{"id":"W4414015822","doi":"10.11159/cist25.141","title":"Improved BoW-BoC Indexing for Short Texts Using Large Language Models","year":2025,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Search engine indexing; Computer science; Natural language processing; Artificial intelligence; Information retrieval","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":[0.001613368,0.001478442,0.002160471,0.005762257,0.0009827071,0.002092337,0.001963435,0.001304876,0.003886828],"category_scores_gemma":[0.006604422,0.0004304606,0.001634011,0.007882917,0.0006392603,0.005593128,0.002118618,0.002180655,0.005070416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009298942,"about_ca_system_score_gemma":0.002042056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008478318,"about_ca_topic_score_gemma":0.008921156,"domain_scores_codex":[0.9981126,0.0003536529,0.0001632629,0.0004215266,0.000756974,0.0001920942],"domain_scores_gemma":[0.9977986,0.0007407481,0.0002171353,0.0004428204,0.0006953059,0.0001053879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003611661,0.0003772512,0.001104046,0.0005221252,0.0001485952,0.0002055717,0.0003203558,0.02337348,0.04495913,0.01926011,0.02956394,0.8798043],"study_design_scores_gemma":[0.0001012056,0.000329937,0.001691164,0.00006476456,0.0001415753,0.00054051,0.0002328461,0.9267582,0.02144491,0.02515987,0.0234102,0.0001247729],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01667224,0.003028484,0.9692029,0.0003429021,0.00031685,0.0003038875,0.001206652,0.006466193,0.00245993],"genre_scores_gemma":[0.1791125,0.002897325,0.7910742,0.0005597529,0.0008765328,0.0008238588,0.01304073,0.000861377,0.01075374],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008478318,"threshold_uncertainty_score":0.01685792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01039318354331234,"score_gpt":0.236154306589306,"score_spread":0.2257611230459937,"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."}}