Audit Detail

This is the hash-chained record. Each field is hashed and linked to the previous entry — tamper with one, the chain breaks.

Ledger entry

verity_audit_id

018b6048-56bc-4a2f-8f40-c1b339ac7938Verify this entry →

model

gpt-4 (openai)

risk_tier

high

entry_hash

82d46b6b4cccd66129635193f11e224e32515efea7aa704faffb26fb7f64adf1

created_at

3/18/2026, 6:08:13 AM

We just recomputed the hash from the raw data. If it matches, the record is untouched.

Integrity check

Chain valid: Yes

Recomputed entry_hash matches stored: Yes

This is the full reasoning trace: what was requested, which model was selected, what it returned, and whether validation passed.

Execution graph

{
  "graphId": "4e87ccf7-6620-4871-9295-cc0da6ab4c5f",
  "release": {
    "released": true,
    "releasedAt": "2026-03-18T06:08:13.746Z"
  },
  "request": {
    "inputHash": "06aca3d13426d356efdac539e7d787d6b792c7556c11395d9c216e2a6f72d360",
    "receivedAt": "2026-03-18T06:08:13.746Z",
    "riskClassification": "high"
  },
  "validation": {
    "rulesApplied": [
      "policy-1"
    ],
    "failuresDetected": [],
    "fallbackTriggered": false
  },
  "modelExecution": {
    "latencyMs": 2950,
    "promptHash": "06aca3d13426d356efdac539e7d787d6b792c7556c11395d9c216e2a6f72d360",
    "rawOutputHash": "89d31ef21d6027f12108721461571a0e27c90fb82ae43b3db7f56d0897d78322"
  },
  "modelSelection": {
    "reason": "risk-tier match",
    "policyVersion": "v1",
    "selectedModel": "gpt-4"
  }
}