Transition Probability Matrix (TPM)

Matrix encoding Markovian micro-dynamics; foundational for EI computation.

Neighborhood — ranked by edge-count

paper

framework

Representation Network (RN)
uses
Novel construct introduced by this paper: a hypothetical graph embedded in the time series of LLM representations, where each dimension is a node and latent connections are edges.

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.

Transition Matrix (B matrix)concept0.813
Prescribes transitions among hidden state factors under action; encodes policy-dependent dynamics
phase transitionconcept0.716
Change between ordered and disordered macroscopic phases; existence depends on topology
Partially Observable Markov Decision Process (POMDP)framework0.687
Modeling framework for discrete state-space decision-making under uncertainty, used as generative model in active inference.
Non-deterministic Transition Systemconcept0.685
Binary relation (S, S, R) on a set modeling computational state transitions; point of entry to coalgebra theory.
Stochastic model of wealth distribution with agent state transitionsframework0.683
Model treating agents as inactive/active with random state transitions; foundational work by Bose & Banerjee.
stochastic thermodynamicsframework0.680
Framework for non-equilibrium free energies; mentioned as future direction to generalise results
Ginibre Matrix Distributionconcept0.676
A class of random matrices with Gaussian entries used to characterize the baseline eigenvalue distribution of OV circuits at initialization, against which learned positive eigenvalue clustering is compared
TEM-Transformer (TEM-t)framework0.674
The transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.