Applications
D-05candidate domainUnder investigation
Optimisation
Verified compositional search over primitive operators for combinatorial and numerical problems.
Current scope
The model-substitution methodology is itself an optimisation problem operated under the same signed-evidence discipline. Extending that discipline to search over primitive operators for external optimisation problems is the focus.
Explicitly out of scope
- General-purpose black-box optimisation service is not the near-term goal.
- No benchmark leaderboards are pursued — results are held to the falsification standard.
Research strands informing this scope
Model-substitution methodology
Illustrates cost-versus-verified-outcome search operated under signed acceptance and cost evidence.
Structural compounding hypothesis
Primitive operators compose the same way abstractions do; the compounding model applies.
Evidence references
Each reference links to the signed dossier for that experiment. Nothing on this page claims deployment — these are the artifacts that inform the current scope.
Open questions
- Which operator families admit verified composition without gate-runtime blow-up?
- How does the substitution methodology generalise beyond model backends to arbitrary solvers?
Next milestone
Apply the same signed-evidence discipline to a non-model operator pool.