Pith Number

pith:7KMPHQDO

pith:2025:7KMPHQDOUYPPUP2OZR3VQ42XWD

not attested not anchored not stored refs pending

S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning

Bang Zhang, Cheng Liu, Jia Li, Jiaqi Chen, Nan Du, Peisong Wang, Ruotian Ma, Xingyan Liu, Xin Zhou

arxiv:2502.12853 v1 · 2025-02-18 · cs.CL · 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{7KMPHQDOUYPPUP2OZR3VQ42XWD}

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

5 papers in Pith

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering

From System 1 to System 2: A Survey of Reasoning Large Language Models

Multi-modal Reasoning with LLMs for Visual Semantic Arithmetic

SVSR: A Self-Verification and Self-Rectification Paradigm for Multimodal Reasoning

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning

Receipt and verification

First computed	2026-07-05T10:16:25.326099Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fa98f3c06ea61efa3f4ecc77587357b0e63b3e10d0aca2eab71e12610ebd1f7c

Aliases

arxiv: 2502.12853 · arxiv_version: 2502.12853v1 · doi: 10.48550/arxiv.2502.12853 · pith_short_12: 7KMPHQDOUYPP · pith_short_16: 7KMPHQDOUYPPUP2O · pith_short_8: 7KMPHQDO

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/7KMPHQDOUYPPUP2OZR3VQ42XWD \
  | 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: fa98f3c06ea61efa3f4ecc77587357b0e63b3e10d0aca2eab71e12610ebd1f7c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8ead46da08533a3cbe5e3024f8855dd8611d8f806215bb5b36407c57878f6507",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-02-18T13:40:22Z",
    "title_canon_sha256": "54a4ed2e32c4fe6cc4830c8d8db45a2e119bf9d13328aac6e9eeb5ac313de1dc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.12853",
    "kind": "arxiv",
    "version": 1
  }
}