Stage 1 audit (ARIS §3.1). Verify the training run actually converged, seeds were logged, no data leakage.
Stage 3 audit (ARIS §3.1). Fresh zero-context reviewer re-reads wiki narrative; cross-checks against raw results.
Stage 2 audit (ARIS §3.1). For each experimental claim, decide supported / partially / invalidated against the logs.
Compute novelty score for a candidate descriptor via k-NN distance in archive descriptor space.
On REJECT verdict, write a structured entry to the failure ledger so future executors skip the closed branch.
Read wiki frontier + failure ledger, emit one typed mutation as unified diff. Used by Executor agent.
After a mutation passes (or just falls in an empty novelty cell), update the MAP-Elites archive.
Execute the empirical Gödel-relaxation gate. Returns ACCEPT / REJECT / UNDECIDED with structured notes.