µ is a monoid homomorphism: µ distributes over monoid operations.

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

• µ is an applicative homomorphism: µ(pure a) = pure a and µ(imf <*> imx) = µ imf <*> µ imx.claim0.850
  Result for Image applicative specification.
• µ is a functor homomorphism: µ ∘ fmap = fmap ∘ µ.claim0.844
  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.claim0.826
  Demonstration on linear transformations.
• Monoid Homomorphismconcept0.776
• Steering vectors from µ(0→2) slightly outperform µ(1→2) for instruction discovery across datasets and modelsfinding0.753
  Shows that contrasting No Reflection with Triggered Reflection provides a stronger signal than Intrinsic vs Triggered.
• Monoidconcept0.751
  Standard algebraic abstraction with identity (ε) and associative binary operation ('); used to specify Image overlay operations.
• X → X[′′] on G and M are closure operators satisfying extensivity, idempotence, and monotonicity.finding0.728
• monosemanticityconcept0.727
  Interpretability property where a latent feature represents a single semantic concept; benchmarked across architectures.