SOX 404 control-test evidence cycle: population, sample, and per-item test results reconcile into ONE test-conclusion artifact (coverage, exception count vs tolerable deviation, test conclusion). gate_status and any deficiency candidate are recorded per the §27 Human Accountability vocabulary: the tester is the §27.1 preparer, every conclusion requires a reviewer sign-off, and deficiency severity classification is a separate reviewer approval record; both recorded now, enforced once HA-RETRO-1's runtime gating is wired to this chain. Never a filed submission.
compose_control_test_evidence{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "compose_control_test_evidence",
"arguments": {}
},
"id": 1
}
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: The SOX test round just closed. Did the key control hold within the tolerable exceptions we declared?
Run the AINumbers MCP tool `run_chain` with {"chain":"icfr-control-test-cycle"} and read `art-461-control-test-evidence-composer.within_tolerance`.
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/icfr-control-test-cycle.html