Pith Number

pith:FUFM5XAV

pith:2025:FUFM5XAVNF56WGVZEI6EYDE4BB

not attested not anchored not stored refs pending

What is the Alignment Objective of GRPO?

Milan Vojnovic, Se-Young Yun

arxiv:2502.18548 v3 · 2025-02-25 · cs.LG · 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{FUFM5XAVNF56WGVZEI6EYDE4BB}

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

Predictable GRPO: A Closed-Form Model of Training Dynamics

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex

f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex

Receipt and verification

First computed	2026-07-05T10:30:31.489784Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2d0acedc15697beb1ab9223c4c0c9c08447de41a62d447b60ae5f67d938c72eb

Aliases

arxiv: 2502.18548 · arxiv_version: 2502.18548v3 · doi: 10.48550/arxiv.2502.18548 · pith_short_12: FUFM5XAVNF56 · pith_short_16: FUFM5XAVNF56WGVZ · pith_short_8: FUFM5XAV

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/FUFM5XAVNF56WGVZEI6EYDE4BB \
  | 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: 2d0acedc15697beb1ab9223c4c0c9c08447de41a62d447b60ae5f67d938c72eb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "57b436cc60cfb230ff9d15b5cae1beb6c413825983b46054b2899458abf1274e",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-02-25T15:56:56Z",
    "title_canon_sha256": "e8a4c6cfbf811e6928fedb9f0888536150863d2acc2321c54f00a6628627c16d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.18548",
    "kind": "arxiv",
    "version": 3
  }
}