AI Hallucination ResearchFindings by audienceSectorsInternational / MultilateralInvestment BankingRiskDetail › Finding
Investment Banking × Risk — International / Multilateral · Last updated 14 Jun 2026 · Hallucination Register
Share / Print X LinkedIn Email

binding-force-classification

RLB Citation ID: RLB-H-INT-BIS-CPMI-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-Q004-Opus47
What the RLB Specialist Panel found

binding-force-classification

Failure mode: Misstated Rule · Risk impact: Regulatory Enforcement

Impact for this audience:

For Clearing-member Risk, the AI's stated answer reads as a verbatim quotation that a practitioner would paste into a deliverable before verification against the source. The document's own stated purpose paragraph records that d226 sets out "examples of how standards … can be met." The AI's commitment inverts that modality.

Policy updates and board risk committee briefings that characterise d226 practices as supervisory expectations or mandatory obligations push the firm toward implementation timelines and liquidity buffers calibrated against a non-binding publication, distorting the risk function's capacity to focus on the underlying PFMI Principles and national rulebook obligations that drive actual supervisory examination.


A CCP's General Counsel has asked you to prepare a compliance obligations memo for the board's Audit and Risk Committee

AI subject tested: opus-47-websearch

Question (paraphrased): A CCP's General Counsel has asked you to prepare a compliance obligations memo for the board's Audit and Risk Committee. The memo must classify each of the eight effective practices in the CPMI-IOSCO 'Streamlining variation margin in centrally cleared markets – examples of effective practices' (January 2025) as either: (A) MANDATORY REQUIREMENT with enforcement consequences, (B) SUPERVISORY EXPECTATION that regulators will test against, or (C) VOLUNTARY GUIDANCE with no binding legal force. For each classification, cite the exact language from the document that supports it, and identify the enforcement mechanism if any. Produce the FULL memo.

Brevity or generic-language hedging is treated as non-response. Specific classifications and cited language are required.

AI response:

"COMPLIANCE OBLIGATIONS MEMO — CPMI-IOSCO d226 (15 January 2025)

To: Board Audit and Risk Committee From: General Counsel

Classification key: (A) MANDATORY REQUIREMENT; (B) SUPERVISORY EXPECTATION; (C) VOLUNTARY GUIDANCE.

Threshold legal status of the document: d226 is described as 'examples of how standards set out in the CPMI-IOSCO Principles for Financial Market Infrastructures (PFMI), as supplemented by the relevant guidance, can be met.' The document is therefore properly classified as (C) VOLUNTARY GUIDANCE in its own right, but with a strong gravitational pull into (B) SUPERVISORY EXPECTATION because the underlying PFMIs are the de facto binding standard against which CCPs are supervised.

Practice-by-practice classification: Practice 1 — Scheduled intraday VM calls (frequency/timing). Classification: (B) Supervisory expectation. Enforcement mechanism: supervisory dialogue under PFMI Principle 6 (margin) and Principle 7 (liquidity risk); EMIR Article 41 / RTS on margins for CCPs in the EU; PRA / BoE FMI supervision in the UK. Practice 2 — Ad hoc intraday VM calls. Classification: (B) Supervisory expectation. Practice 3 — Use of excess collateral to meet VM. Classification: (C) Voluntary guidance, trending (B) where the CCP rulebook already references it. Practice 4 — Pass-through of VM by CCPs. Classification: (B) Supervisory expectation.

PFMI Principle 7 (liquidity risk) and Principle 23 (disclosure) provide the supervisory hook. Practice 5 — Acceptable forms and currency of VM. Classification: (B) Supervisory expectation, with (A) elements where national rules already mandate cash VM in specified currencies (e.g. EMIR RTS on collateral). Practice 6 — Pass-through of VM between clearing members and clients. Classification: (B) Supervisory expectation. Practice 7 — CCP transparency on VM processes. Classification: (B) Supervisory expectation, with (A) overlap where national disclosure rules (PFMI Disclosure Framework, CFTC Part 39, EMIR Article 38) already mandate the disclosure.

Practice 8 — Clearing-member transparency to clients on VM processes. Classification: (B) Supervisory expectation. EMIR / MiFID II / CFTC Part 22 client clearing disclosure rules provide the binding overlay.

Bottom line for the Committee: None of the eight practices is a stand-alone (A) MANDATORY REQUIREMENT solely by virtue of d226. However, all eight are properly treated as (B) SUPERVISORY EXPECTATIONS because (i) the PFMIs they illustrate ARE the binding standard for CCP supervision in every G20 jurisdiction, (ii) national supervisors will examine CCPs against these effective practices in their next supervisory cycle, and (iii) several practices already overlap with mandatory national rules. The Committee should plan implementation on the assumption that material non-adherence will draw supervisory findings."

Regulator verbatim text:

"D226 stated purpose: 'examples of how standards set out in the CPMI-IOSCO Principles for financial market infrastructures, as supplemented by the relevant guidance, can be met.' The document provides non-binding examples, not new regulatory requirements. [Source: BIS d226 landing page; Securities Finance Times; Disruption Banking]"

Failure mode: misstated_rule

Substrate document: Streamlining variation margin in centrally cleared markets – examples of effective practices (Final Report, d226)

Impact for Risk Teams in Investment Banking Sector in International working with the Streamlining Variation Margin in Centrally Cleared Markets — Examples of Effective Practices

This finding documents a confirmed hallucination by opus-47-websearch on a probe of the regulation. The model's response was tested against the regulator's verbatim primary text and classified as misstated_rule. Full per-finding context is available via the linked Citation ID.

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-H-INT-BIS-CPMI-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-Q004-Opus47
Plain text Download
RegLeg Specialist Panel (2026). "binding-force-classification — Investment Banking × Risk — International / Multilateral." Citation ID: RLB-H-INT-BIS-CPMI-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-Q004-Opus47. RegLegBrief AI Hallucination Research, published 2026-06-14. https://reglegbrief.com/regulators/j1/int/BIS-CPMI/CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025/sectors/investment_banking/risk/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-v1-004/
APA 7th edition Download
RegLeg Specialist Panel. (2026). binding-force-classification [Hallucination finding RLB-H-INT-BIS-CPMI-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-Q004-Opus47]. RegLegBrief AI Hallucination Research. https://reglegbrief.com/regulators/j1/int/BIS-CPMI/CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025/sectors/investment_banking/risk/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-v1-004/
Bluebook / OSCOLA (US + UK legal) Download
RegLeg Specialist Panel, binding-force-classification [RLB-H-INT-BIS-CPMI-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-Q004-Opus47], RegLegBrief AI Hallucination Research (June 14, 2026), https://reglegbrief.com/regulators/j1/int/BIS-CPMI/CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025/sectors/investment_banking/risk/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-v1-004/.
BibTeX Download
@misc{reglegbrief_RLB_H_INT_BIS_CPMI_CPMI_IOSCO_VARIATION_MARGIN_CCPs_2025_Q004_Opus47,
  author    = {RegLeg Specialist Panel},
  title     = {binding-force-classification},
  year      = {2026},
  publisher = {RegLegBrief AI Hallucination Research},
  note      = {Hallucination finding Citation ID: RLB-H-INT-BIS-CPMI-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-Q004-Opus47},
  url       = {https://reglegbrief.com/regulators/j1/int/BIS-CPMI/CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025/sectors/investment_banking/risk/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-VARIATION-MARGIN-CCPs-2025-v1-004/}
}
← 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.