Pith Number

pith:3DTCYULK

pith:2025:3DTCYULKYVGXK4XWPGLGXWECBR

not attested not anchored not stored refs pending

SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM

Bin Chen, Bing Yu, Chaohang Wen, Chao Wang, Haotian Zhang, Jinghui Wang, Junyi Peng, Minglei Zhang, Shaojie Wang, Shimiao Jiang, Shiqi Kuang, Shouyu Yin, Wenhao Zhuang, Xiaojiang Zhang, Yinghan Cui, Zheng Lin, Zifei Cheng

arxiv:2504.14286 v2 · 2025-04-19 · 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{3DTCYULKYVGXK4XWPGLGXWECBR}

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

10 papers in Pith

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards

DISA: Offline Importance Sampling for Distribution-Matching LLM-RL

Receipt and verification

First computed	2026-07-05T10:52:23.155763Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d8e62c516ac54d7572f679966bd8820c6f13a6f0c057abfb17f2fb907f8c5e9a

Aliases

arxiv: 2504.14286 · arxiv_version: 2504.14286v2 · doi: 10.48550/arxiv.2504.14286 · pith_short_12: 3DTCYULKYVGX · pith_short_16: 3DTCYULKYVGXK4XW · pith_short_8: 3DTCYULK

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/3DTCYULKYVGXK4XWPGLGXWECBR \
  | 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: d8e62c516ac54d7572f679966bd8820c6f13a6f0c057abfb17f2fb907f8c5e9a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "59165306c115a3a92737b3e4d132add337c31405bc06367f3ea5487d46d7a418",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-04-19T13:06:03Z",
    "title_canon_sha256": "bc275c0153e229821940e265fe4dfe26621ef1ce9137773c4181b33aea0c7b2e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2504.14286",
    "kind": "arxiv",
    "version": 2
  }
}