{"id":"W7134164242","doi":"10.1109/bigdata66926.2025.11401777","title":"Index-Aware Knowledge Grounding of Retrieval-Augmented Generation in Conversational Search for Archival Diplomatics","year":2025,"lang":"","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Key (lock); Focus (optics); Action (physics); Selection (genetic algorithm)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002111612,0.0002750029,0.0004426872,0.00126508,0.0003180642,0.0003069823,0.00079791,0.0001766833,0.000105988],"category_scores_gemma":[0.0002256529,0.0002753751,0.0001888268,0.002254593,0.0002107377,0.00106768,0.0004752208,0.0003572059,0.0000231101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004566777,"about_ca_system_score_gemma":0.00161836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005143575,"about_ca_topic_score_gemma":0.00002781413,"domain_scores_codex":[0.9964117,0.0002678086,0.001442034,0.0004563763,0.0008233821,0.0005987132],"domain_scores_gemma":[0.9974288,0.0006082602,0.000217083,0.0004534921,0.001156963,0.000135347],"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":[0.0008007166,0.001462136,0.02804795,0.002553705,0.0001924263,0.0000046818,0.01539218,0.003183691,0.01036673,0.8295971,0.001640058,0.1067587],"study_design_scores_gemma":[0.002502466,0.000242353,0.02553532,0.000216558,0.00002176506,0.000001642367,0.0004917771,0.9312067,0.03840315,0.0008926741,0.0002434685,0.0002421292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2207663,0.00005202611,0.773818,0.0005613854,0.0008222525,0.001427202,0.00005171218,0.00003342381,0.002467742],"genre_scores_gemma":[0.9912145,0.00004331433,0.005112808,0.0001269648,0.0000964455,0.00003251197,0.0001233612,0.00001054477,0.003239566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.928023,"threshold_uncertainty_score":0.9999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06081781184319278,"score_gpt":0.3447345300433814,"score_spread":0.2839167182001887,"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."}}