Pith Number

pith:U4EW5DVJ

pith:2025:U4EW5DVJEM5WGBYQ4AURKGTS7S

not attested not anchored not stored refs pending

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training

Caishuang Huang, Chenhao Huang, Dingwei Zhu, Enyu Zhou, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Ming Zhang, Qi Zhang, Senjie Jin, Shihan Dou, Tao Gui, Xipeng Qiu, Xuanjing Huang, Yuhui Wang, Yunke Zhang, Yuran Wang, Zhiheng Xi

arxiv:2508.03058 v2 · 2025-08-05 · cs.LG · cs.AI · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{U4EW5DVJEM5WGBYQ4AURKGTS7S}

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

3 papers in Pith

Trust Region On-Policy Distillation

Explicit Critic Guidance for Aligning Diffusion Models

Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning

Receipt and verification

First computed	2026-06-23T02:12:32.632478Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a7096e8ea9233b630710e029151a72fc90d9ecb2c266432171f4916cb1be3657

Aliases

arxiv: 2508.03058 · arxiv_version: 2508.03058v2 · doi: 10.48550/arxiv.2508.03058 · pith_short_12: U4EW5DVJEM5W · pith_short_16: U4EW5DVJEM5WGBYQ · pith_short_8: U4EW5DVJ

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/U4EW5DVJEM5WGBYQ4AURKGTS7S \
  | 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: a7096e8ea9233b630710e029151a72fc90d9ecb2c266432171f4916cb1be3657

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "dd19ed0bd33d4fc1b4756639e11976de26fc658fe5ec0acc7421397c757bb42d",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-08-05T04:05:15Z",
    "title_canon_sha256": "a9ea9560578f27f9b87d0c921e54a5bb7f5d21c6673c449982c7603249463afb"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.03058",
    "kind": "arxiv",
    "version": 2
  }
}