OpenChainGraph Suite · CONTRACT A3 · arch #5

Claim Dispute Bundle to PLD Disclosure Pack

Back office, not lifecycle-bound. Two-step product-liability disclosure flow: build a two-sided replay-challenge dossier for a disputed execution claim, then build the disclosure and rebuttal pack from the receipts in that bundle. The pack traces the receipts in the step 1 bundle; the operator is responsible for putting only in-window receipts into the claim, because art-308 does not filter receipts by disputed_window. Step 1's insufficient_evidence and bundle_claim_strength travel with the pack next to step 2's trace_digest and gap_in_window, so a pack built after step 1 reported insufficient_evidence never reads as a complete dossier. Prepared for Directive (EU) 2024/2853, transposition 9 December 2026.

OpenChainGraph · 3 Steps cryptographic mandate Hash-Anchored §4 chain_depth:3 Client-Side · Zero PII
Chain Topology: Claim Dispute Bundle Builder → PLD Disclosure Pack Builder → Agent-Action Audit-Trail Aggregator
§4 Execution Hash · Chain Definition Anchor
execution_hash:computing…
Chain Stages · 3 Steps
1 ROOT node
Claim Dispute Bundle Builder art-307-claim-dispute-bundle-builder
Then the step 2 run takes the step 1 output's receipts unchanged by name and builds the trace digest and rebuttal mapping from them
MCP Call · build_claim_dispute_bundle
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "build_claim_dispute_bundle",
    "arguments": {}
  },
  "id": 1
}
↓
2 STAGE 2 node
PLD Disclosure Pack Builder art-308-pld-disclosure-pack-builder
Then the disclosure and rebuttal pack is built from the bundle's receipts, with gap_in_window flagged when the receipt set is empty, and step 1's insufficient_evidence and bundle_claim_strength shown next to trace_digest and gap_in_window
MCP Call · build_pld_disclosure_pack
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "build_pld_disclosure_pack",
    "arguments": {}
  },
  "id": 1
}
↓
3 TERMINAL node
Agent-Action Audit-Trail Aggregator cry-05-agent-action-audit-trail-aggregator
Then the session receipts are aggregated into the session receipt
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: A product defect is alleged and disclosure is requested. Does the pack trace the bundle's receipts, and is there a gap we must admit?
Run the AINumbers MCP tool `run_chain` with {"chain":"claim-dispute-bundle-to-pld-disclosure-pack"} and read `art-308-pld-disclosure-pack-builder.gap_in_window`.
Re-run with `inputs` for `art-308-pld-disclosure-pack-builder`, reusing the values that result echoed, with `receipts` changed so remove every receipt and watch trace_digest go null and gap_in_window go true. 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/claim-dispute-bundle-to-pld-disclosure-pack.html