Pith Number

pith:5M3JSVPA

pith:2026:5M3JSVPALLUV2FBANKAMYXYWKM

not attested not anchored not stored refs pending

Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style

Amith Ananthram, Anna Filonenko, Elias Stengel-Eskin, Emily L. Spratt, Hannah Pivo, Kathleen McKeown, Marvin Limpijankit, Milad Alshomary, Mohit Bansal, Noam M. Elcott, Tim Trombley, Yassin Oulad Daoud

Vision language models rely on internal concepts that art historians judge as relevant for style prediction in 90 percent of cases.

arxiv:2603.11024 v3 · 2026-03-11 · cs.CV · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5M3JSVPALLUV2FBANKAMYXYWKM}

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

73% of the extracted concepts are judged by art historians to exhibit a coherent and semantically meaningful visual feature and 90% of concepts used to predict style of a given artwork were judged relevant.

C2weakest assumption

That the latent-space decomposition method accurately isolates the specific concepts the VLM internally uses for style classification rather than producing post-hoc interpretable features.

C3one line summary

Vision-language models predict artistic style using concepts that art historians judge as mostly coherent and relevant, with some success from formal visual features like contrast.

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-20T01:05:10.804590Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

eb369955e05ae95d14206a80cc5f165312e6f63e4e64cdc207ee4319c9fe92b1

Aliases

arxiv: 2603.11024 · arxiv_version: 2603.11024v3 · doi: 10.48550/arxiv.2603.11024 · pith_short_12: 5M3JSVPALLUV · pith_short_16: 5M3JSVPALLUV2FBA · pith_short_8: 5M3JSVPA

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/5M3JSVPALLUV2FBANKAMYXYWKM \
  | 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: eb369955e05ae95d14206a80cc5f165312e6f63e4e64cdc207ee4319c9fe92b1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "de1529f2766e6eda8bd18178abdfe5d453e9ce79e33f0210a3012e147cc1d802",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-03-11T17:49:45Z",
    "title_canon_sha256": "f1ae455c2abac0ca67cabe4e07e8804586bb00e21c63b6db7b517598b360b2b1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.11024",
    "kind": "arxiv",
    "version": 3
  }
}