{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001550416,0.0002279988,0.0005698241,0.0003264719,0.0003168147,0.0003034268,0.00114914,0.0001211965,4.849391e-7],"category_scores_gemma":[0.0005954709,0.0001567087,0.0001351868,0.0009999875,0.000062947,0.0002808936,0.0005052257,0.0003528028,2.018677e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000096751,"about_ca_system_score_gemma":0.0002562001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007581146,"about_ca_topic_score_gemma":2.373703e-7,"domain_scores_codex":[0.9977678,0.0001448027,0.000957089,0.0002345013,0.0006555805,0.0002402358],"domain_scores_gemma":[0.9970044,0.0006389687,0.001074513,0.0003547201,0.0008355061,0.00009191113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003482029,0.0003335718,0.0002663538,0.0001968628,0.00006414922,0.000002071449,0.002185907,0.0006073226,0.00108313,0.9938951,0.00007086781,0.001259802],"study_design_scores_gemma":[0.000907642,0.0001247272,0.0003875169,0.0002021616,0.00003923151,0.00007004771,0.000167466,0.2500331,0.0003874657,0.7474993,0.00005063681,0.0001306996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2519884,0.0005363129,0.7432103,0.0002177558,0.003559255,0.0002649837,0.000001509151,0.00004210753,0.0001793841],"genre_scores_gemma":[0.6952589,0.000002400826,0.3044783,0.00004208798,0.0002058236,0.000001370002,5.725358e-7,0.000008981068,0.00000151982],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4432705,"threshold_uncertainty_score":0.6390393,"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."}}