Cross-model review gate

A receipt is one reviewer's record of exactly what it checked about one exact revision. It reports checks; it does not certify the claim. The gate: the irreversible step waits for a no_concerns receipt on the current revision and the operator's go.

Loop

1. Author commits the artifact. Record the commit id and every artifact hash the claim rests on (e.g. ops.bin sha256, note file hash).
2. Reviewer = a different model family in a different harness (Claude author -> GPT / DeepSeek / Kimi reviewer, or the reverse). Brief it adversarially ("refute this or name what was missed") with paths, not conclusions. It writes a receipt bound to that commit and those hashes:
   • checked (each item, with method: re-ran, re-derived, read source at file:line, rebuilt env -i, ran the trusted evaluator itself) and not_checked (explicit);
   • observations, each a finding with severity;
   • independence per axis (execution, implementation, data, design) and relationships (same operator: always yes);
   • outcome: no_concerns, concerns or serious_concerns.
3. Author answers finding by finding, adds one regression check per finding, lists what stays unverified, and commits again.
4. Reviewer rechecks at the new commit (only the delta plus the regression checks). Loop until no_concerns; about three rounds is normal.
5. Gate: submit / publish / seed only with no_concerns on the exact revision being shipped, plus the operator's go. A changed byte means a new revision and a new receipt.

Benchmark variant (ecdsa.fail)

The strongest receipt is an independent rebuild: the reviewer rebuilds env -i from the committed defaults, checks the ops sha256, runs the evaluator itself, and runs a fixed-input A/B against the parent. A component another model wrote is checked on live trajectories before integration. For notes: the reviewer checks every number against the logs, the credits/dependencies against what was reused, and that required contract text is copied verbatim.

Wiring

Run the reviewer read-only at its highest effort: a second CLI agent from another lab, or a Claude Fable subagent (model: "fable"; confirm the transcript reports the model you asked for, since a silent fallback voids the review). Keep each review record next to the artifact so the next revision's reviewer can diff against it.