{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007983813,0.0003040623,0.0002938893,0.001418102,0.001374326,0.001249641,0.0003934096,0.000640414,0.002362757],"category_scores_gemma":[0.02899976,0.0002380267,0.0001309871,0.001978556,0.00125656,0.001073067,0.001331325,0.0005150334,0.0004601405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005630685,"about_ca_system_score_gemma":0.0006401385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001381493,"about_ca_topic_score_gemma":0.003780033,"domain_scores_codex":[0.9909741,0.006381345,0.0008102349,0.0007362443,0.0008447033,0.0002533351],"domain_scores_gemma":[0.9265847,0.06255452,0.003073348,0.003773446,0.003611174,0.0004028206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.002369728,0.0005748785,0.1488004,0.002633063,0.0001228262,0.003938151,0.2462334,0.0007466825,0.4811936,0.006137347,0.002835313,0.1044147],"study_design_scores_gemma":[0.0001190644,0.001084127,0.6548065,0.0004158675,0.0001984926,0.005323742,0.09810076,0.004883609,0.1875627,0.001971709,0.04532995,0.0002035415],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885163,0.0001663091,0.006314258,0.0001351356,0.00001584094,0.0002025269,0.0008643342,0.00003571874,0.003749611],"genre_scores_gemma":[0.9842406,0.00008491045,0.01269878,0.0000797742,0.00002109201,0.0005769425,0.001696011,0.00003506473,0.0005667327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007983813,"threshold_uncertainty_score":0.04222298,"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."}}