system,total_questions,error_rate,avg_latency_s,t1_pass_rate,t1_decomp_schema_rate,t1_citation_grounded_rate,t1_expired_warning_rate,t2_source_routing_acc,t2_alignment_acc,t2_keyword_coverage,t3_relevance_avg,t3_groundedness_avg,t3_completeness_avg
Baseline1_NaiveRAG,30,0.0,3.5287,,,,,,,0.5923,4.4333,2.7333,3.9333
Baseline2_RAGRerank,30,0.0,3.8487,,,,,,,0.5906,4.4333,3.2667,4.0667
ViLexAgent,30,0.0,5.434,1.0,1.0,0.8,1.0,0.8,0.7,0.6356,4.4333,4.4667,3.8333