{"id":"W4409603837","doi":"10.61091/jcmcc127b-164","title":"A Computational Approach to the Classification of Chinese Syntactic Structures Using a Large-Scale Corpus","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence; Scale (ratio); Cartography; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001404447,0.001178257,0.0008169977,0.00289731,0.001290373,0.001019405,0.00173357,0.000639044,0.003078851],"category_scores_gemma":[0.005482105,0.0006724721,0.001319723,0.003057982,0.0009419364,0.002893486,0.001329358,0.001438898,0.0008894146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001452116,"about_ca_system_score_gemma":0.00389259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02287273,"about_ca_topic_score_gemma":0.0287232,"domain_scores_codex":[0.998938,0.0002722616,0.00008811275,0.000410159,0.0002326014,0.00005890092],"domain_scores_gemma":[0.9979016,0.001079172,0.0001333393,0.000416751,0.000424735,0.00004448698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001613655,0.000192291,0.005283314,0.00060797,0.0001759505,0.0004873807,0.0008428672,0.1265308,0.02480192,0.05339619,0.0162913,0.7712287],"study_design_scores_gemma":[0.00002288415,0.00003609237,0.001690619,0.00002027972,0.00004389855,0.0001059485,0.0001427535,0.9723312,0.004079848,0.01790622,0.003588678,0.00003164787],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02273135,0.0001828329,0.971314,0.0003571705,0.00005362058,0.0002045385,0.0007704619,0.002857473,0.0015286],"genre_scores_gemma":[0.1723565,0.0002685006,0.8199803,0.0001403576,0.00007319525,0.0008756862,0.00393699,0.0002190634,0.002149502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02287273,"threshold_uncertainty_score":0.04547918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0136925082745925,"score_gpt":0.2889689138748566,"score_spread":0.2752764056002641,"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."}}