When several mechanisms have each earned a narrow result, what has been shown about their interaction?
https://github.com/research-farm/construct/blob/main/notes/walkthrough/20_BODY_0_COMPOSITION.md
Separate results do not become an integration result by sharing a sequence. The composed path must retain the intended causal role: it should improve the answer, its removal should make the answer worse, and the protected state and cost claims should still hold.
In one composition study, the machinery replayed correctly, preserved the authority boundary, and used fewer hot tokens. But the composed and reference paths did not produce usable answers, while the ablations did. The experiment could not show that the inherited mechanisms were needed together.
A direction for ablation
An ablation difference has a direction. Removing a mechanism and improving the answer is evidence against its needed role in that experiment. Correct bookkeeping and lower cost do not turn that result into an integration claim.
Questions to carry forward
What behavior must the composed path change? What would make each removed part necessary? Can the answer surface and external oracle score both the intended win and the case where governance should lose?