{"id":"W4408567157","doi":"10.61091/jcmcc124-25","title":"Research on thematic clustering and text mining of chinese modern and contemporary literary texts in the network era","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Thematic map; Cluster analysis; Literature; History; Information retrieval; Linguistics; Data science; Computer science; Artificial intelligence; Art; Geography; Philosophy; Cartography","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":[0.01073826,0.0001659764,0.0006352904,0.0003119401,0.0005602219,0.0002721719,0.0003383025,0.0001115159,0.000001718253],"category_scores_gemma":[0.001091753,0.0001173931,0.0000876081,0.0009094027,0.0002683428,0.0001620225,0.0002913431,0.000542368,1.115911e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004067862,"about_ca_system_score_gemma":0.0002189446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004234143,"about_ca_topic_score_gemma":0.000007315162,"domain_scores_codex":[0.996797,0.001077647,0.0009181963,0.0001786266,0.0007685022,0.0002600531],"domain_scores_gemma":[0.9905108,0.008383405,0.0005194854,0.0001403926,0.0003630405,0.00008286227],"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":[0.0001654133,0.0004029582,0.005395516,0.0003519518,0.0001189741,0.00001962232,0.04201256,0.0002845883,0.00002781921,0.9219869,0.0001399214,0.02909371],"study_design_scores_gemma":[0.001540889,0.0002404141,0.003402348,0.001062642,0.00002711976,0.00000902905,0.00390976,0.02308923,0.000003222918,0.9665036,0.0001047778,0.0001069989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9870988,0.002191548,0.001833781,0.0006247704,0.001690229,0.0002754954,4.756963e-7,0.00000739808,0.00627751],"genre_scores_gemma":[0.9962899,0.00007655854,0.002953166,0.00004231913,0.0006153816,0.000002043394,3.108346e-7,0.000009306848,0.00001098707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04451661,"threshold_uncertainty_score":0.4787153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05007256040533145,"score_gpt":0.3883092477054205,"score_spread":0.338236687300089,"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."}}