Pith. sign in
Pith Number

pith:XIIL7R4U

pith:2024:XIIL7R4UBZAEPCYLKLG4BEOILE
not attested not anchored not stored refs pending

On the Role of Attention Heads in Large Language Model Safety

Fei Huang, Haiyang Yu, Junfeng Fang, Kun Wang, Rongwu Xu, Xinghua Zhang, Yang Liu, Yongbin Li, Zhenhong Zhou

arxiv:2410.13708 v2 · 2024-10-17 · cs.CL · cs.AI · cs.CR · 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{XIIL7R4UBZAEPCYLKLG4BEOILE}

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

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Soft Head Selection for Injecting ICL-Derived Task Embeddings
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs
Receipt and verification
First computed 2026-07-05T10:18:43.610466Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

ba10bfc7940e40478b0b52cdc091c859201465fb3f502a086a44e8da8584a202

Aliases

arxiv: 2410.13708 · arxiv_version: 2410.13708v2 · doi: 10.48550/arxiv.2410.13708 · pith_short_12: XIIL7R4UBZAE · pith_short_16: XIIL7R4UBZAEPCYL · pith_short_8: XIIL7R4U
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/XIIL7R4UBZAEPCYLKLG4BEOILE \
  | 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: ba10bfc7940e40478b0b52cdc091c859201465fb3f502a086a44e8da8584a202
Canonical record JSON 
{
  "metadata": {
    "abstract_canon_sha256": "4268a5157963e9812b49d7e1341762ab5786a81284c475925b5fa7357cffa2f7",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CR",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-10-17T16:08:06Z",
    "title_canon_sha256": "194dc5a0d8c44030b738e852c1cfa25412ba1c88806e9375c62594e754e0c7be"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2410.13708",
    "kind": "arxiv",
    "version": 2
  }
}