Pith Number

pith:TH6SPZXZ

pith:2023:TH6SPZXZDELM3PQ5YD3RARPAVE

not attested not anchored not stored refs pending

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Haoran Wang, Kai Shu

arxiv:2311.09433 v3 · 2023-11-15 · 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{TH6SPZXZDELM3PQ5YD3RARPAVE}

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

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

AgentReview: Exploring Peer Review Dynamics with LLM Agents

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

Refusal in Language Models Is Mediated by a Single Direction

On the Privacy of LLMs: An Ablation Study

Receipt and verification

First computed	2026-07-05T08:55:49.185350Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

99fd27e6f91916cdbe1dc0f71045e0a9241297fcc7824a2f22896f0a183081df

Aliases

arxiv: 2311.09433 · arxiv_version: 2311.09433v3 · doi: 10.48550/arxiv.2311.09433 · pith_short_12: TH6SPZXZDELM · pith_short_16: TH6SPZXZDELM3PQ5 · pith_short_8: TH6SPZXZ

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/TH6SPZXZDELM3PQ5YD3RARPAVE \
  | 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: 99fd27e6f91916cdbe1dc0f71045e0a9241297fcc7824a2f22896f0a183081df

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c2897057f81e15eab1aa7568fe0a5f368c7a14847be3c425c9fa93d50b93990a",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2023-11-15T23:07:40Z",
    "title_canon_sha256": "48869b2ae97ad78a96c2b566ddca4d229cc4c8ea777cd0aa0e44d709a0e80f53"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2311.09433",
    "kind": "arxiv",
    "version": 3
  }
}