AI Hallucination ResearchFindings by audienceSectorsInternational / MultilateralRetail BankingTechnology DataDetail › Finding
Retail Banking × Technology Data — International / Multilateral · Last updated 11 Jun 2026 · Hallucination Register
Share / Print X LinkedIn Email

Finding#1, Fedwire hybrid postal address schema over-specification

RLB Citation ID: RLB-F-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q010
What the RLB Specialist Panel found
Question (paraphrased to protect IP)

When did Fedwire implement the CPMI harmonised ISO 20022 data model requirements, and what postal address format does Fedwire require for the hybrid/end-state approach?

RLB's analysis

The model over-specified the mandatory field tier. The implementing body's published FAQ places Building Number, Post Code, and Country Sub-Division in the optional tier; the model elevated them into a more rigid structured-element category that does not match the published specification. This is a schema over-specification failure, the mandatory/optional boundary was shifted toward greater structure than the regulator's own implementation guide defines, which would cause a practitioner applying the model's output to implement a more restrictive address format than required.

AI Head's analysis — what weakness in the AI model caused this

This failure implicates retrieval coverage of implementing-body FAQ layers. When the FRB Services FAQ defining the hybrid/end-state postal address format is not retrieved, the model reconstructs the mandatory/optional field boundary from training, and reconstruction tends toward over-specification — adding Building Number, Post Code, and Country Sub-Division to the mandatory tier where the FAQ places them as optional. The RAG or retrieval glue is not surfacing the implementing body's own technical specification when it conflicts with a more structured internal representation.

References — raw findings (per AI model)
This finding also affects
Cite this finding

Each finding has a stable Citation ID (RLB-F-… for aggregated case-study findings, RLB-H-… for raw per-model hallucinations) — like a DOI, the ID always resolves to the canonical finding even if URLs change.

RLB Citation ID: RLB-F-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q010
Plain text Download
RegLeg Specialist Panel (2026). "Finding#1, Fedwire hybrid postal address schema over-specification — Retail Banking × Technology Data — International / Multilateral." Citation ID: RLB-F-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q010. RegLegBrief AI Hallucination Research, published 2026-06-11. https://reglegbrief.com/regulators/j1/INT/BIS-CPMI/CPMI-ISO-20022-HARMONISATION-UPDATED-2026/sectors/retail_banking/technology_data/finding/INT-BIS-CPMI-INT-001-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-v1-010/
APA 7th edition Download
RegLeg Specialist Panel. (2026). Finding#1, Fedwire hybrid postal address schema over-specification [Hallucination finding RLB-F-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q010]. RegLegBrief AI Hallucination Research. https://reglegbrief.com/regulators/j1/INT/BIS-CPMI/CPMI-ISO-20022-HARMONISATION-UPDATED-2026/sectors/retail_banking/technology_data/finding/INT-BIS-CPMI-INT-001-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-v1-010/
Bluebook / OSCOLA (US + UK legal) Download
RegLeg Specialist Panel, Finding#1, Fedwire hybrid postal address schema over-specification [RLB-F-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q010], RegLegBrief AI Hallucination Research (June 11, 2026), https://reglegbrief.com/regulators/j1/INT/BIS-CPMI/CPMI-ISO-20022-HARMONISATION-UPDATED-2026/sectors/retail_banking/technology_data/finding/INT-BIS-CPMI-INT-001-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-v1-010/.
BibTeX Download
@misc{reglegbrief_RLB_F_INT_BIS_CPMI_ISO_20022_HARMONISATION_UPDATED_2026_Q010,
  author    = {RegLeg Specialist Panel},
  title     = {Finding#1, Fedwire hybrid postal address schema over-specification},
  year      = {2026},
  publisher = {RegLegBrief AI Hallucination Research},
  note      = {Hallucination finding Citation ID: RLB-F-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q010},
  url       = {https://reglegbrief.com/regulators/j1/INT/BIS-CPMI/CPMI-ISO-20022-HARMONISATION-UPDATED-2026/sectors/retail_banking/technology_data/finding/INT-BIS-CPMI-INT-001-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-v1-010/}
}
← Back to case study summary Case study detail →

Every finding on this page compares an AI subject's account of the rule against the regulator's verbatim text from the regulator's own portal. Both are linked. Each delta, its root causes, and impact analysis are documented and published with immutable Citation IDs.