{"id":"W4410436552","doi":"10.1142/s1793351x25440015","title":"Translative Research Assistant: A Retrieval-Augmented Generation Pipeline Refinement with Keyword Extraction Using Extended Scalable Betweenness Centrality","year":2025,"lang":"en","type":"article","venue":"International Journal of Semantic Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Betweenness centrality; Computer science; Pipeline (software); Scalability; Information retrieval; Centrality; Keyword extraction; Keyword search; Artificial intelligence; Data mining; Database","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002497336,0.0001715623,0.0003236867,0.0008640413,0.0002684593,0.0003178355,0.0009074156,0.0000629319,0.00001133091],"category_scores_gemma":[0.0001865462,0.0001476363,0.0001228385,0.001206747,0.0000820561,0.000807934,0.0001925596,0.0005066156,9.520692e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006389716,"about_ca_system_score_gemma":0.000274336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006781174,"about_ca_topic_score_gemma":0.0000350539,"domain_scores_codex":[0.9966521,0.0003082676,0.0009567877,0.0003624432,0.00141015,0.0003102954],"domain_scores_gemma":[0.9958493,0.0002985484,0.0006900746,0.0002686775,0.00282048,0.00007298157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001282187,0.001979792,0.01165865,0.00014718,0.002397573,0.0008227039,0.003335479,0.06217333,0.4510601,0.03281798,0.001003857,0.4313211],"study_design_scores_gemma":[0.001247882,0.0001502795,0.004581675,0.001032069,0.00008087803,0.0001327607,0.0001821456,0.9004372,0.08729305,0.004085945,0.0005645124,0.0002115483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1995044,0.0001512814,0.7978556,0.0017302,0.0003907878,0.0001346556,0.0000013078,0.00003858751,0.000193201],"genre_scores_gemma":[0.8567918,0.00003169501,0.1427682,0.00005664191,0.0002522494,6.449401e-7,0.000004572117,0.000008324046,0.00008585563],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8382639,"threshold_uncertainty_score":0.6020432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07189166716247476,"score_gpt":0.4239653447684794,"score_spread":0.3520736776060046,"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."}}