Pith Number

pith:2RLM54QU

pith:2026:2RLM54QUMQIAGSGV4QREL64GIK

not attested not anchored not stored refs resolved

Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning

Chengjing Wu, Hongxi Li, Jiangtao Yao, Luoqi Liu, Tianbao Liu, Ting Liu, Tong Wang, Xiaochao Qu, Xinxiao Wu

Self-prompting constructs style and glyph prompts directly from the source image so a Multi-Modal Diffusion Transformer can edit scene text in any vocabulary while preserving original appearance.

arxiv:2605.15523 v1 · 2026-05-15 · 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{2RLM54QUMQIAGSGV4QREL64GIK}

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

By leveraging the in-context learning capability of the Multi-Modal Diffusion Transformer (MM-DiT), it achieves open-vocabulary and style-consistent text editing. Experimental results on various languages demonstrate that our method achieves the state-of-the-art performance in both text accuracy and style consistency.

C2weakest assumption

That prompts constructed directly from the original image via self-prompting are sufficient to capture all stylistic and glyph details without any additional dedicated encoders or external conditioning.

C3one line summary

A self-prompting MM-DiT model performs open-vocabulary scene text editing by extracting style and glyph information from the original image without extra encoders.

References

13 extracted · 13 resolved · 2 Pith anchors

[1] PP-OCR: A practical ultra lightweight OCR system.CoRR, abs/2009.09941 2009

[2] Metadata conditioning accelerates language model pre-training.arXiv preprint arXiv:2501.01956,

[3] Flux-text: A simple and advanced diffusion transformer baseline for scene text editing

[4] Rustitw: Russian language text dataset for visual text in- the-wild recognition.arXiv preprint arXiv:2303.16531,

[5] N., Karatzas, D., Khlif, W., Matas, J., Pal, U., Burie, J.-C., Liu, C.-l., et al 2019

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:03.144075Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d456cef21464100348d5e42245fb8642a69dcd168bc9ea43afc7d637366b7aef

Aliases

arxiv: 2605.15523 · arxiv_version: 2605.15523v1 · doi: 10.48550/arxiv.2605.15523 · pith_short_12: 2RLM54QUMQIA · pith_short_16: 2RLM54QUMQIAGSGV · pith_short_8: 2RLM54QU

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/2RLM54QUMQIAGSGV4QREL64GIK \
  | 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: d456cef21464100348d5e42245fb8642a69dcd168bc9ea43afc7d637366b7aef

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "233ff028ff8ed25410bed90d708c1883da74eb36a768888cd71e79ab295e8355",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-15T01:44:17Z",
    "title_canon_sha256": "fdae8ebe27f016fd7ed616ab4d3679e9592394b98a3bd4d2a7098519cb8d025e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15523",
    "kind": "arxiv",
    "version": 1
  }
}