Compares caller-selected CPMI-IOSCO public quantitative disclosure (PQD) fields across FICC and ICE using a manually-transcribed, source-cited fixture dataset. It is never a live feed and never scraped (no CCP publishes these fields machine-readably). FICC and ICE do not disclose the same field set: a field one side does not publish is reported unavailable, never interpolated or defaulted to zero. Optionally flags a caller-declared threshold breach, evaluated per entity. This is comparison arithmetic and delta reporting only, with no ranking, no better/worse scoring language, and no forecasting. Emits a hash-anchored OpenChainGraph v0.4 artifact.
The demo below is already loaded, so press Run to see a cross-CCP comparison with a threshold flag. Known CCPs: FICC (divisions GSD, MBSD, NSCC); ICE (clearing houses ICC, ICEU, ICUS). CME and LCH are named in the spec but not built in this fixture.
It does not assess CCP soundness, capital adequacy, or resolvability, and produces no ranking or better/worse judgment: AINumbers is not positioned to make that call. It does not pull live data from any CCP; every figure is a manually-transcribed public disclosure, refreshed by hand per quarter. It does not cover CME or LCH, which are both named in the CCP-core spec but not built into this fixture; selecting either as an entity yields an unknown-CCP rejection, never a fabricated figure. It does not recompute a waterfall, size a default fund, or track a margin call: other nodes in the CCP-core family do that.
Part of the CCP-core clearing-primitives family: default-fund Cover-2 sizing, default-waterfall recompute, member margin-call lifecycle, and client-porting-check nodes ship alongside this one as the family completes. Not a duplicate of any existing margin/clearing node; see the reuse check in CCP-CORE-BUILD-SPEC.md §2.
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.
Run the AINumbers MCP tool `compare_cross_ccp_pqd_fields`. Task: Compare a caller-selected set of CPMI-IOSCO public quantitative disclosure (PQD) fields across FICC and ICE using a manually-transcribed, source-cited fixture dataset -- backtest coverage and largest margin deficiency per FICC division (GSD, MBSD, NSCC), and default fund requirement, Cover-2 peak stress loss, and total initial margin required per ICE clearing house (ICC, ICEU, ICUS), plus a CCP-level ICE skin-in-the-game total.
Call it with arguments: {"policy_parameters":{"entity_a":{"ccp":"FICC","division":"GSD"},"entity_b":{"ccp":"FICC","division":"NSCC"},"fields":["backtest_coverage_pct","largest_deficiency_usd"]}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-528-cross-ccp-pqd-comparator.html#p=v1.H4sIAAAAAAAA_wGUAGv_eyJlbnRpdHlfYSI6eyJjY3AiOiJGSUNDIiwiZGl2aXNpb24iOiJHU0QifSwiZW50aXR5X2IiOnsiY2NwIjoiRklDQyIsImRpdmlzaW9uIjoiTlNDQyJ9LCJmaWVsZHMiOlsiYmFja3Rlc3RfY292ZXJhZ2VfcGN0IiwibGFyZ2VzdF9kZWZpY2llbmN5X3VzZCJdff8UrH2UAAAA