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

5833f43b-7e10-4d41-9dd9-d127478ba3ccVerify this entry →

model

gpt-4 (openai)

risk_tier

high

entry_hash

fd43681b399fc0b52bbc1c3b88a32a7827d130de58ea9641cec3f5443faf5396

created_at

3/17/2026, 7:47:35 PM

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": "6fbdb6ad-a6f3-4771-8ea9-dc92ca57b694",
  "release": {
    "released": true,
    "releasedAt": "2026-03-17T19:47:35.131Z"
  },
  "request": {
    "inputHash": "06aca3d13426d356efdac539e7d787d6b792c7556c11395d9c216e2a6f72d360",
    "receivedAt": "2026-03-17T19:47:35.131Z",
    "riskClassification": "high"
  },
  "validation": {
    "rulesApplied": [
      "policy-1"
    ],
    "failuresDetected": [],
    "fallbackTriggered": false
  },
  "modelExecution": {
    "latencyMs": 1962,
    "promptHash": "06aca3d13426d356efdac539e7d787d6b792c7556c11395d9c216e2a6f72d360",
    "rawOutputHash": "46e513fd38fff7c915e8222efeb5ab18cb830bcf8a27985fa16795f95dd25c06"
  },
  "modelSelection": {
    "reason": "risk-tier match",
    "policyVersion": "v1",
    "selectedModel": "gpt-4"
  }
}