Pith Number

pith:WE255U7D

pith:2024:WE255U7DH2S4LQK5YNQRU35JCW

not attested not anchored not stored refs pending

Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Dylan Hadfield-Menell, Lennart Schulze, Oam Patel, Stephen Casper

arxiv:2403.05030 v6 · 2024-03-08 · cs.CR · cs.AI · 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{WE255U7DH2S4LQK5YNQRU35JCW}

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

11 papers in Pith

Efficient Safety Alignment of Language Models via Latent Personality Traits

Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment

Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols

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

Designing Incident Reporting Systems for Harms from General-Purpose AI

Receipt and verification

First computed	2026-07-05T11:44:39.106619Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b135ded3e33ea5c5c15dc3611a6fa9158914189f2014d5520ad7323d830dd9b6

Aliases

arxiv: 2403.05030 · arxiv_version: 2403.05030v6 · doi: 10.48550/arxiv.2403.05030 · pith_short_12: WE255U7DH2S4 · pith_short_16: WE255U7DH2S4LQK5 · pith_short_8: WE255U7D

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/WE255U7DH2S4LQK5YNQRU35JCW \
  | 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: b135ded3e33ea5c5c15dc3611a6fa9158914189f2014d5520ad7323d830dd9b6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4756a843d52927526eb8c6576076d0767705bd292998e587273e55b633913a6d",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2024-03-08T04:22:48Z",
    "title_canon_sha256": "05b742624a3ef983212a95a79c25989f97c44bca8ad6fef9a0305cd1a993f5e3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2403.05030",
    "kind": "arxiv",
    "version": 6
  }
}