Pith Number

pith:MDYTKY3S

pith:2026:MDYTKY3SIV22NHKIUJSOQ7LWJO

not attested not anchored not stored refs pending

P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist

Dongha Lee, Kwangwook Seo

P-Check trains a checklist generator to produce dynamic criteria that align reward models more closely with individual preferences.

arxiv:2601.02986 v3 · 2026-01-06 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{MDYTKY3SIV22NHKIUJSOQ7LWJO}

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

P-Check not only improves reward accuracy but also enhances downstream personalized generation, and remains robust in OOD scenarios.

C2weakest assumption

That a learned checklist generator can reliably synthesize dynamic, multi-faceted criteria that capture nuanced personal judgment without introducing artifacts or requiring user-specific data beyond what static baselines already use.

C3one line summary

P-Check advances personalized reward modeling by training a dynamic checklist generator and preference-contrastive weighting to improve reward accuracy, downstream generation, and OOD robustness.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

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

Receipt and verification

First computed	2026-06-23T03:13:53.111918Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

60f13563724575a69d48a264e87d764b9af931c7642c290d48a671d43568b4a4

Aliases

arxiv: 2601.02986 · arxiv_version: 2601.02986v3 · doi: 10.48550/arxiv.2601.02986 · pith_short_12: MDYTKY3SIV22 · pith_short_16: MDYTKY3SIV22NHKI · pith_short_8: MDYTKY3S

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/MDYTKY3SIV22NHKIUJSOQ7LWJO \
  | 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: 60f13563724575a69d48a264e87d764b9af931c7642c290d48a671d43568b4a4

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9f59bc62fb7dbd6ac008a8e66d5745247b45e948d929d06fd0e052ad5077dc96",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-01-06T12:53:53Z",
    "title_canon_sha256": "bd0023e53efd2552cf40e487c74e538b2722c03b24b3f89cf1951773a470f51d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.02986",
    "kind": "arxiv",
    "version": 3
  }
}