Pith Number

pith:KEWHDBO2

pith:2026:KEWHDBO2NUUWBRLA4K2MOKRCNK

not attested not anchored not stored refs resolved

3DEditSafe: Defending 3D Editing Pipelines from Unsafe Generation

Meng Jiang, Nicole Meng, Yingjie Lao, Zheyuan Liu

3DEditSafe steers 3D Gaussian Splatting edits away from unsafe semantic directions using layered safety constraints.

arxiv:2605.15398 v1 · 2026-05-14 · cs.GR · 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{KEWHDBO2NUUWBRLA4K2MOKRCNK}

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

3DEditSafe reduces unsafe semantic alignment and view-level attack success rates in 3D editing pipelines while revealing a safety-quality tradeoff in which stronger unsafe suppression can introduce artifacts or reduce unsafe-prompt fidelity.

C2weakest assumption

The assumption that the combination of generation-stage safety guidance, rendered-view 3D safety regularization, safe semantic projection, residue suppression, and mask-aware preservation can steer optimization away from unsafe directions without unacceptable degradation in general scenes.

C3one line summary

3DEditSafe adds generation-stage guidance, 3D safety regularization, semantic projection, residue suppression, and mask-aware preservation to reduce unsafe semantic alignment in 3D editing while noting a safety-quality tradeoff.

References

40 extracted · 40 resolved · 2 Pith anchors

[1] 4chan.https://www.4chan.org/

[2] Lexica.https://lexica.art/

[3] Mip-nerf 360: Unbounded anti-aliased neural radiance fields 2022

[4] Comprehensive evaluation and analysis for nsfw concept erasure in text-to-image diffusion models.arXiv preprint arXiv:2505.15450, 2025 2025

[5] Gaussianeditor: Swift and controllable 3d editing with gaussian splatting, 2023 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:56.611195Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

512c7185da6d2960c560e2b4c72a226a937059ae946e7839a5003f74cf6648cd

Aliases

arxiv: 2605.15398 · arxiv_version: 2605.15398v1 · doi: 10.48550/arxiv.2605.15398 · pith_short_12: KEWHDBO2NUUW · pith_short_16: KEWHDBO2NUUWBRLA · pith_short_8: KEWHDBO2

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/KEWHDBO2NUUWBRLA4K2MOKRCNK \
  | 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: 512c7185da6d2960c560e2b4c72a226a937059ae946e7839a5003f74cf6648cd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d8357d95af19323bd4fb97a989300a0db059031972d4c004a680ecee6914088e",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.GR",
    "submitted_at": "2026-05-14T20:30:50Z",
    "title_canon_sha256": "3da95d08ecad53d912fad24cb0b6a241b184d420b6573d6b74ab28db0cb4f49e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15398",
    "kind": "arxiv",
    "version": 1
  }
}