Pith Number

pith:KZWMQ6ZC

pith:2025:KZWMQ6ZCSHPAJFEZENQT3YJSDU

not attested not anchored not stored refs pending

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason

Ang Lv, Feng Wang, Haoyuan Hu, Jinpeng Li, Kaiyi Zhang, Rui Yan, Yongbo Wang

arxiv:2507.02841 v1 · 2025-07-03 · 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{KZWMQ6ZCSHPAJFEZENQT3YJSDU}

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

10 papers in Pith

The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance

Receipt and verification

First computed	2026-07-05T11:31:35.236895Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

566cc87b2291de04949923613de1321d349f1615077dad308bb42856cdc22a33

Aliases

arxiv: 2507.02841 · arxiv_version: 2507.02841v1 · doi: 10.48550/arxiv.2507.02841 · pith_short_12: KZWMQ6ZCSHPA · pith_short_16: KZWMQ6ZCSHPAJFEZ · pith_short_8: KZWMQ6ZC

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/KZWMQ6ZCSHPAJFEZENQT3YJSDU \
  | 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: 566cc87b2291de04949923613de1321d349f1615077dad308bb42856cdc22a33

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7071725cc6d821357e5e666e6d523658e9ff6ce3d2bd390cdb81fe11b6fed664",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-07-03T17:51:06Z",
    "title_canon_sha256": "b990ed007b06d871a93856b91699ac10e60786532f4781394de2130d67a631fe"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2507.02841",
    "kind": "arxiv",
    "version": 1
  }
}