Pith Number

pith:HNN3OEEY

pith:2024:HNN3OEEYADEPUWM663H64FCTE3

not attested not anchored not stored refs pending

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Abhay Sheshadri, Aengus Lynch, Aidan Ewart, Asa Cooper Stickland, Cindy Wu, Dylan Hadfield-Menell, Ethan Perez, Henry Sleight, Phillip Guo, Stephen Casper, Vivek Hebbar

arxiv:2407.15549 v3 · 2024-07-22 · 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{HNN3OEEYADEPUWM663H64FCTE3}

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

28 papers in Pith

Efficient Safety Alignment of Language Models via Latent Personality Traits

Safe-RULE: Safe Reinforcement UnLEarning

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment

Sequential Data Poisoning in LLM Post-Training

Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs

Receipt and verification

First computed	2026-07-05T11:44:40.263371Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3b5bb7109800c8fa599ef6cfee145326ec3e153b71d76e7569b688bbfec5e1ab

Aliases

arxiv: 2407.15549 · arxiv_version: 2407.15549v3 · doi: 10.48550/arxiv.2407.15549 · pith_short_12: HNN3OEEYADEP · pith_short_16: HNN3OEEYADEPUWM6 · pith_short_8: HNN3OEEY

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/HNN3OEEYADEPUWM663H64FCTE3 \
  | 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: 3b5bb7109800c8fa599ef6cfee145326ec3e153b71d76e7569b688bbfec5e1ab

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7a680a54cd4ca320e76b5d59d3a63440abbefaa17dde1a62a6661b4156248be3",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-07-22T11:19:14Z",
    "title_canon_sha256": "d6ad46685abef5958f311df6bee41f32a92dc728a847712d22351ce96bcce3ea"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2407.15549",
    "kind": "arxiv",
    "version": 3
  }
}