Pith Number

pith:4RWFQYLN

pith:2024:4RWFQYLNVGBMNJGMFUI43ZMISO

not attested not anchored not stored refs pending

Robust Preference Optimization through Reward Model Distillation

Adam Fisch, Ahmad Beirami, Alekh Agarwal, Chirag Nagpal, Jacob Eisenstein, Jonathan Berant, Pete Shaw, Vicky Zayats

arxiv:2405.19316 v2 · 2024-05-29 · cs.LG · 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{4RWFQYLNVGBMNJGMFUI43ZMISO}

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

Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution

Multiplayer Nash Preference Optimization

LLM Harms: A Taxonomy and Discussion

Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution

Generating Place-Based Compromises Between Two Points of View

Receipt and verification

First computed	2026-07-05T10:22:46.841026Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e46c58616da982c6a4cc2d11cde58893a1d3c5aed8be6449540fea4262d20460

Aliases

arxiv: 2405.19316 · arxiv_version: 2405.19316v2 · doi: 10.48550/arxiv.2405.19316 · pith_short_12: 4RWFQYLNVGBM · pith_short_16: 4RWFQYLNVGBMNJGM · pith_short_8: 4RWFQYLN

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/4RWFQYLNVGBMNJGMFUI43ZMISO \
  | 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: e46c58616da982c6a4cc2d11cde58893a1d3c5aed8be6449540fea4262d20460

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d518a85ee8c71d5e1bafaf81c45bde5b0667bf3908f88c547d45da2cdc4604a1",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-05-29T17:39:48Z",
    "title_canon_sha256": "3832215bb66ec71f6c9a21a91b62a85c944418c4410e1bd4ea63c7354f79e83c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2405.19316",
    "kind": "arxiv",
    "version": 2
  }
}