OpenChainGraph Suite · CONTRACT A3 · arch #5

Trade Document-Set Integrity & Consistency

Note (dated 2026-08-04): a chain composes independent computations performed in an analytical order. No step's output is carried into the next step by the execution model; each step computes from its own declared inputs. This is true of every chain on this site, including chains whose per-step copy below reads as a data handoff.

W-C. Cross-document consistency + Merkle provenance (ART-55) -> independent Merkle re-verification (cry-04) -> invoicing/volume anomaly monitoring (ml-03). Detects inconsistent or tampered trade-document sets.

OpenChainGraph · 3 Steps risk control Hash-Anchored §4 chain_depth:3 Client-Side · Zero PII
Chain Topology — Trade Document Provenance & Consistency Verifier → Merkle Batch Verifier → Time-Series Anomaly Detector
§4 Execution Hash · Chain Definition Anchor
execution_hash:computing…
Chain Stages · 3 Steps
1 ROOT · D0 node
Trade Document Provenance & Consistency Verifier art-55-trade-document-provenance-verifier
merkle_root and mismatches (H1) feed the batch verifier
MCP Call · verify_trade_document_set
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "verify_trade_document_set",
    "arguments": {}
  },
  "id": 1
}
↓
2 D2 node
Merkle Batch Verifier cry-04-merkle-batch-verifier
verified integrity (H2) feeds the anomaly detector
MCP Call · verify_merkle_batch
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "verify_merkle_batch",
    "arguments": {}
  },
  "id": 1
}
↓
3 TERMINAL · D3 node
Time-Series Anomaly Detector ml-03-timeseries-anomaly-detector
Exports composite integrity artifact with execution_hash (H3), final stage
MCP Call · detect_timeseries_anomalies
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "detect_timeseries_anomalies",
    "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 — no new hash is minted. 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: Our trade doc set runs through a money-laundering red-flag screen. Which periods get flagged as outliers, and what does tightening the z threshold do to that count?
Run the AINumbers MCP tool `run_chain` with {"chain":"digital-trade-doc-integrity"} and read `ml-03-timeseries-anomaly-detector.anomalies_flagged`.
Re-run with `inputs` for `ml-03-timeseries-anomaly-detector`, reusing the values that result echoed, with `zThreshold` set to 1. 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/digital-trade-doc-integrity.html