Metraipolis › archive › dc_70ca33ef518e

Toward a Unified Mathematics of Concepts — arXiv:2609.24554

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24554
License (as archived)
CC0-1.0
Archived
2026-10-09T06:50:10.993Z
SHA-256 of the archived text
4dea75ae7607997694d47e395f243457b2d8e9f9daa281ad9ced0b3027818a97
Stable URL of this page
https://metraipolis.com/documento/dc_70ca33ef518e

How to cite

Toward a Unified Mathematics of Concepts — arXiv:2609.24554 — arXiv (en), https://arxiv.org/abs/2609.24554 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70ca33ef518e (Metraipolis archive dc_70ca33ef518e, sha256 4dea75ae7607997694d47e395f243457b2d8e9f9daa281ad9ced0b3027818a97)
BibTeX
@misc{dc70ca33ef518e,
  title = {Toward a Unified Mathematics of Concepts — arXiv:2609.24554},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24554},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70ca33ef518e; sha256 4dea75ae7607997694d47e395f243457b2d8e9f9daa281ad9ced0b3027818a97},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24554. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Concepts are commonly defined as abstract, compact representations of knowledge and treated as basic units of intelligent behavior. Yet, cognition, psychology, and AI lack a shared mathematical language for them. Modern systems represent concepts as vectors, distributions, symbols, graphs, and other structures, but these formalisms are typically treated as competing rather than as solutions to a common problem. We propose an operation-based view that evaluates mathematical frameworks by the conceptual operations they support, identifying thirteen operations (including similarity, composition, generalization, and grounding) that recur across cognition, psychology, and AI. We show that ten frameworks embody distinct commitments to concepts as self-contained content, relational structure, or evolving process, and that these commitments determine which operations each supports naturally. For example, vector-based models facilitate graded similarity and generalization but struggle with explicit composition, whereas symbolic models support composition but offer but generalize poorly. No single framework we examined naturally supports all operations without extension. We test this account empirically using categorization as a case study, operationalizing nine theories on the same items against human judgments. Despite addressing the same conceptual question, the theories produce different procedures and results, demonstrating that mathematical commitment shapes what a theory can explain. We call for hybrid formalisms that treat content, relation, and process as jointly primary.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.24554 — 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 2026-10-09T06:48:45.055Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).