Representational Isomorphism

The desired property of a bidirectional, behavior-preserving mapping between model representations; the goal MAS pursues.

Neighborhood — ranked by edge-count

framework

Model Alignment Search (MAS)
implements
The primary contribution of the paper: a bidirectional causal method that learns rotation matrices for each model to uncover and compare causally relevant latent subspaces across neural networks.

cosine ≥ 0.65 · no typed edge

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

Procedural Isomorphismconcept0.838
Two skills prescribing the same sequence of steps differing only in surface implementation details, enabling identical downstream performance
Structure in representationsconcept0.792
The central question of whether representational geometry implies corresponding computational structure
Structural Representationalismframework0.787
Dominant interpretation of generative models as neural structures with representational content; main target of critique
Isomorphism Frameworkframework0.785
Representational Alignmentconcept0.779
Measure of similarity between the similarity structures (kernels) induced by two different representations
Representational Transparencyconcept0.778
Property of conscious representations: they do not contain information about the fact that they are representations at the level of the representation itself
Representational Disentanglementconcept0.777
CIMC's characterization of part of the solution to the Hard Problem: insight into the structural necessities of phenomenal representation
Representational dynamicsconcept0.773
The evolution of an agent's latent representations over the course of training, shown to align with reward improvement when causal emergence is high.