AI Hallucination Research › Regulators › Global standard-setters › INT › BIS-CPMI › CPMI-IOSCO-PFMI-2012 › White paper › Detail › Finding
AI Labs · published 2026-05-29 · methodology v2.1

Claude Opus 4.7 with web search

RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q021-Opus47
What the RLB Specialist Panel found
  • Question (paraphrased to protect IP): What has the CPMI and associated authorities said about whether DLT-based systems meet PFMI settlement finality requirements, and when were these statements made?
  • AI's response: "CPMI's most directly on-point statements about DLT and settlement finality come from the February 2017 analytical framework 'Distributed ledger technology in payment, clearing and settlement: an analytical framework' (d157)."
  • Regulator's text: [Cœuré, June 2018] "Current crypto assets still fail to ensure clear and legally certain settlement finality." "The underlying DLT remains immature, costly to maintain and possibly prone to vulnerabilities."
  • Why the AI went wrong: The model identified the 2017 CPMI analytical framework as the primary reference for DLT and settlement finality, which is a reasonable recall from training data but does not capture the more direct senior-official statements made in 2018 that addressed the finality question specifically. The answer reflects the model's training-weighted salience (the 2017 document is widely cited) rather than the most responsive source for the question as framed. No citations were produced.
  • Cited source(s):
Impact for this audience

The model's response reflects training-weighted salience rather than the most responsive source for the question: it anchored on the most frequently cited DLT document in its training data rather than identifying the more directly responsive senior-official statements. This is a retrieval-relevance failure rather than a factual fabrication, but it would mislead a user seeking the most current and directly applicable CPMI position on DLT finality.

← Previous finding Finding 6. Claude Opus 4.7 with web search Next finding → Finding 8. 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-Q021-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-v1-021--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-Q021-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-v1-021--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-Q021-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-v1-021--opus-47-websearch/.
BibTeX 
@misc{reglegbrief_RLB_H_INT_BIS_CPMI_IOSCO_PFMI_2012_Q021_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-Q021-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-v1-021--opus-47-websearch/}
}
← Back to case study summary Case study detail →
About Citation IDs →