Pith Number

pith:LLK7TYZX

pith:2025:LLK7TYZXSRII33SIHT4JVMONJ3

not attested not anchored not stored refs pending

Reinforcement Learning with Rubric Anchors

Guoshan Lu, Haokai Xu, Jianguo Li, Jiaqi Hu, Jiaxin Liu, Junbo Zhao, Peiyi Tu, Ru Peng, Tianyu Zhao, Wenyu Chen, Xiaomeng Hu, Xijun Gu, Yanmei Gu, Yihong Zhuang, Yuanyuan Wang, Yuzhuo Fu, Zenan Huang, Zeyu Qin, Zhanming Shen, Zhengkai Yang, Zhiting Fan

arxiv:2508.12790 v1 · 2025-08-18 · cs.AI · cs.CL · 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{LLK7TYZXSRII33SIHT4JVMONJ3}

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

30 papers in Pith

Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher

ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents

SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents

Receipt and verification

First computed	2026-07-05T11:55:27.281686Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5ad5f9e33794508dee483cf89ab1cd4ec74e5a35053427d637710f8d7445cbba

Aliases

arxiv: 2508.12790 · arxiv_version: 2508.12790v1 · doi: 10.48550/arxiv.2508.12790 · pith_short_12: LLK7TYZXSRII · pith_short_16: LLK7TYZXSRII33SI · pith_short_8: LLK7TYZX

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/LLK7TYZXSRII33SIHT4JVMONJ3 \
  | 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: 5ad5f9e33794508dee483cf89ab1cd4ec74e5a35053427d637710f8d7445cbba

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "afe0a52e4d30f07f695c3233e1c4c4362fec67ab7201af40321b3337701dbc2f",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-08-18T10:06:08Z",
    "title_canon_sha256": "8f87e9d165e5ec2859ddecc94483bfa375cb2737ecd356ecf3aac0cd604badda"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.12790",
    "kind": "arxiv",
    "version": 1
  }
}