Metraipolis › archive › dc_c16decb8f823

From the Transformer to a Formal Semantics of Coordinated Transformations — arXiv:2610.39735

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39735
License (as archived)
CC0-1.0
Archived
2026-10-31T06:09:26.260Z
SHA-256 of the archived text
8f105bd47584f448292954bc86805873bff90d6bd0597642af61a4274d156de9
Stable URL of this page
https://metraipolis.com/documento/dc_c16decb8f823

How to cite

From the Transformer to a Formal Semantics of Coordinated Transformations — arXiv:2610.39735 — arXiv (en), https://arxiv.org/abs/2610.39735 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c16decb8f823 (Metraipolis archive dc_c16decb8f823, sha256 8f105bd47584f448292954bc86805873bff90d6bd0597642af61a4274d156de9)
BibTeX
@misc{dcc16decb8f823,
  title = {From the Transformer to a Formal Semantics of Coordinated Transformations — arXiv:2610.39735},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39735},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c16decb8f823; sha256 8f105bd47584f448292954bc86805873bff90d6bd0597642af61a4274d156de9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39735. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop a formal semantics for a general class of coordinated systems of parameterized transformations, taking the Transformer as a paradigmatic starting point but abstracting from its particular mathematical instantiation. Representational vectors receive both extensional reference and ordered intensional interpretations, while parameter structures acquire relative, second-level interpretations that determine how argument properties are preserved, replaced, or combined. This yields the notion of a transforming concept: a parameterized transformation whose numerical action is coordinated with a corresponding property-level map. We then distinguish the common algebraic-semantic core of these systems from their architecture-specific functional organization, allowing different mathematical instantiations and mechanical realizations of the same abstract system type. The framework is applied to attention heads and residual connections, providing semantic explanations that depend only on the shared algebraic-semantic core and their local functional organization and therefore generalize beyond the standard Transformer. These analyses also reveal the modularity of the framework: complex architectures can be decomposed into simpler semantically coordinated subsystems whose organization may recur across different abstract system types.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2610.39735 — 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 2026-10-31T06:07:08.537Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).