Metraipolis › archive › dc_7603dc707c3d

What Converges in the Platonic Representation Hypothesis? Structure over Geometry — arXiv:2609.27252

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27252
License (as archived)
CC0-1.0
Archived
2026-10-08T10:52:12.836Z
SHA-256 of the archived text
266d5fe0703fb247e9bca89de3147369321e6a9f1a3c0b3e36678b6d93ec646e
Stable URL of this page
https://metraipolis.com/documento/dc_7603dc707c3d

How to cite

What Converges in the Platonic Representation Hypothesis? Structure over Geometry — arXiv:2609.27252 — arXiv (en), https://arxiv.org/abs/2609.27252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7603dc707c3d (Metraipolis archive dc_7603dc707c3d, sha256 266d5fe0703fb247e9bca89de3147369321e6a9f1a3c0b3e36678b6d93ec646e)
BibTeX
@misc{dc7603dc707c3d,
  title = {What Converges in the Platonic Representation Hypothesis? Structure over Geometry — arXiv:2609.27252},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27252},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7603dc707c3d; sha256 266d5fe0703fb247e9bca89de3147369321e6a9f1a3c0b3e36678b6d93ec646e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The Platonic Representation Hypothesis suggests that increasingly capable models converge toward shared representations. Recent work narrows this claim to shared local neighborhood relationships, finding that capacity-dependent trends in several global similarity measures largely disappear after calibration. We challenge this interpretation by showing that prior local-global comparisons confound structural scale (local versus global) with what is compared: relational structure, defined by which samples are related, versus metric geometry, characterized by quantitative relations such as distances, similarities, or correlations. To disentangle these factors, we construct a controlled $2\times2$ framework that evaluates both relational structure and metric geometry at local and global scales. We introduce $H_0$ skeleton overlap as a global counterpart to mutual $k$-nearest neighbors, together with matched distance-aware variants. Across vision-language models, relational structure exhibits robust representational convergence at both scales after calibration, whereas increasingly stringent distance agreement substantially weakens alignment and progressively flattens the capacity-dependent trend. We further extend the analysis beyond ambient Euclidean geometry by evaluating distance agreement under a Riemannian metric approximation and recover the same structure-geometry pattern. The pattern is also reproduced in video-text representations. Together, these results show that relational convergence extends beyond local neighborhoods to global spanning structure, whereas metric geometry exhibits substantially weaker convergence.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV); Algebraic Topology (math.AT).
Pagina del lavoro: https://arxiv.org/abs/2609.27252 — 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 2026-10-08T10:06:16.719Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).