pith. sign in
Pith Number

pith:VV6ZO7CA

pith:2026:VV6ZO7CAHAGPGER476ZT4MZ3UC
not attested not anchored not stored refs resolved

Characterizing Universal Object Representations Across Vision Models

Florian P. Mahner, Francisco Pereira, Johannes Roth, Ka Chun Lam, Martin N. Hebart, Michael F. Bonner

Vision models converge on universal object dimensions that are more interpretable and align better with biological vision.

arxiv:2605.13675 v1 · 2026-05-13 · cs.CV · cs.LG · q-bio.NC

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{VV6ZO7CAHAGPGER476ZT4MZ3UC}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

In contrast to model-specific dimensions, universal dimensions are more interpretable and more strongly driven by conceptual image properties... models with more universal dimensions also better predict macaque IT activity and human similarity judgments, suggesting that universality reflects representations relevant to biological vision.

C2weakest assumption

That reappearance frequency across the 162 models reliably identifies universal dimensions and that the non-negative decomposition fully captures the relevant object similarity structure without significant loss of information.

C3one line summary

Vision models converge on universal object dimensions that are semantically interpretable and align more closely with biological vision than model-specific ones.

References

54 extracted · 54 resolved · 0 Pith anchors

[1] Y . LeCun, Y . Bengio, and G. Hinton. Deep learning.Nature, 521:436–444, 2015 2015
[2] N. Kanwisher, M. Khosla, and K. Dobs. Using artificial neural networks to ask ’why’ questions of minds and brains.Trends in Neurosciences, 46:240–254, 2023 2023
[3] A. Doerig, R. P. Sommers, K. Seeliger, B. Richards, J. Ismael, G. W. Lindsay, K. P. Kording, T. Konkle, M. A. J. van Gerven, N. Kriegeskorte, and T. C. Kietzmann. The neuroconnectionist research progr 2023
[4] D. L. K. Yamins and J. J. DiCarlo. Using goal-driven deep learning models to understand sensory cortex. Nature Neuroscience, 19:356–365, 2016 2016
[5] M. Huh, B. Cheung, T. Wang, and P. Isola. Position: The platonic representation hypothesis.Proceedings of Machine Learning Research, 235:20617–20642, 2024 2024

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Receipt and verification
First computed 2026-05-18T02:44:17.112127Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

ad7d977c40380cf3123cffb33e333ba08aa22105a61901a6abdc251e16968480

Aliases

arxiv: 2605.13675 · arxiv_version: 2605.13675v1 · doi: 10.48550/arxiv.2605.13675 · pith_short_12: VV6ZO7CAHAGP · pith_short_16: VV6ZO7CAHAGPGER4 · pith_short_8: VV6ZO7CA
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/VV6ZO7CAHAGPGER476ZT4MZ3UC \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: ad7d977c40380cf3123cffb33e333ba08aa22105a61901a6abdc251e16968480
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "e7aadf53fad99880373cbdc5a74975621a83eae015ba3bb9b6f47839ff0c2d3a",
    "cross_cats_sorted": [
      "cs.LG",
      "q-bio.NC"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T15:34:41Z",
    "title_canon_sha256": "1e2f0e11f256be3fad11a3981774c2c565bd502d9034ab45f85a08f61e45285f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13675",
    "kind": "arxiv",
    "version": 1
  }
}