Pith Number

pith:BAOAZKMS

pith:2025:BAOAZKMSHAEGMVLOIX4SDHVBUD

not attested not anchored not stored refs pending

Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training

Apoorva Nitsure, Brian Belgodere, Jerret Ross, Jesus Rios, Jiri Navratil, Kristjan Greenewald, Mattia Rigotti, Nicolas Dupuis, Youssef Mroueh

arxiv:2505.22257 v2 · 2025-05-28 · cs.LG · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BAOAZKMSHAEGMVLOIX4SDHVBUD}

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

8 papers in Pith

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

Receipt and verification

First computed	2026-07-05T11:12:34.119481Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

081c0ca992380866556e45f9219ea1a0f44e0d78683dc9393bf4feab1943dbe3

Aliases

arxiv: 2505.22257 · arxiv_version: 2505.22257v2 · doi: 10.48550/arxiv.2505.22257 · pith_short_12: BAOAZKMSHAEG · pith_short_16: BAOAZKMSHAEGMVLO · pith_short_8: BAOAZKMS

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/BAOAZKMSHAEGMVLOIX4SDHVBUD \
  | 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: 081c0ca992380866556e45f9219ea1a0f44e0d78683dc9393bf4feab1943dbe3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e61fd9ff5b55146dc80aaf37d96ad35ff461d9e794eb1fe108314e4789bd371b",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-05-28T11:42:33Z",
    "title_canon_sha256": "f44620a377f93f7d887c27928c0b3760c0c042d36705abf892d2499a2bce4796"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.22257",
    "kind": "arxiv",
    "version": 2
  }
}