RegBench
Exam pack · NAIC AI Risk Evaluation Supplement v6.0 (exposure draft, 16 Oct 2026); v7.0 pending adoption vote, Fall National Meeting

Bluebonnet Mutual Insurance Company (fictional)

NAIC code DEMO-10101 · period 2026-07-01 to 2026-10-29 · TX · built 2026-10-30 11:26
Pack identifier
pack_e922bb504177
Pack hash (on ledger #1374)
bf5322daeb3c9b2cb90702348c2d034e9e6003421ef51a98aa57e7ae9a7363ca
Engine
regbench-engine/0.4.0 · rules 2026.10+dbe5ddf6 · corpus 2026-10-30-5f07c521
Totals
432 assessments · 402 case files · 4 high-risk models
Confidentiality
Produced for the requesting state's examination or inquiry; to be held confidential under that state's authority. The carrier may assert trade-secret protection over model documentation it attaches.

Download JSON Print

Exhibit A · use of AI Exhibit B · AIS Program Exhibit C · high-risk models Exhibit D · model data RegBench disclosure Ledger

Ledger verification at pack time

Chain verified: 689 entries; head hash c752c0f7f51e98ae87877dbde1535b67ce098843958664ad389137e2596e607b

Independent verification procedure

  1. Export the carrier's ledger (seq, ts, kind, ref_id, payload_hash, prev_hash, hash).
  2. Confirm the first entry's prev_hash is sixty-four zeros.
  3. For each entry, recompute SHA-256 of 'prev_hash|ts|kind|ref_id|payload_hash' and compare with hash; confirm prev_hash equals the previous entry's hash.
  4. For any case file, canonicalise its assessment JSON (sorted keys, no whitespace), hash it with SHA-256 and compare with the ledger's payload_hash for that assessment.
  5. Compare the pack's head hash with the hash published in the carrier's periodic anchor statement.