AI Hallucination ResearchRegulatorsGlobal standard-settersINTBIS-CPMICPMI-IOSCO-PFMI-2012White paperDetail › Finding
AI Labs · updated 2026-05-29 · methodology v2.1

Finding on 'Q027 Probe' for Claude Sonnet 4.6 with web search ON

RLB Citation ID: RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q027-Sonnet46
What the RLB Specialist Panel found

Finding on 'Q027 Probe' for Claude Sonnet 4.6 with web search ON

  • Question (paraphrased to protect IP): What specific text, assessment ratings terminology, or paragraph cross-references appear in the IOSCO co-published version of the CPMI-IOSCO disclosure framework and assessment methodology for financial market infrastructures?
  • AI's response: "I do not have verbatim access to the PDF at https://www.iosco.org/library/pubdocs/pdf/IOSCOPD396.pdf… I cannot provide specific verbatim text, exact thresholds, paragraph numbers, or precise named entities from the IOSCOPD396 PDF itself."
  • Regulator's text: [Not provided — verbatim-access question]
  • Why the AI went wrong: The model correctly declined to produce verbatim content from a PDF it acknowledged it could not access. The refusal is appropriately scoped. The cited URL maps to the inaccessible PDF — the same pattern of citing acknowledged-inaccessible sources seen across this model's verbatim-access findings, which represents a mild but consistent presentation inconsistency.
  • Cited source(s):
  • https://www.iosco.org/library/pubdocs/pdf/IOSCOPD396.pdf — Pretextual
Impact for this audience

Citation-alongside-refusal on the IOSCO disclosure framework and assessment methodology. Combined with finding 9 (where Opus 4.7 miscounted the rating scale categories), this finding establishes that the assessment methodology document is not reliably accessible to either model — which means any model-produced compliance assessment against PFMI standards is operating on reconstructed rather than retrieved criteria.

← Previous finding Finding on 'Q026 Probe' for Claude Sonnet 4.6 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-IOSCO-PFMI-2012-Q027-Sonnet46
Plain text Download
RegLeg Specialist Panel (2026). "Finding on 'Q027 Probe' for Claude Sonnet 4.6 with web search ON — AI Labs." Citation ID: RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q027-Sonnet46. 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-l3-027--sonnet-46-websearch/
APA 7th edition Download
RegLeg Specialist Panel. (2026). Finding on 'Q027 Probe' for Claude Sonnet 4.6 with web search ON [Hallucination finding RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q027-Sonnet46]. 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-l3-027--sonnet-46-websearch/
Bluebook / OSCOLA (US + UK legal) Download
RegLeg Specialist Panel, Finding on 'Q027 Probe' for Claude Sonnet 4.6 with web search ON [RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q027-Sonnet46], 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-l3-027--sonnet-46-websearch/.
BibTeX Download
@misc{reglegbrief_RLB_H_INT_BIS_CPMI_IOSCO_PFMI_2012_Q027_Sonnet46,
  author    = {RegLeg Specialist Panel},
  title     = {Finding on 'Q027 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-IOSCO-PFMI-2012-Q027-Sonnet46},
  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-l3-027--sonnet-46-websearch/}
}
← 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.