docs/RELEASE_SCOPE.md

Current v3 scope

This is a reproducible finite-light CPU research reference for Certified Innovation Rendering. It adds conservative validity domains to stored visibility facts and eliminates their residual sampling support. It contains six new self-contained mathematical arguments and two new held-out protocols. The broader standalone architecture and v1/v2 evidence remain available.

Proved under stated assumptions: matrix covariance contraction for exact partial evidence; causal sequential estimation; real-arithmetic sphere/segment validity; finite-domain query count; deterministic direct-light enclosure; a counterexample to universal variance dominance for arbitrary predictions. None is labeled a historically first theorem.

Executed: twenty new procedural scenes; 58 new and retained tests; motion, spatial and known-time query studies; raw results; a portable CPU API; one retained trained visibility prior.

Estimated: 68% broader maturity, per-area status and all GPU engineering budgets. These are subjective or derived quantities, not measured production capability.

Not established: full SR/RR/FG, game integration, end-to-end speedup, full transport, formal floating-point certificates, hidden-event recovery without evidence, optimal future sampling, cross-game generalization, novel fundamental probability theory or independent replication.

Visibility caching and kinetic certificates are prior art. The contribution candidate is their explicit common-state, validity and output-estimation interface. Current root metadata and results_v3 govern the release; history/v2 and legacy documents retain historical claims.