{"id":"W4207014412","doi":"10.1075/cld.21017.new","title":"Mandarin<i>chī</i>‘eat’ sentences in elicitation and corpus data","year":2022,"lang":"en","type":"article","venue":"Chinese Language and Discourse An International and Interdisciplinary Journal","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Mandarin Chinese; Newspaper; Natural language processing; Word (group theory); Computer science; Linguistics; Corpus linguistics; Artificial intelligence; Psychology; Advertising; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004607489,0.0001963187,0.0002400768,0.0003138295,0.001043703,0.0005496122,0.0004152771,0.00001753119,0.00131386],"category_scores_gemma":[0.00003385556,0.0001424315,0.0000418928,0.00005504062,0.0004027776,0.00156409,0.00167675,0.0003349515,0.000001798636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002788227,"about_ca_system_score_gemma":0.00002236913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002959269,"about_ca_topic_score_gemma":0.002799105,"domain_scores_codex":[0.9986939,0.00009449772,0.0003376951,0.0003644195,0.0003218455,0.0001876228],"domain_scores_gemma":[0.9994223,0.00005742096,0.0001542403,0.0002088369,0.00005770675,0.00009946627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0006110957,0.0008894036,0.09694584,0.000056908,0.0006822491,0.001622017,0.7380784,0.0001130809,0.0003038634,0.02800374,0.004180138,0.1285133],"study_design_scores_gemma":[0.001715137,0.0005176687,0.03984715,0.0001251827,0.0001405236,0.001595374,0.9243814,0.009105307,0.000003971598,0.01606492,0.005948074,0.0005552534],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787225,0.003657907,0.0000251664,0.002760927,0.0006774932,0.00007958199,0.0002593042,0.00001696227,0.01380023],"genre_scores_gemma":[0.9957318,0.0004557762,0.00006485223,0.000283135,0.000940974,0.00001385814,0.0002399166,0.00001504425,0.002254647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.186303,"threshold_uncertainty_score":0.9995991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02444701641999727,"score_gpt":0.3468038360098904,"score_spread":0.3223568195898932,"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."}}