Pith Number

pith:RND6AART

pith:2025:RND6AARTW5VGVJBXVMQKBP7EAE

not attested not anchored not stored refs pending

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts

Beidi Chen, Bhavya Kailkhura, Brian R. Bartoldson, Fan Lai, Haizhong Zheng, Jiawei Zhao, Yang Zhou

arxiv:2506.02177 v1 · 2025-06-02 · cs.AI · 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{RND6AARTW5VGVJBXVMQKBP7EAE}

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

25 papers in Pith

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning

N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization

CATPO: Critique-Augmented Tree Policy Optimization

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

On Advantage Estimates for Max@K Policy Gradients

Receipt and verification

First computed	2026-07-05T11:14:33.770986Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8b47e00233b76a6aa437ab20a0bfe40108d2cf81a3618cded7c76f9a75ad4785

Aliases

arxiv: 2506.02177 · arxiv_version: 2506.02177v1 · doi: 10.48550/arxiv.2506.02177 · pith_short_12: RND6AARTW5VG · pith_short_16: RND6AARTW5VGVJBX · pith_short_8: RND6AART

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/RND6AARTW5VGVJBXVMQKBP7EAE \
  | 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: 8b47e00233b76a6aa437ab20a0bfe40108d2cf81a3618cded7c76f9a75ad4785

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "59fa664d92ef60765eb31f1be3294fbc4c5ebb657074d459d3631020b70d083b",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-06-02T19:03:00Z",
    "title_canon_sha256": "70002ab0940069bca99d1a2a4da6401eb1d0a531596b87ebff4d05de5c7a462c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.02177",
    "kind": "arxiv",
    "version": 1
  }
}