Pith Number

pith:IS23CIWQ

pith:2024:IS23CIWQNY4VHTYF37XADJLZL2

not attested not anchored not stored refs pending

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation

Bin Wang, Conghui He, Junyuan Zhang, Ka-Ho Chow, Linke Ouyang, Qintong Zhang, Wentao Zhang, Ying Li, Zichen Wen

arxiv:2412.02592 v4 · 2024-12-03 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IS23CIWQNY4VHTYF37XADJLZL2}

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

3 papers in Pith

LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement

Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Receipt and verification

First computed	2026-07-05T12:01:56.119205Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

44b5b122d06e3953cf05dfee01a5795ea3d8f3d412d6eedb02bdcaeb8cf8defa

Aliases

arxiv: 2412.02592 · arxiv_version: 2412.02592v4 · doi: 10.48550/arxiv.2412.02592 · pith_short_12: IS23CIWQNY4V · pith_short_16: IS23CIWQNY4VHTYF · pith_short_8: IS23CIWQ

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/IS23CIWQNY4VHTYF37XADJLZL2 \
  | 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: 44b5b122d06e3953cf05dfee01a5795ea3d8f3d412d6eedb02bdcaeb8cf8defa

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9525e720cfa0fca7dd27846c0b5a7e5191aab2a57d1b658edb76fb0e1d64e12d",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-12-03T17:23:47Z",
    "title_canon_sha256": "d3fe6b63a6ca77e62e05b5bdcc636b4e87c99b5526228157db4924523211a205"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2412.02592",
    "kind": "arxiv",
    "version": 4
  }
}