AI Labs · published 2026-05-29 · methodology v2.1

Claude Opus 4.7 with web search

RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q005-Opus47

What the RLB Specialist Panel found

Finding 5. Claude Opus 4.7 with web search

Question (paraphrased to protect IP): Is PFMI Principle 15's six-month liquid net assets standard still considered adequate, and what do recent CPMI-IOSCO monitoring assessments say about FMI compliance with this requirement?
AI's response: "The 6-month LNAFE standard in PFMI Principle 15 KC 3 remains the formal floor, but CPMI-IOSCO have signalled that it is being actively reconsidered. The Level 3 assessment published as d228 (2025) flagged serious issues of concern"
Regulator's text: FMI should hold liquid net assets funded by equity (LNAFE) equal to at least six months of current operating expenses. [PFMI Principle 15 — paraphrase from primary document]
Why the AI went wrong: The model accurately identified the six-month floor from the core PFMI text but then fabricated specific compliance findings attributed to a 2025 monitoring report, attaching real BIS publication identifiers to claims it could not have retrieved from the underlying documents. The response presents invented monitoring conclusions with the same surface confidence as the correctly recalled base standard, giving no signal to the reader that the two parts of the answer have fundamentally different epistemic foundations.
Cited source(s):
https://www.bis.org/cpmi/publ/d228.htm — Pretextual
https://www.bis.org/cpmi/publ/d229.htm — Pretextual
https://www.regulationtomorrow.com/2025/11/cpmi-iosco-papers-on-management-of... — Pretextual

Impact for this audience

This finding implicates the training data boundary directly: the model correctly recalled the six-month LNAFE floor from the core PFMI text but fabricated specific compliance monitoring findings from a November 2025 document it could not have seen. The citation generator produced real-format BIS URLs without verifying their content, pointing to a gap in the RAG/retrieval grounding layer that should be testable against the BIS publication naming convention.

Next finding → Finding 2. Claude Opus 4.7 with web search

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.

Plain text

RegLeg Specialist Panel (2026). "Claude Opus 4.7 with web search — AI Labs." Citation ID: RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q005-Opus47. RegLegBrief AI Hallucination Research, published 2026-05-29. https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-iosco-pfmi-2012/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-PFMI-2012-v1-005--opus-47-websearch/

APA 7th edition

RegLeg Specialist Panel. (2026). Claude Opus 4.7 with web search [Hallucination finding RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q005-Opus47]. RegLegBrief AI Hallucination Research. https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-iosco-pfmi-2012/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-PFMI-2012-v1-005--opus-47-websearch/

Bluebook / OSCOLA (US + UK legal)

RegLeg Specialist Panel, Claude Opus 4.7 with web search [RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q005-Opus47], RegLegBrief AI Hallucination Research (May 29, 2026), https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-iosco-pfmi-2012/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-PFMI-2012-v1-005--opus-47-websearch/.

BibTeX

@misc{reglegbrief_RLB_H_INT_BIS_CPMI_IOSCO_PFMI_2012_Q005_Opus47,
  author    = {RegLeg Specialist Panel},
  title     = {Claude Opus 4.7 with web search},
  year      = {2026},
  publisher = {RegLegBrief AI Hallucination Research},
  note      = {Hallucination finding Citation ID: RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q005-Opus47},
  url       = {https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-iosco-pfmi-2012/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-PFMI-2012-v1-005--opus-47-websearch/}
}

← Back to case study summary Case study detail →

About Citation IDs →