Pith Number

pith:X5A3QW32

pith:2024:X5A3QW327MR2UEHB6GIDGM3AEA

not attested not anchored not stored refs pending

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Abulhair Saparov, Alan Chan, Aleksandar Petrov, Alexander Pan, Anton Korinek, Atoosa Kasirzadeh, Benjamin L. Edelman, Christian Schroeder de Witt, Daniel Paleka, Danqi Chen, David Krueger, Ekdeep Singh Lubana, Eric Bigelow, Erik Jenner, Florian Tramer, Gabriel Recchia, Giulio Corsi, He He, Heidi Zhang, Jakob Foerster, Javier Rando, Jose Hernandez-Orallo, Lauro Langosco, Lewis Hammond, Lilian Edwards, Mario G\"unther, Markus Anderljung, Miles Turpin, Oliver Sourbut, Peter Hase, Philip H.S. Torr, Ruiqi Zhong, Samuel Albanie, Se\'an \'O h\'Eigeartaigh, Stephen Casper, Sumeet Ramesh Motwan, Tegan Maharaj, Tomasz Korbak, Usman Anwar, Yejin Choi, Yoshua Bengio, Zhaowei Zhang

arxiv:2404.09932 v2 · 2024-04-15 · cs.LG · cs.AI · cs.CL · cs.CY

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{X5A3QW327MR2UEHB6GIDGM3AEA}

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

21 papers in Pith

Investigating The Security of Modern AI and Cloud Infrastructure

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders

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

Receipt and verification

First computed	2026-07-05T09:03:52.856623Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bf41b85b7afb23aa10e1f190333360200ca978c78595569f2e4f716d94f62911

Aliases

arxiv: 2404.09932 · arxiv_version: 2404.09932v2 · doi: 10.48550/arxiv.2404.09932 · pith_short_12: X5A3QW327MR2 · pith_short_16: X5A3QW327MR2UEHB · pith_short_8: X5A3QW32

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/X5A3QW327MR2UEHB6GIDGM3AEA \
  | 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: bf41b85b7afb23aa10e1f190333360200ca978c78595569f2e4f716d94f62911

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f0bb85f43fd698cc4f545b3138fa2a94aa0c06b4a0d3d107b31ec0c66f4b5b4a",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL",
      "cs.CY"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-04-15T16:58:28Z",
    "title_canon_sha256": "1e5ca19e9f4a87aa343df30f0ea7c8549389cc62167f38f1b4f6123a5d06f9fb"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2404.09932",
    "kind": "arxiv",
    "version": 2
  }
}