Pith Number

pith:OVAJQYWJ

pith:2026:OVAJQYWJFX36O56ZZIRWAIGTBS

not attested not anchored not stored refs resolved

Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance

Junlan Feng, Liang Li, Qian Wang, Song Wu, Xinyu Chen, Zili Yi

A tuning-free video editing method uses selective noise levels and guidance to change only the intended parts.

arxiv:2605.15533 v1 · 2026-05-15 · 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{OVAJQYWJFX36O56ZZIRWAIGTBS}

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

We propose a tuning-free, instruction-based video editing framework... Experiments show that our proposed method achieves better visual quality and state-of-the-art performance.

C2weakest assumption

That assigning higher noise levels to edited regions and lower noise levels to unedited regions, combined with the proposed Noise Guidance Mechanism, will reliably preserve unedited content and overall coherence using only the generative model's video prior.

C3one line summary

Proposes SNIS and NGM to enable tuning-free instruction-based video editing with improved visual quality and claimed SOTA results.

References

35 extracted · 35 resolved · 8 Pith anchors

[1] Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance 2026 · arXiv:2605.15533

[2] RELATED WORKS Relevant works in image editing focus on converting image generation models into editing models through prompt guid- anceandattentionmanipulation[1,2,3]. Owingtothedelayed development of

[3] Replace the bear with a tiger

[4] Replace the elephant with a zebra

[5] Delete the rhino 1901

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance

Receipt and verification

First computed	2026-05-20T00:01:03.827501Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

75409862c92df7e777d9ca236020d30cbccdc797da08fbea94bb6b7b7eacfa50

Aliases

arxiv: 2605.15533 · arxiv_version: 2605.15533v1 · doi: 10.48550/arxiv.2605.15533 · pith_short_12: OVAJQYWJFX36 · pith_short_16: OVAJQYWJFX36O56Z · pith_short_8: OVAJQYWJ

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/OVAJQYWJFX36O56ZZIRWAIGTBS \
  | 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: 75409862c92df7e777d9ca236020d30cbccdc797da08fbea94bb6b7b7eacfa50

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9810eb3b8d31fe3635c1d839ea309f54499ed86cef865472ac69155ef138c3a6",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-15T02:09:06Z",
    "title_canon_sha256": "4527fce4094b1bce1e90ba27bdae54de8aacefe3aa83f8be8f81e67d504db627"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15533",
    "kind": "arxiv",
    "version": 1
  }
}