Pith Number

pith:Y73VMJFI

pith:2025:Y73VMJFI2HFW5YFBHLWXNHCQZN

not attested not anchored not stored refs pending

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization

Dong Huang, Luu Anh Tuan, Mingzhe Du, Qian Liu, See-kiong Ng, Xinyi He, Yue Liu, Yuhao Qing, Zejun Ma

arxiv:2505.23387 v3 · 2025-05-29 · cs.SE · 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{Y73VMJFI2HFW5YFBHLWXNHCQZN}

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

9 papers in Pith

SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation

Chiseling Out Efficiency: Structured Skeleton Supervision for Efficient Code Generation

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

Receipt and verification

First computed	2026-07-05T11:15:00.698058Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c7f75624a8d1cb6ee0a13aed769c50cb7ba648c067905d9ba131d43e42fa7281

Aliases

arxiv: 2505.23387 · arxiv_version: 2505.23387v3 · doi: 10.48550/arxiv.2505.23387 · pith_short_12: Y73VMJFI2HFW · pith_short_16: Y73VMJFI2HFW5YFB · pith_short_8: Y73VMJFI

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/Y73VMJFI2HFW5YFBHLWXNHCQZN \
  | 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: c7f75624a8d1cb6ee0a13aed769c50cb7ba648c067905d9ba131d43e42fa7281

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "891dfba1256e1b3cb6a10b88204c8861858e83d8a84ad1c660a491ed51a8cca9",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2025-05-29T12:14:29Z",
    "title_canon_sha256": "9f6cf7b81ddac9dc10d269f04d1c3845cbda9655d9d5cccfd67b2ba74dbf87c5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.23387",
    "kind": "arxiv",
    "version": 3
  }
}