{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005943739,0.0001492675,0.0002355667,0.0003199143,0.0002460697,0.0003885491,0.0007769128,0.00003886845,3.124742e-8],"category_scores_gemma":[0.00003844824,0.0001110498,0.00004184476,0.0009234496,0.00005343814,0.0003804275,0.0003847016,0.0001570576,1.871052e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004833765,"about_ca_system_score_gemma":0.00005142514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001430024,"about_ca_topic_score_gemma":7.399664e-7,"domain_scores_codex":[0.9986761,0.000003807116,0.0002491512,0.0004585657,0.0002336608,0.0003786796],"domain_scores_gemma":[0.9994478,0.00008132168,0.00006960601,0.0001676165,0.0001546349,0.00007899383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001269134,0.00004531195,0.000604619,0.0003924788,0.00003335485,7.08688e-7,0.0003840651,0.0309477,0.02619874,0.9184112,0.00008196018,0.02288718],"study_design_scores_gemma":[0.0001827278,0.00003484351,0.0001133394,0.0002951267,0.000006623703,0.000007875879,0.000008301675,0.9955078,0.003347123,0.0002549218,0.0001187679,0.0001224939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2219382,0.0006828339,0.7754545,0.0001326445,0.001133146,0.0004006161,0.000001217057,0.00009450511,0.0001624386],"genre_scores_gemma":[0.9881936,0.00000443506,0.01140674,0.00006770804,0.00007620281,0.00001777092,3.738468e-8,0.000005903184,0.000227626],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9645602,"threshold_uncertainty_score":0.4528478,"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."}}