Pith Number

pith:JECZIIMD

pith:2025:JECZIIMDDOJYK437VGPVEBNJOL

not attested not anchored not stored refs pending

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent

Dian Yu, Dong Yu, Haitao Mi, Linfeng Song, Nan Jiang, Tao Ge, Yuheng Zhang, Zhichen Zeng

arxiv:2502.16852 v1 · 2025-02-24 · cs.LG · cs.AI · 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{JECZIIMDDOJYK437VGPVEBNJOL}

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

5 papers in Pith

Reinforcement Learning from Human Feedback

Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment

Multiplayer Nash Preference Optimization

Towards General Preference Alignment: Diffusion Models at Nash Equilibrium

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective

Receipt and verification

First computed	2026-07-05T10:19:00.886825Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

49059421831b9385737fa99f5205a972fefc95e9f9afe4f324f55df33ddaac18

Aliases

arxiv: 2502.16852 · arxiv_version: 2502.16852v1 · doi: 10.48550/arxiv.2502.16852 · pith_short_12: JECZIIMDDOJY · pith_short_16: JECZIIMDDOJYK437 · pith_short_8: JECZIIMD

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/JECZIIMDDOJYK437VGPVEBNJOL \
  | 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: 49059421831b9385737fa99f5205a972fefc95e9f9afe4f324f55df33ddaac18

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "469d80476c992b3a30b6e32a23b7cbb5886278d00db28bc31f00201debe01e52",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-02-24T05:24:52Z",
    "title_canon_sha256": "f3e112b569265803411ada93a1b8b2c8c7d8e7a39336ffd2b7689cc5887fe7c0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.16852",
    "kind": "arxiv",
    "version": 1
  }
}