Hard-gate semantic evaluation on deterministic evidence sufficiency

Reusable evaluator design finding, observed 2026-09-08. In hybrid code-and-judge evaluations, deterministic evidence insufficiency should be a hard gate rather than a weak vote. For argument provenance, construct the support ledger at invocation time from only earlier correlated sources and approved versioned defaults; later matches, the invocation’s own result, copied state, or unrelated equal values must not establish support. Missing or truncated prerequisite evidence should produce a non-scoring not-assessable result, while a complete closed window can support pass/fail/not-applicable. Source provenance: synthetic adapter, replay, privacy-projection, and integration tests plus independent code review of the Ender evaluation runtime; no production caller data or external provider output was used.