Bayesian inference; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008331507,0.00009432984,0.00009249077,0.00005448685,0.0002121949,0.00001415721,0.0000945,0.00005621648,0.001743831],"category_scores_gemma":[0.00001660815,0.00008300199,0.00003404523,0.00005743114,0.00003402129,0.0001457581,0.00001192695,0.00006903012,0.00008638399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001933713,"about_ca_system_score_gemma":0.00003639837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000250422,"about_ca_topic_score_gemma":0.0001271876,"domain_scores_codex":[0.9993548,0.0000249035,0.000117861,0.0001936618,0.00007721063,0.0002315094],"domain_scores_gemma":[0.9997365,0.00003155079,0.00002954233,0.0001198404,0.00002175171,0.00006080767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001230673,0.001546449,0.4978367,0.00007377782,0.0005336448,0.0001761345,0.2818786,0.002315639,0.00479218,0.1208121,0.05745859,0.03134556],"study_design_scores_gemma":[0.01749202,0.002172311,0.08581153,0.00002390058,0.000239356,0.0004470739,0.2136608,0.6391268,0.005258698,0.01567119,0.01578112,0.004315261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6880342,0.00007564112,0.2234091,0.0001551516,0.000211232,0.0002723503,0.00000245599,0.0002379067,0.08760201],"genre_scores_gemma":[0.9737955,0.000003255642,0.005846516,0.0003498519,0.00003876576,0.0000592869,0.00006350678,0.00001915407,0.01982414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6368111,"threshold_uncertainty_score":0.9991687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03008754079335142,"score_gpt":0.3102462791563757,"score_spread":0.2801587383630243,"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."}}