OpenChainGraph Suite · CONTRACT A3 · arch #5

IRRBB NMD Ladder SOT EVE Check

Check interest rate risk in the banking book in three independent runs plus a session receipt: map non-maturity deposit balances into a bucketed net repricing gap schedule under a caller-declared behavioral allocation (ART-442), sweep the prescribed US parallel shock ladder over that schedule and name the rung with the lowest delta-EVE (ART-369), then compare that worst delta-EVE against 15 percent of Tier 1 capital as a ladder-based proxy outlier indication (ART-184), closing with a session receipt aggregating the run execution hashes (CRY-05). All balances, allocations, betas, gaps, and capital are caller-supplied inputs; each run is an independent recompute from its own declared inputs. This chain is an analytical check and a comparison against a threshold under a stated ladder.

OpenChainGraph · 4 Steps cryptographic mandate Hash-Anchored §4 chain_depth:4 Client-Side · Zero PII
Chain Topology: NMD Behavioral Repricing Mapper → Rate Shock Ladder Replay → IRRBB SOT EVE Evaluator → Agent-Action Audit-Trail Aggregator
§4 Execution Hash · Chain Definition Anchor
execution_hash:computing…
Chain Stages · 4 Steps
1 ROOT node
NMD Behavioral Repricing Mapper art-442-nmd-behavioral-repricing-mapper
Maps caller-declared non-maturity deposit segment balances into a bucketed net repricing gap schedule using a caller-declared behavioral allocation and a deposit beta. The schedule uses the bucket keys on_1m, m1_y1, y1_y3, y3_y5, y5_y10, y10_plus, the same keys the step 2 run declares for its repricing gaps. No decay curve is supplied by this step.
MCP Call · map_nmd_behavioral_repricing
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "map_nmd_behavioral_repricing",
    "arguments": {}
  },
  "id": 1
}
↓
2 STAGE 2 node
Rate Shock Ladder Replay art-369-run-rate-shock-ladder
Sweeps the prescribed parallel magnitudes (+100, +200, +300, +400 basis points and their negatives) over a bucketed repricing gap schedule, reporting a duration-weighted delta-EVE leg and a 12-month cumulative-gap delta-NII leg per shock, with worst_scenario naming the rung with the lowest delta-EVE. The schedule in the chain page worked example is the step 1 schedule, declared again with the same bucket keys. worst_scenario reads as a ladder magnitude, for example parallel_down_400bp.
MCP Call · run_rate_shock_ladder
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "run_rate_shock_ladder",
    "arguments": {}
  },
  "id": 1
}
↓
3 STAGE 3 node
IRRBB SOT EVE Evaluator art-184-irrbb-sot-eve-evaluator
Compares the worst delta-EVE cited from the step 2 run against 15 percent of caller-declared Tier 1 capital and reports a ladder-based proxy outlier indication. The step 3 run takes worst_delta_eve as a caller-passed field into eve_shock.worst_delta_eve, since the step 3 node declared predecessor is art-183, and the step 2 to step 3 link is a caller field pass. In the chain page worked example the step 2 run reports worst_delta_eve -246200 and the step 3 run compares it against Tier 1 capital 1000000, giving 24.62 percent and eve_outlier true as a ladder-based proxy outlier indication.
MCP Call · evaluate_irrbb_sot_eve
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "evaluate_irrbb_sot_eve",
    "arguments": {}
  },
  "id": 1
}
↓
4 TERMINAL node
Agent-Action Audit-Trail Aggregator cry-05-agent-action-audit-trail-aggregator
Produces session_receipt_root, the Merkle root over the run execution hashes (final stage)
MCP Call · aggregate_execution_receipts
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "aggregate_execution_receipts",
    "arguments": {}
  },
  "id": 1
}
Export Artifacts
Download the §4 chain definition artifact (hash-anchored composite JSON) or the §13.11 W3C Verifiable Credentials view. Both derive from the chain definition. Available after hash computation.

Ask your agent

Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this whole workflow on the server and check one field that answers a real question.

Question: Under the US parallel ladder, what is the ladder-based proxy outlier indication against 15 percent of Tier 1 capital?
Run the AINumbers MCP tool `run_chain` with {"chain":"nmd-ladder-sot-eve-check"} and read `art-184-irrbb-sot-eve-evaluator.eve_outlier`.
Re-run with `inputs` for `art-184-irrbb-sot-eve-evaluator`, reusing the values that result echoed, with `capital` changed so Tier 1 capital is larger. Compare the same field.
Verify: call `verify_execution_hash` (https://mcp.ainumbers.co/mcp) with `claimed_hash` set to `composite_execution_hash` and the full `composite_artifact`.
Ledger, for a human re-check: https://ledger.ainumbers.co/
PII rule: send synthetic or anonymised inputs only. The MCP server runs these kernels and logs no payloads.
Chain page: https://ainumbers.co/chaingraph/chains/nmd-ladder-sot-eve-check.html