AI Hallucination Research › Regulators › Global standard-setters › INT › BIS-CPMI › CPMI-ISO-20022-HARMONISATION-UPDATED-2026 › White paper › Detail › Finding
AI Labs · Last updated 7 Jun 2026 · methodology vv2.3 · Hallucination Register

Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON

RLB Citation ID: RLB-H-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q006-Sonnet46
What the RLB Specialist Panel found

Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON

  • Question (paraphrased to protect IP): What share of faster payment systems and RTGS systems are currently using ISO 20022, according to CPMI monitoring data from the December 2024 survey?
  • AI's response: "79% of both real-time gross settlement (RTGS) systems and fast payment systems (FPS) either have already implemented ISO 20022 or have concrete plans to do so"
  • Regulator's text: More than three quarters of faster payment systems covered by the survey, and approaching half of RTGS systems, are now using ISO 20022.
  • Why the AI went wrong: The model collapsed two distinct statistics into a single symmetric figure, reporting the same 79% adoption rate for both faster payment systems and RTGS systems. The regulator's survey data shows materially different adoption rates across these two system types, faster payments substantially ahead of RTGS, a disaggregation the model's response erased entirely. The fabricated third-party citation suggests the model's retrieval pulled from a secondary source that had itself misreported the figures, and the model treated that paraphrased summary as authoritative without flagging the discrepancy.
  • Cited source(s):
  • https://www.centralbanking.com/benchmarking/payments/7973047/half-of-central-..., Fabricated
Impact for this audience

This failure mirrors the Opus 4.7 conflation on the same adoption-rate question — the model produced an identical blended 79% figure applied symmetrically to faster payment systems and RTGS systems, where the regulator's record gives two distinct figures that diverge by roughly thirty percentage points. The Sonnet variant adds a fabricated third-party citation pointing to a centralbanking.com URL that does not contain the figure attributed to it, suggesting the retrieval pipeline surfaced a paraphrased secondary source and the model treated that summary as authoritative without flagging the discrepancy.

The cross-model recurrence is the load-bearing signal: where both Opus and Sonnet produce the same composite shape on a subcategory-disaggregated regulator statistic, the gap is in the retrieval ranker's weighting of official-speech channels, not in a single model's calibration.

References — raw findings (per AI model)
This finding also affects
← Previous finding Finding on 'Q010 Probe' for Claude Opus 4.7 with web search ON
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-H-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q006-Sonnet46
Plain text Download 
RegLeg Specialist Panel (2026). "Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON — AI Labs." Citation ID: RLB-H-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q006-Sonnet46. RegLegBrief AI Hallucination Research, published 2026-06-07. https://reglegbrief.com/regulators/j1/int/BIS-CPMI/CPMI-ISO-20022-HARMONISATION-UPDATED-2026/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-v1-006--sonnet-46-websearch/
APA 7th edition Download 
RegLeg Specialist Panel. (2026). Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON [Hallucination finding RLB-H-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q006-Sonnet46]. RegLegBrief AI Hallucination Research. https://reglegbrief.com/regulators/j1/int/BIS-CPMI/CPMI-ISO-20022-HARMONISATION-UPDATED-2026/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-v1-006--sonnet-46-websearch/
Bluebook / OSCOLA (US + UK legal) Download 
RegLeg Specialist Panel, Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON [RLB-H-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q006-Sonnet46], RegLegBrief AI Hallucination Research (June 07, 2026), https://reglegbrief.com/regulators/j1/int/BIS-CPMI/CPMI-ISO-20022-HARMONISATION-UPDATED-2026/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-v1-006--sonnet-46-websearch/.
BibTeX Download 
@misc{reglegbrief_RLB_H_INT_BIS_CPMI_ISO_20022_HARMONISATION_UPDATED_2026_Q006_Sonnet46,
  author    = {RegLeg Specialist Panel},
  title     = {Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON},
  year      = {2026},
  publisher = {RegLegBrief AI Hallucination Research},
  note      = {Hallucination finding Citation ID: RLB-H-INT-BIS-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-Q006-Sonnet46},
  url       = {https://reglegbrief.com/regulators/j1/int/BIS-CPMI/CPMI-ISO-20022-HARMONISATION-UPDATED-2026/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-ISO-20022-HARMONISATION-UPDATED-2026-v1-006--sonnet-46-websearch/}
}
← Back to case study summary Case study detail →
About Citation IDs →

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.