Pith Number

pith:XBQN44YY

pith:2023:XBQN44YYN5Q2QNGDXEKJGVAV6I

not attested not anchored not stored refs pending

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models

Chaowei Xiao, Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik

arxiv:2311.09641 v2 · 2023-11-16 · cs.AI · cs.CL · cs.CR · cs.HC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{XBQN44YYN5Q2QNGDXEKJGVAV6I}

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

2 papers in Pith

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders

Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback

Receipt and verification

First computed	2026-07-05T08:34:07.793572Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b860de73186f61a834c3b914935415f23dc629c5056ac502e0f48fdb9d43c702

Aliases

arxiv: 2311.09641 · arxiv_version: 2311.09641v2 · doi: 10.48550/arxiv.2311.09641 · pith_short_12: XBQN44YYN5Q2 · pith_short_16: XBQN44YYN5Q2QNGD · pith_short_8: XBQN44YY

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/XBQN44YYN5Q2QNGDXEKJGVAV6I \
  | 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: b860de73186f61a834c3b914935415f23dc629c5056ac502e0f48fdb9d43c702

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "14a70659a62525a38aaa044c68d8268614636705cb18f379765692eeb8ba8b91",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.CR",
      "cs.HC"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2023-11-16T07:48:45Z",
    "title_canon_sha256": "54a5c82f4c696f798fbcdb542e634df9ba4ca0165242f041adb7976fcaf18a33"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2311.09641",
    "kind": "arxiv",
    "version": 2
  }
}