Pith Number

pith:DJRWIYNU

pith:2024:DJRWIYNUUJJ6H4DOUZMUHEBJWB

not attested not anchored not stored refs pending

Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms

Bradley Knox, Chelsea Finn, Harshit Sikchi, Joey Hejna, Rafael Rafailov, Ryan Park, Scott Niekum, Yaswanth Chittepu

arxiv:2406.02900 v2 · 2024-06-05 · 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{DJRWIYNUUJJ6H4DOUZMUHEBJWB}

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

9 papers in Pith

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search

The Differences Between Direct Alignment Algorithms are a Blur

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Likelihood scoring for continuations of mathematical text: a self-supervised benchmark with tests for shortcut vulnerabilities

Receipt and verification

First computed	2026-07-05T09:31:03.719850Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1a636461b4a253e3f06ea659439029b05f510d6d27c044a766345258c75a8644

Aliases

arxiv: 2406.02900 · arxiv_version: 2406.02900v2 · doi: 10.48550/arxiv.2406.02900 · pith_short_12: DJRWIYNUUJJ6 · pith_short_16: DJRWIYNUUJJ6H4DO · pith_short_8: DJRWIYNU

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/DJRWIYNUUJJ6H4DOUZMUHEBJWB \
  | 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: 1a636461b4a253e3f06ea659439029b05f510d6d27c044a766345258c75a8644

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fb051add89d3b124e94d0c64c25b9bfb4fdc1eeb222ffa2b685d5db35a82e67e",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-06-05T03:41:37Z",
    "title_canon_sha256": "e5d73989fe210f83270294d1a61ea10742618f1b9b9c8c08fdeea49a005f2b29"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2406.02900",
    "kind": "arxiv",
    "version": 2
  }
}