AI4OfficialStats: Audit Statistical Fidelity of AI-Mediated Official Statistics
Provides deterministic tools for auditing whether artificial
intelligence systems preserve the numerical, semantic, contextual,
temporal, geographic, unit, provenance, revision, transformation, and
uncertainty properties of official statistics. Structured reference
statistics and machine-generated claims can be compared using
non-compensatory critical-error rules, weakest-link and geometric fidelity
summaries, provenance graphs, and portable SHA-256 proof bundles. The
package provides bounded connectors for official statistical services and
an extensible HTTPS JSON API registry. Prompt perturbation, statistical
red-team generation, minimal-pair tests, and benchmark data support
reproducible evaluation of generative, retrieval-augmented, and agentic
statistical systems. An embedded alignment layer maps claim-level controls
to relevant activities of the Generic Statistical Business Process Model
(GSBPM) 5.2, including Analyse, Disseminate, Evaluate, Quality Management,
and Metadata Management. The GSBPM alignment follows United Nations
Economic Commission for Europe (2025) "Generic Statistical Business
Process Model (GSBPM) version 5.2"
<https://unece.org/statistics/gsbpm-v5.2>.
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=AI4OfficialStats
to link to this page.