Metraipolis › archive › dc_7e31ad22689d

An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models — arXiv:2608.28541

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28541
License (as archived)
CC0-1.0
Archived
2026-10-17T07:47:03.761Z
SHA-256 of the archived text
c5bec10c3e54c72baa8098ad9862098dd45f2e682bfcf1fd40102e33aae361ad
Stable URL of this page
https://metraipolis.com/documento/dc_7e31ad22689d

How to cite

An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models — arXiv:2608.28541 — arXiv (en), https://arxiv.org/abs/2608.28541 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e31ad22689d (Metraipolis archive dc_7e31ad22689d, sha256 c5bec10c3e54c72baa8098ad9862098dd45f2e682bfcf1fd40102e33aae361ad)
BibTeX
@misc{dc7e31ad22689d,
  title = {An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models — arXiv:2608.28541},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28541},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e31ad22689d; sha256 c5bec10c3e54c72baa8098ad9862098dd45f2e682bfcf1fd40102e33aae361ad},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28541. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A code world model accepted by a sampling gate can be exactly right on everything the gate can see and arbitrarily wrong beyond it. We characterize what a certified model can know, and what its errors can cost, when the omission is an annular freeze mode enclosing an unreachable interior. The gate quotient makes the question precise: acceptance-with-certainty determines the model exactly on the reachable query set; beyond reach is gauge. On a minimal ring instrument we prove the extreme case (a wrong-topology filled-disc artifact unfalsifiable by any sampling gate and bitwise harmless at play) and measure, with LLM synthesis across three model families, how one knob (a channel of width gamma) walks the same artifact through three regimes: unfalsifiable-and-harmless, falsifiable-and-costly, and instantly falsified. Three principles organize the empirics. First, danger is topology relative to reach: a channel the planner can use collapses the blind model's exploitation (play cost 1.09 to ~0 over a knee at gamma ~ 0.1), while a hidden channel with the same first Betti number keeps it at full strength (1.12). Second, repair is parameter-bound and sensor-bound: no family recovers the region from outside evidence; from inside, models pose the right topology but cannot pin its parameters, and the posed topology tracks the guiding persistent-homology summary's wrong beta_1 (a sensor with a measured geometric resolution limit), not the truth. Third, mitigation must match the error's dimension and direction: point fences fail against the one-dimensional boundary, a dimension-matched persisted fence collapses exploitation to a two-lesson transient (0.999 to 0.058), and the dual freedom certificate collapses the invented-mode failure symmetrically (1.769 to 0.029). In n dimensions the shell makes misidentification near-certain while the danger stays fully exploitable: the two axes are independent.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2608.28541 — 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 2026-10-17T07:28:26.651Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).