method
active
method:spectral-graph-theory

Spectral Graph Theory

Technique using principal eigenvectors to identify densest clusters; applied to find principal Markov blanket in simulations.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Markov Blanket
    implements
    A statistical partition of states that separates internal states from external hidden states; fundamental to self-organization in the paper.

Related by similarity (8)

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.

  • graph Hamiltonianframework0.724
    Hamiltonian constructed from adjacency matrix and coupling strengths on a graph
  • Graph Geometryconcept0.713
    A more complex geometric structure used to characterize in-context learning task representations
  • Graph structure constraining local interactions and ordering
  • Stack Theoryframework0.706
    Bennett's multi-level formal account of representation as a stack of abstraction layers, applied to representational time.
  • Mathematical and conceptual framework for modeling complex self-organizing systems; applied here to action and cognition.
  • Classical quantitative theory of information; paper seeks to reconcile with qualitative domain-theoretic approaches.
  • Category Theoryconcept0.694
    Fundamental mathematical tool; poset-as-category provides simple instances of categorical notions like products and adjunctions.
  • Janus proposes transformer computation viewed as causal graph with foliations/time-slices specifying computation order.