Pith Number

pith:DB6OCLO7

pith:2024:DB6OCLO76QFE6TYWDMJ2JA3XVJ

not attested not anchored not stored refs pending

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing

Alexander Robey, Bairu Hou, Eric Wong, George J. Pappas, Hamed Hassani, Jiabao Ji, Shiyu Chang, Yang Zhang

arxiv:2402.16192 v2 · 2024-02-25 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{DB6OCLO76QFE6TYWDMJ2JA3XVJ}

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.

Cited by

8 papers in Pith

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Receipt and verification

First computed	2026-07-05T07:50:23.805749Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

187ce12ddff40a4f4f161b13a48377aa7cac299eda281361df3bb79b8313f729

Aliases

arxiv: 2402.16192 · arxiv_version: 2402.16192v2 · doi: 10.48550/arxiv.2402.16192 · pith_short_12: DB6OCLO76QFE · pith_short_16: DB6OCLO76QFE6TYW · pith_short_8: DB6OCLO7

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/DB6OCLO76QFE6TYWDMJ2JA3XVJ \
  | 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: 187ce12ddff40a4f4f161b13a48377aa7cac299eda281361df3bb79b8313f729

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6a9075f11c6ab213de02bb0acd6f10d988a02d7377c2277cdbcf2fd1f2489a66",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-02-25T20:36:03Z",
    "title_canon_sha256": "3dd6dff03031a89f165919f91829fcbd3e0f601b184e98b156d9cbf16e8394b2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2402.16192",
    "kind": "arxiv",
    "version": 2
  }
}