{"id":"W4285245912","doi":"10.18653/v1/2022.lchange-1.2","title":"Language Acquisition, Neutral Change, and Diachronic Trends in Noun Classifiers","year":2022,"lang":"en","type":"article","venue":"","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Classifier (UML); Ambiguity; Computer science; Categorization; Artificial intelligence; Noun; Population; Mandarin Chinese; Natural language processing; Speech recognition; Machine learning; Linguistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002020773,0.00004482248,0.00005795552,0.0000656729,0.0003589031,0.00002647804,0.00007289376,0.00002684638,0.00343151],"category_scores_gemma":[0.0000048133,0.00003897209,0.00002410766,0.0003625659,0.00005688607,0.0002000284,0.00004050375,0.0000874727,0.000006926291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001677268,"about_ca_system_score_gemma":0.00002069471,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01079466,"about_ca_topic_score_gemma":0.02062855,"domain_scores_codex":[0.9993725,0.0001162681,0.0000639339,0.0001203994,0.0001341053,0.0001928383],"domain_scores_gemma":[0.9998662,0.0000107446,0.00001907053,0.00005025799,0.0000073331,0.00004637287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005044738,0.0002146805,0.02196279,0.00001229172,0.00002150271,0.0001142412,0.6060047,0.00001895635,0.002013459,0.1313859,0.02245932,0.2157417],"study_design_scores_gemma":[0.001449739,0.0002105021,0.360305,0.000009244551,0.00002342728,0.00001087509,0.5133734,0.0003275918,0.0000889986,0.001151709,0.1225338,0.0005157337],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9220237,0.0009912201,0.000002006171,0.003257778,0.000139844,0.00008349357,0.000007211307,0.00005711698,0.07343763],"genre_scores_gemma":[0.9879559,0.00004048115,0.00001320719,0.0005006165,0.0001808738,0.00004691793,0.00002796079,0.0000030261,0.01123098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3383422,"threshold_uncertainty_score":0.9974795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03106964159270493,"score_gpt":0.3062419235609651,"score_spread":0.2751722819682602,"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."}}