Ω Omega Protocol Work together
MEASURED

Artifact

proof-carrying-evals

Governance properties routed to the checker whose logic fits, with the LLM judge's score sealed beside the proof.

§ 1

What it establishes

That an evaluation harness can route each checkable governance property to a formal checker (Z3 for one decision, Lean 4 for a trace, TLA+ for interleavings, CryptoVerif for authorisation) and keep the language-model judge's opinion labelled as an opinion, so that on the six violating cases the judge's 4 of 6 passes and the checker's 6 of 6 proofs sit in one record.

§ 2

What it does not establish

That a frontier judge would fail the same way; the judge is a local 14B model and sometimes grades its own output. Two dependencies are not yet published on their own and are vendored with provenance.

§ 3

Method

Sixteen sealed records from one complete rerun; model-authored and planted-adversarial decisions reported separately; CI recomputes the headline counts.

§ 4

Results

Judge passed 4 of 6 violating decisions; checker proved 6 of 6; on six non-violating rows both agree.

§ 5

What has to be trusted

Z3, Lean 4, TLC and CryptoVerif and each encoding; the vendored omega_seal and omega_gate packages; the local judge model.

§ 6

Prior work

LLM-as-judge evaluation and formal runtime verification. The contribution is the routing by property kind with both verdicts sealed together.

§ 7

Reproduce it

python3 scripts/verify_records.py

Findings drawn from this artifact are on the evidence ledger.