Pith Number

pith:OPOWPHNA

pith:2026:OPOWPHNAHUAFW4EBE3HLIKGLUJ

not attested not anchored not stored refs resolved

KamonBench: A Grammar-Based Dataset for Evaluating Compositional Factor Recovery in Vision-Language Models

Richard Sproat, Stefano Peluchetti

KamonBench supplies 20,000 grammar-generated crest images whose explicit container, modifier, and motif factors let models be scored directly on compositional recovery rather than caption match alone.

arxiv:2605.13322 v1 · 2026-05-13 · cs.CV · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{OPOWPHNAHUAFW4EBE3HLIKGLUJ}

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

KamonBench therefore provides a controlled testbed for sparse compositional visual recognition and factor recovery in vision-language models.

C2weakest assumption

The grammar rules and synthetic generation process produce images whose factor structure mirrors the compositional challenges present in natural images and real-world visual recognition tasks.

C3one line summary

KamonBench is a grammar-generated synthetic dataset of compositional kamon crests with explicit factor annotations to evaluate factor recovery in vision-language models.

References

29 extracted · 29 resolved · 4 Pith anchors

[1] Understanding intermediate layers using linear classi- fier probes 2017

[2] Probing Classifiers: Promises, Shortcomings, and Advances 2022 · doi:10.1162/coli_a_00422

[3] Kadokawa Shoten (角川書店), Tokyo, 1993 1993

[4] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2021 · arXiv:2010.11929

[5] John Weatherhill, New York, 1971 1971

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:48.652722Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

73dd679da03d005b708126ceb428cba241f9591dcb0ef192f72ed6e3901001ce

Aliases

arxiv: 2605.13322 · arxiv_version: 2605.13322v1 · doi: 10.48550/arxiv.2605.13322 · pith_short_12: OPOWPHNAHUAF · pith_short_16: OPOWPHNAHUAFW4EB · pith_short_8: OPOWPHNA

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/OPOWPHNAHUAFW4EBE3HLIKGLUJ \
  | 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: 73dd679da03d005b708126ceb428cba241f9591dcb0ef192f72ed6e3901001ce

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "13de2adc754bafe5a892ae7bf65d2f8ae20a7bcc00474eb6a082691b611a5df6",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T10:35:07Z",
    "title_canon_sha256": "018246d88a61fe17bcde891e1739c69112d2d5f4e748bdc6510af481eee352ac"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13322",
    "kind": "arxiv",
    "version": 1
  }
}