Citadel binds an operation's declared route to what actually ran, its measured and modeled cost lenses, and whether a deterministic verifier outside the routed model accepted the outcome. Failed policies stay failed. Unknown cost stays unknown.
V1's aggregate was timeout-sensitive. V2 showed that verification escalation can cost more. The representative shakedown proved repository-artifact replay while still missing its frozen economic gates.
Across 12 tasks × 2 policies × 3 timing repetitions, adaptive recorded 27/36 verified cells versus 24/36. Its frozen aggregate missed both 30% gates, and excluding one matched 60-second baseline timeout reverses all three economic comparisons.
Twelve new exact instances, mostly from task templates already seen in v1, routed work to 1.5B, 3B, or 7B. Model-external verification matched the baseline cell completion at higher measured GPU energy and modeled GPU cost.
Six fixture repositories × 2 policies × 2 timing repetitions. Both policies verified 6/12 cells. Citadel used 7.1% less measured GPU energy, below the frozen 20% gate, and 13.2% more tokens.
Each artifact answers a different question. The state at right is the gate's actual outcome, not a maturity badge.
All 120 signed cells preserve 33 verified, 51 failed, and 36 unknown outcomes; 84 cells reached a model and 36 remained setup-unknown.
Integrity passed 02 / ROMAA pinned recursive stack consumed the operation contract; control evidence passed and the efficiency hypothesis failed.
Policy failed 03 / RUNTIMERequested and observed model/topology matched, the public clone changed as required, and a deterministic repository verifier outside the model passed.
Integration passed 04 / LOCAL V112 tasks × 2 policies × 3 timing repetitions; 27/36 versus 24/36 verified cells; frozen economic gates failed and timeout sensitivity reversed the economic direction.
Gate failed 05 / LOCAL V212 exact task instances × 2 policies × 3 timing repetitions; matched baseline cell completion; verifier escalation made measured GPU economics worse.
Policy regressed 06 / REPOSITORYSix artifact-producing tasks × 2 policies × 2 timing repetitions; both policies verified 6/12 cells; integrity gates passed and economic gates failed.
Gate failed 07 / ONBOARDFive unattended engineering stages completed from a clean local clone in 28.17 seconds; the nested doctor command exited zero but reported semantic health as unknown.
5 stages completedCitadel is not presented as a best-in-class model router. Its demonstrated advantage is that operation policies can be controlled, observed, graded outside the routed model, and rejected.
These commands recompute routes, exact-answer verdicts, model identity, cost derivations, source bindings, artifact digests, receipt chains, and Ed25519 signatures from committed evidence.
Evaluator guidenpm run readiness:verify
npm run readiness:v2:verify
npm run representative:v2:verify
npm run operation-proof:verify
npm run application:evidence:check
npm run onboarding:fresh-clone:verifyFunding expands the controller from frozen local pilots to multiple open agent stacks, task categories, model families, hardware profiles, tool routes, and complete cost lenses. The method and negative results remain public either way. Frontier must first verify at least 80% overall and 70% in every frozen task stratum, or the comparison is invalid.