Pith Number

pith:PDCTJBTC

pith:2023:PDCTJBTC6GDYS74PKQ3BCJJPGR

not attested not anchored not stored refs resolved

Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Damai Dai, Deli Chen, Lei Li, Peiyi Wang, R.X. Xu, Yifei Li, Y.Wu, Zhifang Sui, Zhihong Shao

Math-Shepherd trains reward models on auto-generated step labels to verify and reinforce LLM math solutions without human annotations.

arxiv:2312.08935 v3 · 2023-12-14 · cs.AI · 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{PDCTJBTC6GDYS74PKQ3BCJJPGR}

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.

Claims

C1strongest claim

the step-by-step PPO with Math-Shepherd significantly improves the accuracy of Mistral-7B (77.9%→84.1% on GSM8K and 28.6%→33.0% on MATH). The accuracy can be further enhanced to 89.1% and 43.5% on GSM8K and MATH with the verification of Math-Shepherd.

C2weakest assumption

That automatically constructed process-wise supervision data accurately labels correct versus incorrect reasoning steps without systematic bias or noise from the generation process itself.

C3one line summary

Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.

References

60 extracted · 60 resolved · 19 Pith anchors

[1] Red teaming language models with language models 2022 · doi:10.18653/v1/2022.emnlp-main.225

[10] International Conference on Machine Learning , pages= 2023

[11] Proceedings of the 29th Symposium on Operating Systems Principles , pages=

[13] Chi and Quoc V

[14] Xuezhi Wang and Jason Wei and Dale Schuurmans and Quoc V. Le and Ed H. Chi and Sharan Narang and Aakanksha Chowdhery and Denny Zhou , title =. The Eleventh International Conference on Learning Represe 2023

Formal links

2 machine-checked theorem links

Cited by

39 papers in Pith

How Far Are We from Generating Missing Modalities with Foundation Models?

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

A Survey on LLM-as-a-Judge

Efficient Reasoning with Hidden Thinking

A Survey of Scaling in Large Language Model Reasoning

Receipt and verification

First computed	2026-05-17T23:39:21.442498Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

78c5348662f187897f8f543611252f34475cba6704c6af5bff58952f261625f2

Aliases

arxiv: 2312.08935 · arxiv_version: 2312.08935v3 · doi: 10.48550/arxiv.2312.08935 · pith_short_12: PDCTJBTC6GDY · pith_short_16: PDCTJBTC6GDYS74P · pith_short_8: PDCTJBTC

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/PDCTJBTC6GDYS74PKQ3BCJJPGR \
  | 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: 78c5348662f187897f8f543611252f34475cba6704c6af5bff58952f261625f2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "91adbad2920422e205f37202aebe55cbf7b3d38603738d2a71ec7336af409f1b",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2023-12-14T13:41:54Z",
    "title_canon_sha256": "58c714679bd1e6ffd8b0af13ba869ae97a1daf04659e61eab2fc800ac1e80bd8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2312.08935",
    "kind": "arxiv",
    "version": 3
  }
}