Pith Number

pith:L4YR4RGU

pith:2024:L4YR4RGUOMAGXKAOI3MN2KI2OS

not attested not anchored not stored refs pending

Secrets of RLHF in Large Language Models Part II: Reward Modeling

Binghai Wang, Caishuang Huang, Chenyu Shi, Enyu Zhou, Hang Yan, Jun Zhao, Lixing Shen, Lu Chen, Nuo Xu, Qi Zhang, Rui Zheng, Senjie Jin, Shihan Dou, Songyang Gao, Tao Gui, Tao Ji, Wei Shen, Xiaoran Fan, Xiao Wang, Xipeng Qiu, Xuanjing Huang, Yan Liu, Yu-Gang Jiang, Yuhao Zhou, Zhan Chen, Zhiheng Xi, Zuxuan Wu

arxiv:2401.06080 v2 · 2024-01-11 · 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{L4YR4RGUOMAGXKAOI3MN2KI2OS}

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

22 papers in Pith

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

Understanding helpfulness and harmless tension in reward models

Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization

BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards

Receipt and verification

First computed	2026-07-05T07:32:45.902283Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5f311e44d473006ba80e46d8dd291a7483f5f48ded40fcbb91e4e543934a54ff

Aliases

arxiv: 2401.06080 · arxiv_version: 2401.06080v2 · doi: 10.48550/arxiv.2401.06080 · pith_short_12: L4YR4RGUOMAG · pith_short_16: L4YR4RGUOMAGXKAO · pith_short_8: L4YR4RGU

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/L4YR4RGUOMAGXKAOI3MN2KI2OS \
  | 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: 5f311e44d473006ba80e46d8dd291a7483f5f48ded40fcbb91e4e543934a54ff

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b5cb2bb7a43f2ef38b68e830eb925e9c44251a95f4798f4a9cc8dafd7b30c922",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2024-01-11T17:56:59Z",
    "title_canon_sha256": "9bc59c8055a435abbd703a9c8d769f052216263221491a5d8d240b1fbccc3390"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2401.06080",
    "kind": "arxiv",
    "version": 2
  }
}