Emission gate
Boundry Gate
Keep priors from leaking past proof.
Boundary Gate keeps model priors from slipping past the evidence layer unchecked. It is the final separation between fluent generation and claims the system is actually willing to let reach a user. The Gate reads the Claim Ledger output and makes the release decision — not based on model confidence, but based on what the evidence supports.
Without this: the Ledger scores claims but nothing enforces the boundary. A response with one unsupported claim still reaches the user as a complete answer. The scoring becomes telemetry, not governance.
How the Gate works
The Boundary Gate reads the Claim Ledger's per-claim evaluation and makes a single deterministic decision about the entire response. It does not re-evaluate claims. It enforces the boundary the Ledger defined.
- Reads per-claim scores, attribution, and gate reason codes from the Ledger
- Applies the output-state taxonomy based on aggregate claim support
- Assigns one of five states to the response before it reaches the caller
- Deterministic — same Ledger output always produces the same Gate decision
Who this is for
Governance runtime
executes automatically as the final step in the bounded-synthesis pipeline. No manual review, no override path.
The caller
receives a response that has already passed the Gate — or receives an explicit state explaining why the response was classified as partial, narrative, or blocked.