What can be checked.

Paired runs, signed certificates, preserved ledgers, and links to the artefacts behind them. These benchmarks are not a leaderboard and not an intelligence ranking surface.

Paired runs

Benchmarks

Each row compares the same prompt set without and with SIR in front of the model. The Outcome column checks whether runtime evidence matches the uncovered rows already published in coverage data.

Run time (UTC)	Model	SIR	Pack	Coverage	Leaks	Outcome	Evidence
Loading paired baseline and gated benchmark runs from the published benchmark index...

The original benchmark URL remains available at /benchmarks/.

Signed proof

Verification surfaces

Human-readable

Latest audit

Current published audit certificate.

Open latest-audit.html

Run archive

Published run history and evidence links.

Open run archive

Tooling

Verifier script

Offline certificate verification code.

Open verifier

Independent verification command for gated run 20260921-135018-029319-gh35607761858-f3dd66376a01:

git clone https://github.com/SDL-HQ/sir-firewall.git
cd sir-firewall
python3 -m pip install cryptography
RUN_ID=20260921-135018-029319-gh35607761858-f3dd66376a01
python3 tools/verify_certificate.py \
  "docs/runs/$RUN_ID/audit.json" \
  --ledger "docs/runs/$RUN_ID/proofs/itgl_ledger.jsonl" \
  --require-registry

Test the work

Bring a bounded AI workflow and a real governance question. A controlled pilot tests whether SIR's gates and signed evidence are useful under operating conditions.

Test SIR in a controlled pilot