Published January 4, 2026 | Version 1.0.0
Preprint Open

Bounded Lattice Inference: A Governed Reasoning Substrate with Persistent State and Non-Linguistic Authority

Authors/Creators

Description

This work describes a governed reasoning substrate that introduces persistent 
state to language-model systems without granting agency, goals, or 
self-modification. The contribution is architectural: separating linguistic 
proposal from non-linguistic authority, and measuring the resulting system 
using standard tools from queueing theory and supervisory control.

Key results:
- Interiority confirmed via hysteresis testing (16.7% divergence rate)
- Two distinct phase boundaries identified (budget starvation, glass ossification)
- Safety invariants maintained across all experimental conditions
- No agency, consciousness, or alignment claims

The system enforces epistemic constraints by construction and is evaluated 
via falsifiable experiments. 76 test suites confirm architectural properties.

Files

bounded_lattice_inference.pdf

Files (101.1 kB)

Name Size Download all
md5:fd7cf7a21b1e1e4ff54847b9bc2288ee
101.1 kB Preview Download

Additional details

Related works

References
Preprint: 10.5281/zenodo.17726790 (DOI)
Preprint: 10.5281/zenodo.18071265 (DOI)

References

  • Ashby, W.R. (1956). An Introduction to Cybernetics. Chapman & Hall.
  • Ashby, W.R. (1960). Design for a Brain: The Origin of Adaptive Behavior. Chapman & Hall.
  • Beer, S. (1972). Brain of the Firm. Allen Lane.
  • Conant, R.C. & Ashby, W.R. (1970). Every good regulator of a system must be a model of that system. Int. J. Systems Sci. 1(2), 89-97. Control Theory
  • Ramadge, P.J. & Wonham, W.M. (1987). Supervisory control of a class of discrete event processes. SIAM J. Control Optim. 25(1), 206-230. Prior Work (Author)