{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005615639,0.001509276,0.001020876,0.004031645,0.001152855,0.00297688,0.00208746,0.001410972,0.008511818],"category_scores_gemma":[0.03092735,0.0005239535,0.001062594,0.002571679,0.0009590618,0.004662331,0.003682819,0.001408532,0.006113503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000948071,"about_ca_system_score_gemma":0.002650666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001926239,"about_ca_topic_score_gemma":0.002628586,"domain_scores_codex":[0.9933661,0.003151296,0.0004759953,0.001313537,0.00148399,0.0002090658],"domain_scores_gemma":[0.9829868,0.008457114,0.0009876046,0.003372485,0.003704082,0.0004918914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000882256,0.0004030469,0.002377772,0.001267148,0.0001278949,0.0009622921,0.004063225,0.01010025,0.06444348,0.01932487,0.01905187,0.8769959],"study_design_scores_gemma":[0.0005892271,0.001030379,0.003481462,0.0002951234,0.0003972653,0.002351654,0.004251604,0.6382912,0.1480142,0.07812476,0.1228369,0.0003361001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01524789,0.000279644,0.9633266,0.0006047927,0.0001298113,0.0006889868,0.000666909,0.01608677,0.002968626],"genre_scores_gemma":[0.1159861,0.000172022,0.8742648,0.0002497231,0.0001027557,0.0006444821,0.002160297,0.001284419,0.005135368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008511818,"threshold_uncertainty_score":0.02969867,"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."}}