Fabricated Date-and-Format Commitment and Numeric Drift on the CPMI API harmonisation recommendations for cross-border payments. Two frontier AI models tested by the RLB Specialist Panel produced regulator-fluent answers on CPMI's October 2024 d224 report that the panel was able to bind, line-by-line, to regulator-issued source text the AI subjects did not match. The pattern recurs across 2 substrate-bound findings on named partnerships, per-recommendation stakeholder taxonomy, ISO 20022 update language and fast payment system statistics.

The pattern in one line

For operations teams at corporate banking firms, the audit pattern is consistent: the AI subjects answer CPMI questions in the same fluent, structured register they use for verified facts, even when the underlying CPMI source the answer cites was never actually retrieved. The wrong number, the wrong availability claim, the wrong named partnership, and the fabricated date-and-format mandate all arrive in the same prose voice as the AI's correctly-sourced output.

There is no surface signal in the answer that tells the reader which paragraphs are bound to a CPMI publication and which are constructed from category names and adjacent training data. The failure pattern is therefore not primarily a prompt-engineering issue; it is a verification-process issue, and it sits upstream of any tone or formatting fix that operations teams at corporate banking firms apply at the AI drafting stage.

How the RLB Specialist Panel tested this

Questions are prepared by the RLB Specialist Panel based on real practical AI usage in the workflows operations teams at corporate banking firms use AI for. Each question is bound to verbatim regulator-issued source text held as primary substrate before the question is ever issued to a model. The Panel issued each question to two frontier AI models with web search enabled, recorded the answer verbatim with timestamp and model identity, and then bound the answer against the regulator-stated text from CPMI's primary publications.

The primary substrate for this regulation includes the October 2024 d224 report (the master CPMI API harmonisation recommendations and toolkit), CPMI Brief No. 9 (November 2025) on the pre-validation API recommendation and the SARB collaboration, and CPMI speech sp231115 (Tara Rice, November 2023) on the global fast payment system landscape statistics. Findings are only published where the AI answer fails the substrate-binding check against one or more of these primary CPMI publications. Positive observations (correctly-sourced answers, well-calibrated refusals) are not published as findings; only substantive regulator-contradicting errors enter the public audit record.

What the models got wrong

Claude Sonnet 4.6: ISO 20022 structured-address mandate fabricated

Claude Sonnet 4.6 with web search asserted that from November 2026 only structured or hybrid addresses will be permitted in ISO 20022 cross-border payment messages, framed as drawn from the updated CPMI document. The answer is recorded verbatim and cited as RLB-H-INT-BIS-CPMI-API-HARMONISATION-CROSS-BORDER-2024-Q009-Sonnet46, bound to the regulator's actual text:

The CPMI's own description of the update reads: 'The updated version of the report takes into account standardisation and regulatory developments since 2023, provides clarification where market participants had sought further guidance, and sets out the updated and expanded data model in a separate technical annex.' No specific November 2026 cutover commitment is recorded in that source.

The substantive consequence: Vendor due diligence, client briefings and implementation roadmaps that adopt the AI's commitment statement work from a fabricated mandate, with downstream operational decisions, address-format remediation plans and contractual amendments built on a regulator quote that does not exist in the regulator's text.

Claude Opus 4.7: Global FPS count understated by survey-sample substitution

Claude Opus 4.7 with web search stated that the 2025 monitoring survey covers 57 FPS as the most recent CPMI count of operational systems globally. The answer is recorded verbatim and cited as RLB-H-INT-BIS-CPMI-API-HARMONISATION-CROSS-BORDER-2024-Q010-Opus47, bound to the regulator's actual text:

CPMI speech sp231115 (Tara Rice, November 2023) records '70+ domestic fast payment systems currently operational globally', alongside '14 fast payment systems already enabling cross-border exchanges' and '24 systems planning linkages within five years'.

The substantive consequence: A market briefing or strategy memo that quotes 57 understates global connectivity by roughly 20 percent, mis-prioritises corridor strategy, and embeds an authoritative-sounding statistic that the primary source contradicts.

Why this matters for operations teams at corporate banking firms

An operational readiness paper that records a November 2026 structured-ISO-20022-address cutover as a CPMI mandate triggers a remediation programme against a regulator commitment the regulator never made. A capacity-planning briefing that uses 57 as the global FPS count under-sizes corridor expansion against a regulator-stated 70+ universe. An operational risk register update that records 'no SARB involvement' on the pre-validation workstream misses a live regulator-bilateral programme the operations function will be expected to know about. The factual gap, once it enters a deliverable that operations teams at corporate banking firms produce, is durable.

It travels into firm-level institutional records, into client-facing collateral, into supervisory horizon scans and into engagement-letter knowledge bases. It is hard to walk back without quietly issuing a correction, and the supervisory cost of the correction is often higher than the original verification effort would have been.

The regulator's actual position

The regulator-stated positions, drawn verbatim from CPMI's primary publications (d224 October 2024, CPMI Brief No. 9 November 2025, speech sp231115 November 2023), read as follows.

The CPMI's own description of the update reads: 'The updated version of the report takes into account standardisation and regulatory developments since 2023, provides clarification where market participants had sought further guidance, and sets out the updated and expanded data model in a separate technical annex.' No specific November 2026 cutover commitment is recorded in that source.

