Route-target planning receipt

Compare downstream targets.
Seal what the planning evidence actually supports.

This proof starts after candidate discovery. It ranks a curated set of route targets for the task and seals a portable selection/v1 route-decision receipt you can re-verify offline. It does not discover models, establish hardware fit, authorize a release, or prove inference.

Choose a task to route

or route any task
the planner classifies it, weighs evidence-labeled candidates, and seals the statement · ⌘↵

Why a route-decision receipt, not just an answer

A model gateway is judged on the answer. A governed one is judged on the decision behind it. When a regulator asks whya route target was recommended before release, “the router picked it” is not an answer an auditor can re-check. This planning receipt records the incomplete candidate set, evidence disposition, and unperformed execution. A later successful turn needs a separate request-time receipt. Verification is available offline through the method documented at the verification guide. Signature validity proves integrity under the embedded key; independent authority pinning and statement policy determine what the receipt can actually be trusted to mean.

See the live router The model passports it binds to
Emit + verify a selection receipt
POST /api/router/select        { "scenario": "clinical-summary" }
  → { receipt: { format:"governed-receipt/v1", algorithm:"Ed25519",
                 body:{ statement:"selection/v1", ... }, signature, public_key } }

POST /api/verify-selection     <the receipt>
  → { verified: true }          # same Ed25519 math as lockedinlabs.ai/verify

Selection proof

How proving a route-target decision works

Why a signed selection/v1 receipt is different from an opaque routing decision — and why it still does not authorize a release by itself.

Does LeanLogix prove which model was selected and why?

LeanLogix can seal a route-selection decision into a portable receipt containing the chosen catalog entry, rationale, inputs, body digest, signing fingerprint, and signature state. The zero-dependency source-checkout verifier checks receipt integrity offline; callers must pin the expected authority fingerprint separately to establish authority trust. A selection receipt does not prove artifact identity, loaded weights, execution, or release authority.

What is a signed model passport?

A model passport is canonical release evidence signed with Ed25519: release identity, source job, evaluation and policy results, and independent approval. The anonymous verification endpoint exposes only a privacy-safe server-verified summary. Raw canonical passport bytes, signature, and public key are authenticated member exports; those exported bytes can be verified offline. Selection receipts are a separate public proof format with a zero-dependency Node 22 verifier in the source checkout.

How is a model foundry different from a fine-tuning platform or an inference host?

A fine-tuning platform creates weights and an inference host runs them. LeanLogix governs whether an exact release candidate may be promoted and admitted to serving: local evidence, policy, independent approval, a signed passport, and a fail-closed gate. Generic base training and quantization are retired, and fork serving remains unavailable. The product boundary is release authority and evidence, not raw GPU execution.

What is LeanLogix?

LeanLogix is the governed AI release control plane for one invitation-only workspace. It records candidate and evaluation evidence, applies local policy, enforces separation-of-duties approval, signs release passports, and governs a narrow base-serving path. It is not a general inference cloud, GPU host, or claim that every training and serving lane is operational. LeanLogix is built by LockedIn Labs for regulated teams.