Pith Number

pith:EOQZGMUF

pith:2025:EOQZGMUF5W65JSQQPAUGZJNNGA

not attested not anchored not stored refs pending

Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening

Andre He, Daniel Fried, Sean Welleck

arxiv:2506.02355 v2 · 2025-06-03 · 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{EOQZGMUF5W65JSQQPAUGZJNNGA}

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

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

Teacher-Free Self-Training Amplifies but Does Not Compound: A Pass@$K$ Crossover on a Free-Verifier Domain

On Advantage Estimates for Max@K Policy Gradients

BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards

Polychromic Objectives for Reinforcement Learning

Receipt and verification

First computed	2026-07-05T11:24:21.783767Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

23a1933285edbdd4ca1078286ca5ad300b35bea4a2b6167993bff0468c197140

Aliases

arxiv: 2506.02355 · arxiv_version: 2506.02355v2 · doi: 10.48550/arxiv.2506.02355 · pith_short_12: EOQZGMUF5W65 · pith_short_16: EOQZGMUF5W65JSQQ · pith_short_8: EOQZGMUF

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/EOQZGMUF5W65JSQQPAUGZJNNGA \
  | 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: 23a1933285edbdd4ca1078286ca5ad300b35bea4a2b6167993bff0468c197140

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4b508de4a02db58e113f64fdce8377b03a2e234e3535af5ea3f65e81ce57d59a",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-06-03T01:15:15Z",
    "title_canon_sha256": "63c9a06f85bf570ac08526abbc4d78f5949a73adb832f290582f085586f6d4f0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.02355",
    "kind": "arxiv",
    "version": 2
  }
}