Pith Number

pith:H6X43XHD

pith:2023:H6X43XHDWAIJSECPR5PJ4LJMFJ

not attested not anchored not stored refs pending

Confronting Reward Model Overoptimization with Constrained RLHF

Aaditya K. Singh, Anca D. Dragan, DJ Strouse, Ruslan Salakhutdinov, Stephen McAleer, Ted Moskovitz, Tuomas Sandholm

arxiv:2310.04373 v2 · 2023-10-06 · 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{H6X43XHDWAIJSECPR5PJ4LJMFJ}

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

6 papers in Pith

Against Proxy Optimization

Towards Context-Invariant Safety Alignment for Large Language Models

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion

Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion

Receipt and verification

First computed	2026-07-05T06:59:00.578183Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3fafcddce3b01099104f8f5e9e2d2c2a5c6bd7fdd6202b3fda5e2990f4642373

Aliases

arxiv: 2310.04373 · arxiv_version: 2310.04373v2 · doi: 10.48550/arxiv.2310.04373 · pith_short_12: H6X43XHDWAIJ · pith_short_16: H6X43XHDWAIJSECP · pith_short_8: H6X43XHD

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/H6X43XHDWAIJSECPR5PJ4LJMFJ \
  | 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: 3fafcddce3b01099104f8f5e9e2d2c2a5c6bd7fdd6202b3fda5e2990f4642373

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "46631051abb021ca270527031b82525a0b959a9550ed0472937f866b725e7fc7",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2023-10-06T16:59:17Z",
    "title_canon_sha256": "a2efabab29e20192724b2d3668dab8b7c859d1be77b79f786bef31770ef250fe"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2310.04373",
    "kind": "arxiv",
    "version": 2
  }
}