Pith Number

pith:JESFYQN6

pith:2020:JESFYQN6V5D5V7NSADHFEEHKNM

not attested not anchored not stored refs pending

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

Adrian Weller, Alex Ingerman, Allan Dafoe, Amanda Askell, Andrew Lohn, Andrew Trask, Ariel Herbert-Voss, Ben Laurie, Bianca Martin, Brian Tse, Carina Prunkl, Carrick Flynn, Charlotte Stix, Cullen O'Keefe, David Krueger, Elizabeth Barnes, Elizabeth Seger, Emma Bluemke, Federica Carugati, Frens Kroeger, Gillian Hadfield, Girish Sastry, Gretchen Krueger, Haydn Belfield, Heidy Khlaaf, Helen Toner, Igor Krawczuk, Jack Clark, Jade Leung, Jasmine Wang, JB Rubinovitz, Jingying Yang, Jonathan Lebensold, Lisa Dyer, Logan Graham, Maritza Johnson, Mark Koren, Markus Anderljung, Martijn Rasser, Miles Brundage, Noa Zilberman, Pang Wei Koh, Paul Scharre, Peter Eckersley, Peter Henderson, Rebecca Kagan, Rosario Cammarota, Ruth Fong, Saif Khan, Sarah de Haas, Sara Hooker, Se\'an \'O h\'Eigeartaigh, Shagun Sodhani, Shahar Avin, Tamay Besiroglu, Tegan Maharaj, Th\'eo Ryffel, Thomas Krendl Gilbert, Yoshua Bengio

arxiv:2004.07213 v2 · 2020-04-15 · 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{JESFYQN6V5D5V7NSADHFEEHKNM}

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

18 papers in Pith

The AI Evaluability Gap: The Missing Layer for Managing Risk and Sustaining Value

Automation and AI Technology in Surface Mining With a Brief Introduction to Open-Pit Operations in the Pilbara

Output-Constrained Decision Trees

Large Language Model Agent: A Survey on Methodology, Applications and Challenges

LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions

Receipt and verification

First computed	2026-07-05T00:56:49.781630Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

49245c41beaf47dafdb200ce5210ea6b0e5e74901491dce4823d5797ca8dea4a

Aliases

arxiv: 2004.07213 · arxiv_version: 2004.07213v2 · doi: 10.48550/arxiv.2004.07213 · pith_short_12: JESFYQN6V5D5 · pith_short_16: JESFYQN6V5D5V7NS · pith_short_8: JESFYQN6

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/JESFYQN6V5D5V7NSADHFEEHKNM \
  | 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: 49245c41beaf47dafdb200ce5210ea6b0e5e74901491dce4823d5797ca8dea4a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "269e108d4a351ecbdd1d62c4a4374d6f7691305aade5244428a3e08f046b682a",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CY",
    "submitted_at": "2020-04-15T17:15:35Z",
    "title_canon_sha256": "accfcaab10709ebdfd803b8bb736c34a6d452d1a4787dc4eb238996cc479fc23"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2004.07213",
    "kind": "arxiv",
    "version": 2
  }
}