Pith Number

pith:QMYUDFWA

pith:2025:QMYUDFWAX4FXXBHUYD2P2UWX3Z

not attested not anchored not stored refs pending

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning

Andy Arditi, Joe Benton, Julian Michael, Marvin Li, Miles Turpin

arxiv:2506.22777 v2 · 2025-06-28 · cs.CL · 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{QMYUDFWAX4FXXBHUYD2P2UWX3Z}

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

4 papers in Pith

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Receipt and verification

First computed	2026-07-05T11:36:33.745862Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

83314196c0bf0b7b84f4c0f4fd52d7de5c2fecc470f21faa21bd1108d00c7560

Aliases

arxiv: 2506.22777 · arxiv_version: 2506.22777v2 · doi: 10.48550/arxiv.2506.22777 · pith_short_12: QMYUDFWAX4FX · pith_short_16: QMYUDFWAX4FXXBHU · pith_short_8: QMYUDFWA

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/QMYUDFWAX4FXXBHUYD2P2UWX3Z \
  | 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: 83314196c0bf0b7b84f4c0f4fd52d7de5c2fecc470f21faa21bd1108d00c7560

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d5c02fa9d9f6cf323e0ad8233d295fd38a3969fc9140e7f20bc933ea4299d83c",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-06-28T06:37:10Z",
    "title_canon_sha256": "4a99ca29dd93783ca280883a4e2b876f7f49751323e1ebdaf84df9f4d166d29f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.22777",
    "kind": "arxiv",
    "version": 2
  }
}