Pith Number

pith:HL5YFUJS

pith:2025:HL5YFUJSVDXGKH6F26QUUOY6MM

not attested not anchored not stored refs pending

Adversarial Training of Reward Models

Adithya Renduchintala, Alexander Bukharin, Haifeng Qian, Oleksii Kuchaiev, Olivier Delalleau, Shengyang Sun, Soumye Singhal, Tuo Zhao, Zhilin Wang

arxiv:2504.06141 v2 · 2025-04-08 · 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{HL5YFUJSVDXGKH6F26QUUOY6MM}

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

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning

Trust Region On-Policy Distillation

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback

Receipt and verification

First computed	2026-07-05T10:47:57.957153Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3afb82d132a8ee651fc5d7a14a3b1e63114f83879d84de9eccd8cc460dae18d0

Aliases

arxiv: 2504.06141 · arxiv_version: 2504.06141v2 · doi: 10.48550/arxiv.2504.06141 · pith_short_12: HL5YFUJSVDXG · pith_short_16: HL5YFUJSVDXGKH6F · pith_short_8: HL5YFUJS

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/HL5YFUJSVDXGKH6F26QUUOY6MM \
  | 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: 3afb82d132a8ee651fc5d7a14a3b1e63114f83879d84de9eccd8cc460dae18d0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6364a0b1bb21fce200f2844dc3e6cbe266252a11969831d695fe738dc87a1b9e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-04-08T15:38:25Z",
    "title_canon_sha256": "073f5a39139677eda19602a08a374341a7353f3683382dc0490c7a34784f78c8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2504.06141",
    "kind": "arxiv",
    "version": 2
  }
}