{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001615736,0.0004594099,0.0004093054,0.007265294,0.00184077,0.001929381,0.0006892048,0.0003653317,0.001119194],"category_scores_gemma":[0.005292787,0.0001842346,0.0006464257,0.008638603,0.0009289875,0.004367242,0.0007373556,0.0004890584,0.0002560885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001266602,"about_ca_system_score_gemma":0.001655461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004220459,"about_ca_topic_score_gemma":0.005134362,"domain_scores_codex":[0.9990933,0.0002326273,0.00008677837,0.0002293661,0.0002886732,0.00006914684],"domain_scores_gemma":[0.9976926,0.00102317,0.0002922807,0.0001883024,0.0007175333,0.00008619318],"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":[0.0002287936,0.0001386468,0.0574815,0.002800607,0.0002949526,0.0009176574,0.02227637,0.01663761,0.01966627,0.07561748,0.007276953,0.7966632],"study_design_scores_gemma":[0.00005159117,0.0003836335,0.1896165,0.001054573,0.0008497519,0.002359151,0.04421096,0.4304381,0.05334006,0.1369878,0.1404705,0.000237307],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6213523,0.01049971,0.3330012,0.002831419,0.0003939766,0.0004017994,0.00118404,0.0005571725,0.0297785],"genre_scores_gemma":[0.8518191,0.00597014,0.1338707,0.0001692555,0.0003166506,0.0002916861,0.001164442,0.00008870838,0.0063094],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007265294,"threshold_uncertainty_score":0.009189844,"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."}}