Pith Number

pith:PEF2OU4T

pith:2025:PEF2OU4TOXCBZH4PVJNZFZ3AAW

not attested not anchored not stored refs pending

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Aleksander Madry, Bowen Baker, David Farhi, Jakub Pachocki, Joost Huizinga, Leo Gao, Melody Y. Guan, Wojciech Zaremba, Zehao Dou

arxiv:2503.11926 v1 · 2025-03-14 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PEF2OU4TOXCBZH4PVJNZFZ3AAW}

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

23 papers in Pith

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents

Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute

Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics

Receipt and verification

First computed	2026-05-21T07:19:08.432765Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

790ba7539375c41c9f8faa5b92e76005a784d06da9a90c3ef002668a5aa1b086

Aliases

arxiv: 2503.11926 · arxiv_version: 2503.11926v1 · doi: 10.48550/arxiv.2503.11926 · pith_short_12: PEF2OU4TOXCB · pith_short_16: PEF2OU4TOXCBZH4P · pith_short_8: PEF2OU4T

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/PEF2OU4TOXCBZH4PVJNZFZ3AAW \
  | 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: 790ba7539375c41c9f8faa5b92e76005a784d06da9a90c3ef002668a5aa1b086

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2fbdfbb085b5adefc733d5cd9bc5ae7e80bb1de223cb9dc850eefb5d8ee9d4a4",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-03-14T23:50:34Z",
    "title_canon_sha256": "102c0c2ed72098ed7888ecdd28cfdac614ee8c0d65e205fcd64c54134857b2c7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.11926",
    "kind": "arxiv",
    "version": 1
  }
}