Pith Number

pith:MBBCYRW6

pith:2024:MBBCYRW6NROTE64AGNQ5HOUMQN

not attested not anchored not stored refs pending

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Bill Yuchen Lin, Fengqing Jiang, Jinyuan Jia, Luyao Niu, Radha Poovendran, Zhangchen Xu

arxiv:2402.08983 v4 · 2024-02-14 · cs.CR · cs.AI · 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{MBBCYRW6NROTE64AGNQ5HOUMQN}

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

11 papers in Pith

SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

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

Receipt and verification

First computed	2026-07-05T08:48:41.302689Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

60422c46de6c5d327b803361d3ba8c8362f30d975208a4fd361ae2aba26a5560

Aliases

arxiv: 2402.08983 · arxiv_version: 2402.08983v4 · doi: 10.48550/arxiv.2402.08983 · pith_short_12: MBBCYRW6NROT · pith_short_16: MBBCYRW6NROTE64A · pith_short_8: MBBCYRW6

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/MBBCYRW6NROTE64AGNQ5HOUMQN \
  | 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: 60422c46de6c5d327b803361d3ba8c8362f30d975208a4fd361ae2aba26a5560

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f858b4341ecae7901441d136ebda6c18cccce87ecc228cfaf524d3ebe8a7ba35",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2024-02-14T06:54:31Z",
    "title_canon_sha256": "0ce4061727074ac4fc22b1656cbec25cc064ba6b4f7bee34545182db619934f8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2402.08983",
    "kind": "arxiv",
    "version": 4
  }
}