Pith Number

pith:ODALYDF2

pith:2024:ODALYDF2OTUDXWHQZMHNZY4FPO

not attested not anchored not stored refs pending

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Boyi Wei, Kaixuan Huang, Mengdi Wang, Mengzhou Xia, Peter Henderson, Prateek Mittal, Tinghao Xie, Xiangyu Qi, Yangsibo Huang

arxiv:2402.05162 v4 · 2024-02-07 · cs.LG · 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{ODALYDF2OTUDXWHQZMHNZY4FPO}

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

16 papers in Pith

Faithfulness to Refusal: A Causal Audit of Neuron Selectors

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets

Persona-Model Collapse in Emergent Misalignment

A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving

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

Receipt and verification

First computed	2026-07-05T09:25:39.490118Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

70c0bc0cba74e83bd8f0cb0edce3857ba0f99944f5681faf384d7bf7e7411d9c

Aliases

arxiv: 2402.05162 · arxiv_version: 2402.05162v4 · doi: 10.48550/arxiv.2402.05162 · pith_short_12: ODALYDF2OTUD · pith_short_16: ODALYDF2OTUDXWHQ · pith_short_8: ODALYDF2

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/ODALYDF2OTUDXWHQZMHNZY4FPO \
  | 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: 70c0bc0cba74e83bd8f0cb0edce3857ba0f99944f5681faf384d7bf7e7411d9c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "54acf59667ff6ccfac9816ddab5f5c5d91785bff227fa2d91c6e6d70cf494667",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-02-07T18:34:38Z",
    "title_canon_sha256": "3344489afdccf9f16e936a88ebd47396f69ae75967ee7a9a707dab0cb3e721b4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2402.05162",
    "kind": "arxiv",
    "version": 4
  }
}