Pith Number

pith:QIJHMMIU

pith:2025:QIJHMMIU7WIBIPJI5KXMXHCIXX

not attested not anchored not stored refs pending

PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier

Chao Xin, Lin Yan, Qianchuan Zhao, Wenyuan Xu, Yufeng Yuan, Yuhua Jiang, Yuwen Xiong, Yu Yue

arxiv:2506.10406 v1 · 2025-06-12 · cs.CL · 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{QIJHMMIU7WIBIPJI5KXMXHCIXX}

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

REVES: REvision and VErification--Augmented Training for Test-Time Scaling

Trust Region On-Policy Distillation

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions

A Survey of Reinforcement Learning for Large Reasoning Models

Receipt and verification

First computed	2026-07-05T11:20:22.901018Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8212763114fd90143d28eaaecb9c48bdf603ed0f57db8c36f39a4fa78f754446

Aliases

arxiv: 2506.10406 · arxiv_version: 2506.10406v1 · doi: 10.48550/arxiv.2506.10406 · pith_short_12: QIJHMMIU7WIB · pith_short_16: QIJHMMIU7WIBIPJI · pith_short_8: QIJHMMIU

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/QIJHMMIU7WIBIPJI5KXMXHCIXX \
  | 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: 8212763114fd90143d28eaaecb9c48bdf603ed0f57db8c36f39a4fa78f754446

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2fb0f35ee56e3e2bf9349385c9dbd1bb5b6264ea0efc91c77499dd72860715dd",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-06-12T06:59:35Z",
    "title_canon_sha256": "f2e9bcc801555309351daa46d2c058bc54005f1e1e3b7b03e39dd1fe91749451"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.10406",
    "kind": "arxiv",
    "version": 1
  }
}