Pith Number

pith:VY6CAMKN

pith:2025:VY6CAMKNMILHNX3BKXVVUBGXTV

not attested not anchored not stored refs pending

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

Dongyun Xue, Houqiang Li, Jianfeng Cai, Jinhua Zhu, Kangwen Zhao, Li Li, Ruopei Sun, Wengang Zhou

arxiv:2505.12843 v2 · 2025-05-19 · cs.LG · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VY6CAMKNMILHNX3BKXVVUBGXTV}

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

3 papers in Pith

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction

Receipt and verification

First computed	2026-06-25T01:17:44.540713Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ae3c20314d621676df6155eb5a04d79d48467c83cdec1e008d2f5cdf8baa5c8e

Aliases

arxiv: 2505.12843 · arxiv_version: 2505.12843v2 · doi: 10.48550/arxiv.2505.12843 · pith_short_12: VY6CAMKNMILH · pith_short_16: VY6CAMKNMILHNX3B · pith_short_8: VY6CAMKN

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/VY6CAMKNMILHNX3BKXVVUBGXTV \
  | 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: ae3c20314d621676df6155eb5a04d79d48467c83cdec1e008d2f5cdf8baa5c8e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ed09b76b56fc3504728515dea65f4cf3a1ef9c0bf901936362d2745e5dd6fe55",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-05-19T08:29:28Z",
    "title_canon_sha256": "f78ce95c7711845b3b0eb572e5e3ea1cfe6918640f1089524a73f54ed8266d27"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.12843",
    "kind": "arxiv",
    "version": 2
  }
}