Pith Number

pith:R3RNULAH

pith:2025:R3RNULAH2ZVUS6HRXSXFA6DB3J

not attested not anchored not stored refs pending

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation

Fan Lai, Haizhong Zheng, Minghao Fang, Udbhav Bamba, Yifan Yu

arxiv:2510.06672 v3 · 2025-10-08 · 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{R3RNULAH2ZVUS6HRXSXFA6DB3J}

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

6 papers in Pith

Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy

Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning

LASER: A Data-Centric Method for Low-Cost and Efficient SQL Rewriting based on SQL-GRPO

Receipt and verification

First computed	2026-05-26T02:03:57.261916Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8ee2da2c07d66b4978f1bcae507861da7987fa4c3d8ed1049fc335be02e65869

Aliases

arxiv: 2510.06672 · arxiv_version: 2510.06672v3 · doi: 10.48550/arxiv.2510.06672 · pith_short_12: R3RNULAH2ZVU · pith_short_16: R3RNULAH2ZVUS6HR · pith_short_8: R3RNULAH

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/R3RNULAH2ZVUS6HRXSXFA6DB3J \
  | 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: 8ee2da2c07d66b4978f1bcae507861da7987fa4c3d8ed1049fc335be02e65869

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4a3ce8dd7bafb378c22e4a4c3dc72707405b15ba991f244f7d43ef7631ecb6ae",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-10-08T05:53:56Z",
    "title_canon_sha256": "aeb3a1f7c27971c892cbf037a77f4e4dd6d2492567454a4a5247814f9a2ee246"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2510.06672",
    "kind": "arxiv",
    "version": 3
  }
}