Pith Number

pith:5METPRLA

pith:2025:5METPRLAG7EYRGO2VVOKHWME4E

not attested not anchored not stored refs pending

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Dong Yu, Haitao Mi, Jiahao Xu, Pinjia He, Tian Liang, Wenxuan Wang, Xiaoyuan Liu, Zhaopeng Tu, Zhiwei He

arxiv:2505.13445 v1 · 2025-05-19 · 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{5METPRLAG7EYRGO2VVOKHWME4E}

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

7 papers in Pith

Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

ICRL: Learning to Internalize Self-Critique with Reinforcement Learning

Selective Off-Policy Reference Tuning with Plan Guidance

Receipt and verification

First computed	2026-07-05T11:05:30.289474Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

eb0937c56037c98899daad5ca3d984e11324f686a375f2f1f80053a1ca30e0d6

Aliases

arxiv: 2505.13445 · arxiv_version: 2505.13445v1 · doi: 10.48550/arxiv.2505.13445 · pith_short_12: 5METPRLAG7EY · pith_short_16: 5METPRLAG7EYRGO2 · pith_short_8: 5METPRLA

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/5METPRLAG7EYRGO2VVOKHWME4E \
  | 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: eb0937c56037c98899daad5ca3d984e11324f686a375f2f1f80053a1ca30e0d6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f65761d4dda5886dd907144a1847d4055109d4ad083b82b2cc5a734961453a86",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-05-19T17:59:31Z",
    "title_canon_sha256": "934e35a029ad0c1b1a17880e51115c26251a07ea595b982404fc5933b884e0f0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.13445",
    "kind": "arxiv",
    "version": 1
  }
}