arXiv cs.CY· Andres Cruz Degante (Universidad Aut\'onoma de Occidente)·· 11 小时前AI 评分35
面向公共行政的受治理主权 RAG：墨西哥 Tlaxcala 州公民服务门户的三方认知路由与确定性数值校验
Governed Sovereign RAG for Public Administration: Tripartite Epistemic Routing, Facet-Guided Clarification, and Deterministic Numeric Verification in Citizen Services
AI 导读
墨西哥 Tlaxcala 州在官方门户部署受治理的主权 RAG 系统，覆盖 1,143 项办事流程与 924 个办事机构目录，通过三方认知门在直接回答、引导澄清与拒答之间路由。
正文
Abstract:Deploying conversational assistants at government service desks faces a tension between regulatory certainty (zero tolerance for invented fees), data sovereignty prohibiting commercial clouds, and high rates of underspecified or out-of-jurisdiction citizen queries. We present and evaluate a governed, sovereign Retrieval-Augmented Generation (RAG) architecture deployed on the official portal of the State of Tlaxcala, Mexico (this http URL), covering 1,143 procedures and a decoupled directory of 924 offices. The system governs interactions via three pillars: (1) a two-stage tripartite epistemic gate (clarify_policy and a Boltzmann distribution over AnyJev) arbitrating among answering (SPECIFIC), facet-guided clarification (CLARIFY), and abstaining (ABSTAIN); (2) a post-generation deterministic numeric verifier (verify_numeric_guardrail) with SHA-256 cache invalidation ensuring every generated fee or validity figure belongs to the retrieved official record; and (3) an empirical evaluation across 380 organic production traces (8 weeks) and a 200-query stratified benchmark (5-fold CV: 86.41% +/- 7.50%). In production, 89.47% of traffic is resolved at Level 0 via deterministic templates without free generation (global p50 = 0.665 s; direct L0 p50 = 0.445 s; slow-tail p95 = 30.412 s under CPU queuing), with 0/40 fiscal amount hallucinations observed in Level 1 (95% bound <= 8.81%). On the benchmark, the system achieves 86.50% strict Top-1 accuracy (+10.00 pp over a binary neural gate, p = 0.00453, p_Holm = 0.01172), pairing a 93.00% conditional safe upper bound with a 70.87% dropout-adjusted effective resolution after accounting for 53.33% citizen drop-off in clarification menus.
| Comments: | 19 pages, 5 figures, 6 tables. Deployed in production at SEDECO/CEMERT, State of Tlaxcala, Mexico |
| Subjects: | Computers and Society (cs.CY); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.36561 [cs.CY] |
| (or arXiv:2610.36561v1 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36561 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andres Cruz Degante [view email]
[v1]
Tue, 27 Oct 2026 03:09:12 UTC (3,601 KB)
来源：arXiv cs.CY · arxiv.org