{"id":"W1970536639","doi":"10.3366/cor.2007.2.1.97","title":"The Wenzhou Spoken Corpus","year":2007,"lang":"en","type":"article","venue":"Corpora","topic":"China's Ethnic Minorities and Relations","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"XPath; Markup language; XML; Computer science; Transcription (linguistics); Natural language processing; Information retrieval; Linguistics; Artificial intelligence; World Wide Web; XML database","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":[],"consensus_categories":[],"category_scores_codex":[0.001025153,0.00004531364,0.00005070275,0.00001797557,0.001213557,0.00005227198,0.0001941614,0.00006647866,0.0001548203],"category_scores_gemma":[0.0001224646,0.00003118296,0.00004849578,0.0001806801,0.0003365563,0.00005312014,0.00002735062,0.0001176431,0.0001306092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005095882,"about_ca_system_score_gemma":0.00009689081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001477427,"about_ca_topic_score_gemma":0.006726044,"domain_scores_codex":[0.9993089,0.0000374202,0.0001220152,0.00008437252,0.0002098656,0.0002374341],"domain_scores_gemma":[0.9993307,0.0003249665,0.00006667541,0.0001438373,0.00004798741,0.00008583321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001054409,0.0000199026,0.01579313,0.000001771108,0.0000103001,0.00001421969,0.008362547,0.000003464204,0.00002510019,0.8792729,0.03024545,0.06624065],"study_design_scores_gemma":[0.00007746948,0.000009375982,0.03501259,0.000004278686,0.000005540055,0.000001212696,0.003891262,0.00000952455,0.00001217289,0.02184433,0.9390701,0.00006211467],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1976643,0.002682412,0.001170599,0.005785887,0.002848547,0.0002634159,0.000004027434,0.0001327998,0.789448],"genre_scores_gemma":[0.9483617,0.0005121483,0.0001112421,0.000145617,0.0006649981,0.000002511499,0.000001963986,0.000005849121,0.050194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9088247,"threshold_uncertainty_score":0.9333825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02606158654718032,"score_gpt":0.3246620743798674,"score_spread":0.2986004878326871,"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."}}