Metraipolis › archive › dc_bc226257c050

Certified Access: Test-Time Compute on Conservative Physics-Structured AI Memory — arXiv:2610.39073

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39073
License (as archived)
CC0-1.0
Archived
2026-10-31T06:09:10.845Z
SHA-256 of the archived text
e350f8ecaad66057a7015ddeeb2b3d001731aaeae885a3ed9217d83b9defb3c4
Stable URL of this page
https://metraipolis.com/documento/dc_bc226257c050

How to cite

Certified Access: Test-Time Compute on Conservative Physics-Structured AI Memory — arXiv:2610.39073 — arXiv (en), https://arxiv.org/abs/2610.39073 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc226257c050 (Metraipolis archive dc_bc226257c050, sha256 e350f8ecaad66057a7015ddeeb2b3d001731aaeae885a3ed9217d83b9defb3c4)
BibTeX
@misc{dcbc226257c050,
  title = {Certified Access: Test-Time Compute on Conservative Physics-Structured AI Memory — arXiv:2610.39073},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39073},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc226257c050; sha256 e350f8ecaad66057a7015ddeeb2b3d001731aaeae885a3ed9217d83b9defb3c4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39073. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Test-time compute mechanisms, such as retries, confidence-based escalation and non-local routing, are conventionally deployed as black-box additions to trained models. They typically add forward passes or halting heads, but give no structural account of what the extra compute buys or what it costs against the model's stability guarantees. We therefore propose a theoretical and empirical framework for test-time compute on a Latent Dynamics Model used as the memory. When an encoder's latent state $(q,p)$ is advanced by a damped symplectic (velocity-Verlet) step of a learned Hamiltonian, every mechanism that expands access has an exact phase-volume Jacobian, a bounded energy change and an exact latch-transport law. We split reachability failures into escape failures and reach failures. A Lorentz squeeze resolves escape failures by injecting bounded, re-absorbable energy. A gated canonical translation (a one-step channel across $C_T$) resolves reach failures at $\detJ=1$ exactly. We verify this certificate stack on a designed analytic testbed. Reaching just beyond $C_T$ with the squeeze requires energy that grows quadratically in the excess distance. The gated channel's energy cost equals the potential difference between its endpoints, which is zero on the matched channel measured here, and so does not grow with distance in this testbed. An untrained state-replacing map annihilates phase volume and erases stored charge, while the gated channel transports it. On a learned physics-structured memory, we show calibrated compute rationing and evaluate the scaling limits of non-local routing against a physics-free baseline. The main contribution is the formalization and verification of the certificate stack, not benchmark performance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; High Energy Physics - Phenomenology (hep-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.39073 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T06:07:08.505Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).