finding
active
finding:a-unique-local-hamiltonian-with-window-length-can-be-associated-to-any-ar-model-theorem-3A unique local Hamiltonian with window length ω can be associated to any AR(ω) model (Theorem 3)
Mapping autoregressive models to spin systems
Source paper
extracted_from(2025) · Francesco Sacco · Dalton A R Sakthivadivel · Michael Levin
Neighborhood — ranked by edge-count
Communities (2)
community
- Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
- Theoretical and empirical analysis of why AR language models cannot maintain coherence or convergence beyond their context window through local interactions alone.
Findings (1)
finding
- Autoregressive model unable to converge to a single stored pattern for any finite β (Corollary 2)supportsConsequence of Theorem 3 and 1D no-order result
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Topological equivalence theorem for local Hamiltonians
- Establishes that the boundary is a modelling choice not determined by the underlying physics
- No ordered phase in 1D with multiple stored patterns
- Core result demonstrating topological constraints on self-organization
- Core technical concept: a Hamiltonian where spin-spin interactions are defined only within finite windows ω, enabling generic analysis across diverse lattices
- Sum of windowed Hamiltonians with same window length; a key construct introduced in the paper to model local interactions on graphs
- A foundational empirical result undermining mechanistic separability, cited as evidence that the whole influences local events.