Pith Number

pith:QZTY4XUO

pith:2024:QZTY4XUOWDDO2JFH5CKLBY3ESP

not attested not anchored not stored refs pending

Robust LLM safeguarding via refusal feature adversarial training

Karen Hambardzumyan, Lei Yu, Nicola Cancedda, Virginie Do

arxiv:2409.20089 v2 · 2024-09-30 · cs.LG · cs.CL · cs.CR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{QZTY4XUOWDDO2JFH5CKLBY3ESP}

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

4 papers in Pith

Efficient Safety Alignment of Language Models via Latent Personality Traits

Harnessing non-adversarial robustness in large language models

LLM-Safety Evaluations Lack Robustness

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms

Receipt and verification

First computed	2026-07-05T10:35:36.560307Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

86678e5e8eb0c6ed24a7e894b0e36493d8fc9eaebf369306d64704d2ca06998a

Aliases

arxiv: 2409.20089 · arxiv_version: 2409.20089v2 · doi: 10.48550/arxiv.2409.20089 · pith_short_12: QZTY4XUOWDDO · pith_short_16: QZTY4XUOWDDO2JFH · pith_short_8: QZTY4XUO

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/QZTY4XUOWDDO2JFH5CKLBY3ESP \
  | 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: 86678e5e8eb0c6ed24a7e894b0e36493d8fc9eaebf369306d64704d2ca06998a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d82124a87f82985217f4cd6c3c6bdf32dc681af99d02a3b9f3856b94efa01c9f",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.CR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-09-30T08:41:39Z",
    "title_canon_sha256": "5506a9e23dc84486ea1dbed0755cd9d005c1d172d80c34f239a4691ee8d615f1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2409.20089",
    "kind": "arxiv",
    "version": 2
  }
}