Metraipolis › archive › dc_e9b293f05b02

When Can World Models Recover Physical Laws? — arXiv:2610.06877

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06877
License (as archived)
CC0-1.0
Archived
2026-10-07T11:19:56.697Z
SHA-256 of the archived text
e4c3da5558bcad1c0ab50bd226d9746f14f4db651001312aac3148855ccb8902
Stable URL of this page
https://metraipolis.com/documento/dc_e9b293f05b02

How to cite

When Can World Models Recover Physical Laws? — arXiv:2610.06877 — arXiv (en), https://arxiv.org/abs/2610.06877 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e9b293f05b02 (Metraipolis archive dc_e9b293f05b02, sha256 e4c3da5558bcad1c0ab50bd226d9746f14f4db651001312aac3148855ccb8902)
BibTeX
@misc{dce9b293f05b02,
  title = {When Can World Models Recover Physical Laws? — arXiv:2610.06877},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06877},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e9b293f05b02; sha256 e4c3da5558bcad1c0ab50bd226d9746f14f4db651001312aac3148855ccb8902},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06877. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate prediction does not establish that a world model has recovered a physical law: distinct dynamics can generate identical records under the same observation protocol. We formulate law recovery on a fixed physical domain under an explicit catalog of experiments, sensor uncertainty, and an acquisition budget. A rate--distortion converse separates the information needed to describe a law from the information the apparatus can reveal. Its constructive counterpart gives a finite response codebook and an explicit decoding budget. On compact world classes, uniform recovery is possible exactly when every pair of different laws is experimentally distinguishable; equivalently, the apparatus can recover all the entropy of every finite law source. An inverse response modulus quantifies stability. For Lipschitz fields on a $d$-dimensional state--action domain, noisy full-state readouts after resets require minimax budget $\Theta(\varepsilon^{-(d+4)/2})$ for squared law error $\varepsilon$, compared with $\Theta(\varepsilon^{-(d+2)/2})$ for direct field observations. Exact crossing-time symmetries establish the lower bound under adaptive experiment selection and arbitrary durations with constant inputs. Reproducible synthetic cases illustrate the separate roles of intervention, calibration, and repeated measurement. Together, the results identify which evidence supports a claim of physical-law recovery and the cost of acquiring it.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Other Statistics (stat.OT) ; Artificial Intelligence (cs.AI); Information Theory (cs.IT); Machine Learning (cs.LG); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.06877 — 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 2026-10-07T11:15:24.637Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).