Pith Number

pith:JE2DQKXL

pith:2026:JE2DQKXLVZTEM3HMN4TWRHTQ5E

not attested not anchored not stored refs pending

Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes

Bingzhang Wang, Bofei Zhang, Cong Zhang, Qiaofeng Zheng, Yew-Soon Ong, Yifan Jiang, Yifan Yang

Current top vision-language models reach only 51.7 percent accuracy on questions that demand both precise visual details from high-resolution scenes and external knowledge verification.

arxiv:2602.00593 v3 · 2026-01-31 · 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{JE2DQKXLVZTEM3HMN4TWRHTQ5E}

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

the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools.

C2weakest assumption

The questions and answers produced by PhD annotators from top universities faithfully represent expert-level challenges of fine-grained visual grounding plus external knowledge without introducing systematic biases or inconsistent difficulty.

C3one line summary

Pix2Fact benchmark shows top VLMs achieve only 51.7 percent accuracy on fine-grained visual questions needing both detailed image grounding and web-verified external knowledge.

Cited by

1 paper in Pith

UltraVR: A Diagnostic Ultra-Resolution Image-VQA Benchmark for Evidence-Grounded Reasoning

Receipt and verification

First computed	2026-05-21T01:05:15.363778Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4934382aebae66466cec6f27689e70e933c12b2fa0992274f3f1cdadfaae155f

Aliases

arxiv: 2602.00593 · arxiv_version: 2602.00593v3 · doi: 10.48550/arxiv.2602.00593 · pith_short_12: JE2DQKXLVZTE · pith_short_16: JE2DQKXLVZTEM3HM · pith_short_8: JE2DQKXL

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/JE2DQKXLVZTEM3HMN4TWRHTQ5E \
  | 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: 4934382aebae66466cec6f27689e70e933c12b2fa0992274f3f1cdadfaae155f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9d8ea0c9882e7ffc902416ce4f3798bf7963edf2a08bbb474f7aed1126b7b940",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-01-31T08:18:34Z",
    "title_canon_sha256": "f4ac130dec96a28cdd2bfa5a7818e264f2516ede4ee3c2fc286eae329071d30c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.00593",
    "kind": "arxiv",
    "version": 3
  }
}