CPMI speech sp231115 (Tara Rice, November 2023) records '70+ domestic fast payment systems currently operational globally', alongside '14 fast payment systems already enabling cross-border exchanges' and '24 systems planning linkages within five years'.

Each of these passages is held inside the RLB primary substrate against which the AI answer was bound. Where the AI answer states a partnership, a stakeholder assignment, a dated commitment or a numeric figure that contradicts the verbatim regulator text above, the discrepancy is recorded as a substantive finding with an immutable RLB Citation ID.

What this tells us about AI for operations teams at corporate banking firms

For operations functions, the failure pattern is acute because operations teams rely on dated, numbered and explicitly committed regulator statements to drive implementation timing. The models manufacture exactly those commitments in the same register the regulator uses. A runbook update built on an AI-asserted CPMI cutover date triggers real-money remediation against an imaginary mandate. The control point is binding every dated CPMI claim in an operational deliverable to a primary CPMI publication before the deliverable enters change-management.

The taxonomy lens for this audience is straightforward: treat the AI's regulator-quoting prose as a draft to be verified, not as a sourced deliverable to be word-smithed. The verification step has to be explicit, separate from the AI drafting step, and run against a named CPMI publication rather than against general web search.

The four substantive CPMI failure modes documented in this audit (named partnership denial, per-recommendation stakeholder fabrication, ISO 20022 structured-address mandate fabrication, FPS count and operator-split misstatement) are now publicly logged, so the verification step does not need to be open-ended: it can run against the known failure list as a starting point.

What the RLB Specialist Panel is doing about it

The RLB Specialist Panel records each CPMI finding with an immutable RLB Citation ID and binds it to the regulator-issued primary source. The CPMI API Harmonisation for Cross-Border Payments hub at https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-api-harmonisation-cross-border-2024/ is the live record of substrate-bound CPMI AI failure modes that operations teams at corporate banking firms can lift directly into firm-level AI-use risk registers, into client-deliverable verification checklists, and into supervisory horizon scans. The Panel partners with firms, agencies and standards bodies that use AI on CPMI deliverables, surfacing new failure modes against the firm's own actual deliverable types as the CPMI issues further briefs and speeches.

Partnership engagement gives a firm or agency early access to flagged AI failure modes against its own deliverable templates, and a documented audit trail showing that the firm has tested for the failure pattern before a supervisor asks about it.

What operations teams at corporate banking firms teams should do

The action items below are framed for operations teams at corporate banking firms specifically and map onto the four documented failure modes:

• Add a primary-source check on every dated CPMI claim in an operational readiness paper, runbook update or change-request, before the document enters the firm's change-management pipeline.
• Maintain a verified CPMI implementation-milestone register (with named CPMI source per milestone) and reconcile any AI-drafted operational planning text against the register.
• Brief operations leads on the SARB pre-validation partnership and on the actual 70+ FPS / 14 already-cross-border / 24 planned-cross-border CPMI numbers so the operational planning baseline starts from primary-source figures.
• Treat AI-drafted CPMI cutover language as a planning prompt that requires verification, not as a milestone to schedule against.
• Stamp AI-drafted runbooks and operational papers with a sourcing tag identifying primary-source-verified paragraphs against AI-asserted paragraphs.
• Engage with the RLB Specialist Panel partnership track to surface CPMI AI failure modes against the firm's runbook and readiness-paper templates.

Each action is operationally lightweight at the unit-deliverable level and compounds across the function as a control standard. The cost of building the verification step into the AI drafting workflow is consistently lower than the cost of issuing a correction on an AI-drafted deliverable that has already entered firm or supervisory records.

Right of Reply

These findings and associated work have been put up in public with a view of the greater good for the development of a safer AI ecosystem. Any party reading this or any finding on reglegbrief.com may contact us and have an unconditional right of reply; the Specialist Panel will publish any factual correction or contextual response alongside the original finding, with no editorial gatekeeping. Researchers, regulators, and compliance teams with questions on methodology or specific findings can reach the Specialist Panel via the same channel.

Source & Methodology Standards

RegLeg Brief is operated by Verdus Technologies Pte. Ltd. (UEN 201616982R), incorporated in Singapore. The RLB Specialist Panel, with an aggregate of over 60 years of public-policy and industry experience, documents only confirmed hallucination findings, under a methodology that requires a verbatim regulator excerpt for every documented claim. All findings, citation IDs, model outputs, regulator excerpts, and methodology notes are open-access.

Primary source verified: CPMI Report d224, Harmonised application programming interfaces for enhancing cross-border payments (October 2024) · Substrate documents: p_05_GUIDELINE_d218___d230_update__what_changed_from_or_d223.htm, p_10_GUIDELINE_Tara_Rice_speech_Nov_2023___FPS_statisti_d230.htm · CPMI portal: bis.org/cpmi

Citation IDs referenced:

• RLB-H-INT-BIS-CPMI-API-HARMONISATION-CROSS-BORDER-2024-Q009-Sonnet46
• RLB-H-INT-BIS-CPMI-API-HARMONISATION-CROSS-BORDER-2024-Q010-Opus47