{"id":"W3048188704","doi":"10.1162/ling_a_00401","title":"Statistical Evidence for Learnable Lexical Subclasses in Japanese","year":2020,"lang":"en","type":"article","venue":"Linguistic Inquiry","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Phonotactics; Lexicon; Learnability; Linguistics; Computer science; Natural language processing; Phonology; Psychology; Artificial intelligence; Philosophy","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003276397,0.0001456101,0.0002242062,0.0000645304,0.00006957613,0.0001633902,0.000844312,0.00009269579,0.00001365186],"category_scores_gemma":[0.01447375,0.0001334767,0.0000396127,0.0003496533,0.0001118042,0.0002023228,0.0002445519,0.0002721504,0.00002652277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005269421,"about_ca_system_score_gemma":0.0001384146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005362503,"about_ca_topic_score_gemma":0.000005358736,"domain_scores_codex":[0.998549,0.00006094971,0.0002938499,0.0004907545,0.0002439769,0.0003615025],"domain_scores_gemma":[0.9982827,0.001090845,0.00006651795,0.0002741803,0.0001467044,0.000139022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002872736,0.0001584258,0.001923357,0.0009819758,0.00001777689,0.0007977874,0.02538359,0.00006271212,0.004095403,0.9395732,0.009278005,0.01744051],"study_design_scores_gemma":[0.002112476,0.002064914,0.001599973,0.001336713,0.00006179388,0.00009120085,0.0007100855,0.4228321,0.01927127,0.528075,0.01971066,0.002133806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002736604,0.001455781,0.9925916,0.001837564,0.0004517177,0.0002622301,0.000003629638,0.0004746707,0.0001861962],"genre_scores_gemma":[0.6067562,0.000006205867,0.3916763,0.001027904,0.000450611,0.00002771426,0.000002971557,0.000009684406,0.0000424401],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6040196,"threshold_uncertainty_score":0.9938278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1347884067309446,"score_gpt":0.3918053928929698,"score_spread":0.2570169861620252,"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."}}