Pith Number

pith:VC6X3BEX

pith:2025:VC6X3BEXBQLESEEOBZBKLAUL73

not attested not anchored not stored refs pending

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

Chao Xin, Guanlin Liu, Lin Yan, Qingping Yang, Ruofei Zhu, Wei Shen, Yu Yue, Zheng Wu

arxiv:2503.22230 v3 · 2025-03-28 · 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{VC6X3BEXBQLESEEOBZBKLAUL73}

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

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs

Seed1.5-VL Technical Report

Receipt and verification

First computed	2026-07-05T10:43:27.025786Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a8bd7d84970c1649108e0e42a5828bfeca83eab7d67d4ae82d1e7f5ca775347d

Aliases

arxiv: 2503.22230 · arxiv_version: 2503.22230v3 · doi: 10.48550/arxiv.2503.22230 · pith_short_12: VC6X3BEXBQLE · pith_short_16: VC6X3BEXBQLESEEO · pith_short_8: VC6X3BEX

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/VC6X3BEXBQLESEEOBZBKLAUL73 \
  | 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: a8bd7d84970c1649108e0e42a5828bfeca83eab7d67d4ae82d1e7f5ca775347d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "be2fae74c0e3d4c1f3cb68f816e4cd582a46eef307a6f2bf32564318a119fcfa",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-03-28T08:26:41Z",
    "title_canon_sha256": "9e57e31b4e817387e81a3855790a06a276dacc95bda4c9e0ee5f3c59775f0a50"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.22230",
    "kind": "arxiv",
    "version": 3
  }
}