Pith Number

pith:JAZXSO7A

pith:2026:JAZXSO7AP45V32VNEHI4B7RVYG

not attested not anchored not stored refs pending

Rethinking the Trust Region in LLM Reinforcement Learning

Chao Du, Min Lin, Penghui Qi, Tianyu Pang, Wee Sun Lee, Xiangxin Zhou, Zichen Liu

arxiv:2602.04879 v2 · 2026-02-04 · 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{JAZXSO7AP45V32VNEHI4B7RVYG}

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

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

Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates

Policy Improvement Reinforcement Learning

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

ZAYA1-8B Technical Report

Receipt and verification

First computed	2026-05-27T01:05:44.090209Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4833793be07f3b5deaad21d1c0fe35c1884a8f78aab7b96e1a3402ebe75dfda1

Aliases

arxiv: 2602.04879 · arxiv_version: 2602.04879v2 · doi: 10.48550/arxiv.2602.04879 · pith_short_12: JAZXSO7AP45V · pith_short_16: JAZXSO7AP45V32VN · pith_short_8: JAZXSO7A

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/JAZXSO7AP45V32VNEHI4B7RVYG \
  | 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: 4833793be07f3b5deaad21d1c0fe35c1884a8f78aab7b96e1a3402ebe75dfda1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a0f2c2bec1e1b1e5cdbd5c800575b30a2b44350e21314a34dd59c49b9b76debc",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-02-04T18:59:04Z",
    "title_canon_sha256": "07dfe94646fd52c73a5ab32c147e3006959ccad0c9d4e47d47dcd6c45bcec377"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.04879",
    "kind": "arxiv",
    "version": 2
  }
}