Metraipolis › archive › dc_6dc8d754e351

Discovering Physical Representation Languages — arXiv:2609.23381

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23381
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:11.690Z
SHA-256 of the archived text
c706bb45b8e9132ad5543845f748ba1c056e0472722897d1b063548b4cd2390c
Stable URL of this page
https://metraipolis.com/documento/dc_6dc8d754e351

How to cite

Discovering Physical Representation Languages — arXiv:2609.23381 — arXiv (en), https://arxiv.org/abs/2609.23381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6dc8d754e351 (Metraipolis archive dc_6dc8d754e351, sha256 c706bb45b8e9132ad5543845f748ba1c056e0472722897d1b063548b4cd2390c)
BibTeX
@misc{dc6dc8d754e351,
  title = {Discovering Physical Representation Languages — arXiv:2609.23381},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23381},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6dc8d754e351; sha256 c706bb45b8e9132ad5543845f748ba1c056e0472722897d1b063548b4cd2390c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Before a machine can discover a physical law, it must discover what its measurements are: which observations live on cells, which are intensive or extensive, which sectors are dual, and which distinctions are merely gauge. We introduce physical representation-language discovery, the problem of recovering this hidden ontology directly from anonymous controlled experiments. We give an identifiability theory and constructive polynomial-time procedure that recovers a carrier and differential sequence, measurement types and orientation twist, noninvertible refinement semantics, primal-dual Maxwell diagrams, and the residual equivalences that no permitted experiment can break. The theory turns material nuisance into a commutant, uses refinement to separate quantities from coordinates, and selects physics only after its representation has been recovered. For a certified finite experiment family, we prove an end-to-end two-stage measurement bound and a matching minimax rate in dimension, accuracy, and confidence. Blind Maxwell experiments recover complete primal/relative-dual ontologies on regular and unstructured carriers under jointly corrupted observations; an independent unstructured RLC system demonstrates that the result is not specific to Maxwell. The framework scales to tens of thousands of cells per carrier, while stress audits demonstrate robustness across severe physical regimes - including non-Markovian memory, nonlinearities, nonlocality, and complex constitutive hysteresis. A public FDTD audit demonstrates the emergence of anonymous curl structure from incomplete field data, while characterizing the informational prerequisites for complete recovery. The goal is to move scientific ML from learning laws in a human-supplied language to discovering the language in which laws become expressible, establishing exact theoretical limits on observational identifiability.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.23381 — 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 2026-10-09T06:58:09.297Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).