Pith Number

pith:ZHV6GX25

pith:2024:ZHV6GX2556ABJWK2KIA5VXRMTS

not attested not anchored not stored refs pending

Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing

Jun Sun, Wei Zhao, Ye Zhang, Yige Li, Zhe Li

arxiv:2405.18166 v2 · 2024-05-28 · 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{ZHV6GX2556ABJWK2KIA5VXRMTS}

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

5 papers in Pith

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring

Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types

Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation

LLM Safety From Within: Detecting Harmful Content with Internal Representations

Receipt and verification

First computed	2026-07-05T08:31:51.618421Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c9ebe35f5def8014d95a5201dade2c9cb65c075ea822c774dbc72c07876a970b

Aliases

arxiv: 2405.18166 · arxiv_version: 2405.18166v2 · doi: 10.48550/arxiv.2405.18166 · pith_short_12: ZHV6GX2556AB · pith_short_16: ZHV6GX2556ABJWK2 · pith_short_8: ZHV6GX25

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/ZHV6GX2556ABJWK2KIA5VXRMTS \
  | 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: c9ebe35f5def8014d95a5201dade2c9cb65c075ea822c774dbc72c07876a970b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ef54ef1ee622f8f845db8a938babbcfdd5f88fb39397ef1ca59ec3c4943f1735",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2024-05-28T13:26:12Z",
    "title_canon_sha256": "ff1efc823a5f3c1af5b5964f6113277d674970d2aa5aa17e603dad74ce80d2e5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2405.18166",
    "kind": "arxiv",
    "version": 2
  }
}