pith. sign in
Pith Number

pith:3LCHIT7F

pith:2025:3LCHIT7FYHXM6DUASVPUCHA3XO
not attested not anchored not stored refs resolved

PaddleOCR 3.0 Technical Report

Changda Zhou, Cheng Cui, Dianhai Yu, Hongen Liu, Jiaxuan Liu, Jing Zhang, Jun Zhang, Kui Huang, Manhui Lin, Tingquan Gao, Ting Sun, Wenyu Lv, Xueqing Wang, Yanjun Ma, Yichao Zhang, Yi Liu, Yubo Zhang, Yue Zhang, Zelun Zhang

PaddleOCR 3.0 shows models under 100 million parameters match billion-parameter vision-language models on OCR and document tasks.

arxiv:2507.05595 v1 · 2025-07-08 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{3LCHIT7FYHXM6DUASVPUCHA3XO}

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

Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs.

C2weakest assumption

The benchmarks used to claim competitiveness are representative of real-world use and do not contain undisclosed advantages in data selection or evaluation protocol.

C3one line summary

PaddleOCR 3.0 releases compact open-source models for OCR, document structure parsing, and information extraction that rival billion-parameter VLMs.

References

73 extracted · 73 resolved · 9 Pith anchors

[2] R. AI. Rolmocr: A faster, lighter open source ocr model, 2025 2025
[3] Ernie 4.5 technical report, 2025 2025
[4] L. Blecher, G. Cucurull, T. Scialom, and R. Stojnic. Nougat: Neural optical understanding for academic documents, 2023 2023
[5] breezedeus. Pix2text. https://github.com/breezedeus/Pix2Text, 2022. Accessed: 2025-06-23 2022
[6] R. Casey and E. Lecolinet. A survey of methods and strategies in character segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18 0 (7): 0 690--706, 1996. doi:10.1109/34.5067 1996 · doi:10.1109/34.506792

Formal links

1 machine-checked theorem link

Cited by

36 papers in Pith

Receipt and verification
First computed 2026-05-17T23:39:19.863640Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

dac4744fe5c1eecf0e80955f411c1bbb9075f922086dba3861300c2853576ee0

Aliases

arxiv: 2507.05595 · arxiv_version: 2507.05595v1 · doi: 10.48550/arxiv.2507.05595 · pith_short_12: 3LCHIT7FYHXM · pith_short_16: 3LCHIT7FYHXM6DUA · pith_short_8: 3LCHIT7F
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/3LCHIT7FYHXM6DUASVPUCHA3XO \
  | 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: dac4744fe5c1eecf0e80955f411c1bbb9075f922086dba3861300c2853576ee0
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "3f3e53475258f1b87f64798338c41e36fa6fcf35184ce7b6b8681d3116db5f47",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-07-08T02:14:10Z",
    "title_canon_sha256": "82285a5b2ad48f34d92c2129da2d5f2f609456792d462a63c6650508507b1e8e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2507.05595",
    "kind": "arxiv",
    "version": 1
  }
}