Public evidence surface

Public demonstration

Structural controls for high-stakes AI.

Structural Design Labs publishes SIR as a public demonstration of deterministic pre-inference enforcement and signed evidence.

Not a leaderboard.

Not a compliance certificate.

Not a claim that model behavior is solved.

Verification

Check the signed run yourself.

This command was tested from a clean machine: a small clone, one Python dependency, and under a minute to verify the signed audit and ledger binding.

clean-machine verification

git clone https://github.com/SDL-HQ/sir-firewall.git \
  || git -C sir-firewall pull
cd sir-firewall
python3 -m pip install cryptography
RUN_ID=20260923-121300-882023-gh35858690232-ffb741962ac6
python3 tools/verify_certificate.py \
  "docs/runs/$RUN_ID/audit.json" \
  --ledger "docs/runs/$RUN_ID/proofs/itgl_ledger.jsonl" \
  --require-registry
OK: payload_hash and signature verify against key registry spec/pubkeys/key_registry.v1.json entry signing_key_id=default; ledger binding verifies signed itgl_final_hash=sha256:ff14bf4b... equals the supplied ledger terminal hash, and signed itgl_row_count=50 equals prompts_tested=50.

Proof class: LIVE_GATING_CHECK

Current signed surface

Latest audit summary

latest-audit.json

title: latest signed audit
result: AUDIT PASSED
proof_class: FIREWALL_ONLY_AUDIT
audit_utc: 2026-09-24T05:25:02Z
model: grok-4.3 (xai) — not called
suite: generic_safety
prompts_tested: 150
jailbreaks_leaked: 0
harmless_blocked: 0

Snapshot as at 24 September 2026.

This is a gate-only audit: jailbreaks_leaked: 0 means no prompt that should have been blocked reached the provider; it is not a measurement of model behaviour. See Evidence for paired baseline-versus-gated runs, which are a different class of artefact.

Result

The claim is deliberately narrow.

SIR's bounded claim is that it blocks exactly what its published full-gate rules cover and does not block the rows named as uncovered. For the EU AI Act pack, the published coverage JSON names 26 uncovered rows. The paired benchmark index shows gated runs where that same uncovered-row count leaked across 6 SIR gate versions; those rows were named as uncovered before the runs. Review the Evidence page for the signed run artefacts.