Pith Number

pith:G4CSUWHD

pith:2026:G4CSUWHDN6JZNJ3WCMIB6XLS2I

not attested not anchored not stored refs pending

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference

Ben Wan, Jia Wang, Tongxuan Liu, Weizhe Huang, Yan Feng, Yuting Zeng, Zihan Tang

RTPrune applies a two-stage pruning process to DeepSeek-OCR that first keeps high-norm visual tokens and then merges the rest with optimal transport to cut inference time while preserving OCR accuracy.

arxiv:2605.00392 v3 · 2026-05-01 · 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{G4CSUWHDN6JZNJ3WCMIB6XLS2I}

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

Extensive experiments demonstrate state-of-the-art performance, as evidenced by 99.47% accuracy and 1.23× faster prefill on OmniDocBench, achieved with 84.25% token retention when applied to DeepSeek-OCR-Large.

C2weakest assumption

The observed two-stage reading trajectory in DeepSeek-OCR is stable and general enough that pruning high-norm tokens first followed by optimal-transport merging of the rest will preserve textual fidelity across OCR tasks.

C3one line summary

RTPrune delivers 99.47% accuracy and 1.23x faster prefill on OmniDocBench for DeepSeek-OCR-Large by retaining only 84.25% of tokens through a reading-twice inspired two-stage pruning process.

Cited by

1 paper in Pith

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing

Receipt and verification

First computed	2026-05-22T01:04:03.814269Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

37052a58e36f9396a77613101f5d72d22f0c36fb3f6651797da4d843074d4778

Aliases

arxiv: 2605.00392 · arxiv_version: 2605.00392v3 · doi: 10.48550/arxiv.2605.00392 · pith_short_12: G4CSUWHDN6JZ · pith_short_16: G4CSUWHDN6JZNJ3W · pith_short_8: G4CSUWHD

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/G4CSUWHDN6JZNJ3WCMIB6XLS2I \
  | 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: 37052a58e36f9396a77613101f5d72d22f0c36fb3f6651797da4d843074d4778

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "098170005d634e2acc0930416f394483e1c5e24fbe27629fdd2c002129c26e5e",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-01T04:30:16Z",
    "title_canon_sha256": "a92fc25361f723038ba98b4e0329bea793aea9d31f4909d71ddfebcc635c0a0c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.00392",
    "kind": "arxiv",
    "version": 3
  }
}