Pith Number

pith:OF3WSCAT

pith:2026:OF3WSCATZKUYMVYBTHIC7MCD2Z

not attested not anchored not stored refs pending

TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection

Alexandre Mourachko, Christophe Ropers, Hady Elsahar, Hongyan Chang, Pierre Fernandez, Rashel Moritz, Surya Parimi, Sylvestre-Alvise Rebuffi, Tom\'a\v{s} Sou\v{c}ek, Tom Sander, Tuan Tran, Valeriu Lacatusu, Vanessa Stark

TextSeal adds a detectable watermark to LLM outputs that stays visible even after mixing with human text or distillation into new models.

arxiv:2605.12456 v2 · 2026-05-12 · cs.CR · cs.CL · 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{OF3WSCATZKUYMVYBTHIC7MCD2Z}

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

TextSeal strictly dominates baselines like SynthID-text in detection strength and is robust to dilution, maintaining confident localized detection even in heavily mixed human/AI documents. The scheme is theoretically distortion-free... Beyond its use for provenance detection, TextSeal is also 'radioactive': its watermark signal transfers through model distillation, enabling detection of unauthorized use.

C2weakest assumption

That the watermark signal reliably transfers through model distillation with sufficient strength for detection, and that the theoretical distortion-free property and lack of quality impact hold under all practical serving conditions and adversarial mixing.

C3one line summary

TextSeal provides a localized, distortion-free LLM watermark that enables provenance tracking and distillation detection while preserving performance and text quality.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-22T02:04:42.400498Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7177690813caa986570199d02fb043d6742963a9cf6a5d1f98d3f140b5d9aa0a

Aliases

arxiv: 2605.12456 · arxiv_version: 2605.12456v2 · doi: 10.48550/arxiv.2605.12456 · pith_short_12: OF3WSCATZKUY · pith_short_16: OF3WSCATZKUYMVYB · pith_short_8: OF3WSCAT

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/OF3WSCATZKUYMVYBTHIC7MCD2Z \
  | 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: 7177690813caa986570199d02fb043d6742963a9cf6a5d1f98d3f140b5d9aa0a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b6051be10e39559e5d087a36b72e6e88fc5168782e47e0693aae7f9e40a30de5",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-05-12T17:44:41Z",
    "title_canon_sha256": "ba4f0a1c38c93ec636dbbe3018e21baf25d8f76309e94f62f656bd6c159e032a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12456",
    "kind": "arxiv",
    "version": 2
  }
}