Pith. sign in
Pith Number

pith:OWZLOWUR

pith:2025:OWZLOWUR4RN22EUFGPMDPRSFMS
not attested not anchored not stored refs pending

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets

Lei Hsiung, Linyue Song, Pin-Yu Chen, Tianyu Pang, Tsung-Yi Ho, Yaoqing Yang, Yung-Chen Tang

arxiv:2506.05346 v1 · 2025-06-05 · cs.CR · cs.CL · 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{OWZLOWUR4RN22EUFGPMDPRSFMS}

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

6 papers in Pith

Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries
The Evaluation Game: Beyond Static LLM Benchmarking
The Power of Order: Fooling LLMs with Adversarial Table Permutations
The Power of Order: Fooling LLMs with Adversarial Table Permutations
Receipt and verification
First computed 2026-07-05T11:16:46.213593Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

75b2b75a91e45bad128533d837c6456490332fa02c570739ce549bbe9a0a68aa

Aliases

arxiv: 2506.05346 · arxiv_version: 2506.05346v1 · doi: 10.48550/arxiv.2506.05346 · pith_short_12: OWZLOWUR4RN2 · pith_short_16: OWZLOWUR4RN22EUF · pith_short_8: OWZLOWUR
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/OWZLOWUR4RN22EUFGPMDPRSFMS \
  | 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: 75b2b75a91e45bad128533d837c6456490332fa02c570739ce549bbe9a0a68aa
Canonical record JSON 
{
  "metadata": {
    "abstract_canon_sha256": "84d4d599a91bb86e0fdb3a7b4420dae9f3b0daf4ae843a4fc11593615ae0e485",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2025-06-05T17:59:55Z",
    "title_canon_sha256": "2df6fd9183487b510367d6d197893ed5e7823df56e620c4a0242204d0fc94dfd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.05346",
    "kind": "arxiv",
    "version": 1
  }
}