Pith Number

pith:W56OMABI

pith:2026:W56OMABIAVXK6JP5VW4TVOSZAN

not attested not anchored not stored refs resolved

Prefix-Adaptive Block Diffusion for Efficient Document Recognition

Chenyu Liu, Dingwei Zhu, Jiazheng Zhang, Jihua Kang, Jun Long, Kaidi Zhang, Mingxu Chai, Qi Zhang, Ruoyu Chen, Tao Gui, Zhiheng Xi, Ziyu Shen

Prefix-Adaptive Block Diffusion replaces fixed block boundaries with causal prefix denoising and dynamic commitment to fix information conflicts in document parsing.

arxiv:2605.16861 v1 · 2026-05-16 · cs.CV · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{W56OMABIAVXK6JP5VW4TVOSZAN}

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 3B PA-BDM achieves higher recognition scores on several benchmarks and improves inference throughput by 71.6% over the 2.5B MinerU-Diffusion.

C2weakest assumption

That switching to causal prefix-to-suffix denoising inside blocks plus Confidence-gated Structural Loss and Progressive Prefix Commitment will eliminate the information-flow conflict between intra-block and inter-block generation without introducing new errors in structure-sensitive recognition.

C3one line summary

PA-BDM adapts block diffusion by switching to causal intra-block denoising and dynamically committing reliable prefixes to KV cache, yielding higher accuracy and 71.6% higher throughput than a comparable baseline on document benchmarks.

References

118 extracted · 118 resolved · 1 Pith anchors

[1] Aho and Jeffrey D 1972

[2] Publications Manual , year = "1983", publisher = 1983

[3] Chandra and Dexter C 1981 · doi:10.1145/322234.322243

[4] Scalable training of

[5] Dan Gusfield , title =. 1997 1997

Receipt and verification

First computed	2026-05-20T00:03:26.914245Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b77ce60028056eaf25fdadb93aba59034fafecc972b712426b0b293ee935581d

Aliases

arxiv: 2605.16861 · arxiv_version: 2605.16861v1 · doi: 10.48550/arxiv.2605.16861 · pith_short_12: W56OMABIAVXK · pith_short_16: W56OMABIAVXK6JP5 · pith_short_8: W56OMABI

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/W56OMABIAVXK6JP5VW4TVOSZAN \
  | 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: b77ce60028056eaf25fdadb93aba59034fafecc972b712426b0b293ee935581d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3d0e029d0acc37b2b84c0cae23919a1995ea8581737a056556de4ed856f03de8",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T07:50:13Z",
    "title_canon_sha256": "28660fb7e126fe914be3c88185a9fed7deef4c015f65c496a73379146ed6bdc9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16861",
    "kind": "arxiv",
    "version": 1
  }
}