Pith Number

pith:RY4PNJH3

pith:2025:RY4PNJH3S3E6JF7X4AWO7KXTLC

not attested not anchored not stored refs pending

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Aixin Sun, Haodong Duan, Jiaqi Wang, Jinsong Li, Pan Zhang, Xiaobao Wu, Xiaoyi Dong, Yixin Cao, Yubo Ma, Yuhang Cao, Yuhang Zang

arxiv:2506.04997 v1 · 2025-06-05 · cs.IR · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{RY4PNJH3S3E6JF7X4AWO7KXTLC}

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.

Cited by

2 papers in Pith

CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval

Receipt and verification

First computed	2026-07-05T11:16:40.573982Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8e38f6a4fb96c9e497f7e02cefaaf358810a038e20ab0d59e85867d324758f84

Aliases

arxiv: 2506.04997 · arxiv_version: 2506.04997v1 · doi: 10.48550/arxiv.2506.04997 · pith_short_12: RY4PNJH3S3E6 · pith_short_16: RY4PNJH3S3E6JF7X · pith_short_8: RY4PNJH3

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/RY4PNJH3S3E6JF7X4AWO7KXTLC \
  | 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: 8e38f6a4fb96c9e497f7e02cefaaf358810a038e20ab0d59e85867d324758f84

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8f8ffb75819278d0a0e13b504aa5336ac64e6996c6b6ce3a0d64eec28b605310",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2025-06-05T13:06:01Z",
    "title_canon_sha256": "1f19adb2ad78196cb756f0e3f9606463ed06024521c9a8a60982acaf5ec9737f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.04997",
    "kind": "arxiv",
    "version": 1
  }
}