µ is an applicative homomorphism: µ(pure a) = pure a and µ(imf <*> imx) = µ imf <*> µ imx.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• µ is a functor homomorphism: µ ∘ fmap = fmap ∘ µ.claim0.869
  Result for Image functor specification.
• The specification for (⊸) is a category homomorphism (µ id = id, µ(g ∘ f) = µg ∘ µf), leading to a correct-by-construction implementation.claim0.864
  Demonstration on linear transformations.
• µ is a monoid homomorphism: µ distributes over monoid operations.claim0.850
  Derived result for Image monoid specification.
• Steering vectors from µ(0→2) slightly outperform µ(1→2) for instruction discovery across datasets and modelsfinding0.759
  Shows that contrasting No Reflection with Triggered Reflection provides a stronger signal than Intrinsic vs Triggered.
• Contrasting No Reflection with Triggered Reflection (µ(0→2)) provides a stronger reflection signal than contrasting Intrinsic with Triggered Reflection (µ(1→2)).claim0.755
  Empirical interpretation of which reference baseline yields more useful steering vectors.
• Applicative Homomorphismconcept0.747
• X → X[′′] on G and M are closure operators satisfying extensivity, idempotence, and monotonicity.finding0.742
• In AOMIC ID1000 movie-watching fMRI data, NIS+ finds a one-dimensional macro-state representing 100-dimensional micro-states.finding0.739
  Real brain imaging result suggesting a compressed emergent representation.