Pith Number

pith:BHEEIWWA

pith:2023:BHEEIWWARMYM576EHCA63VHSK6

not attested not anchored not stored refs pending

Is RLHF More Difficult than Standard RL?

Chi Jin, Qinghua Liu, Yuanhao Wang

arxiv:2306.14111 v2 · 2023-06-25 · cs.LG · cs.AI · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BHEEIWWARMYM576EHCA63VHSK6}

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

Finding Stationary Points by Comparisons

Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification

Convex Optimization for Alignment and Preference Learning on a Single GPU

On the optimization dynamics of RLVR: Gradient gap and step size thresholds

OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration

Receipt and verification

First computed	2026-07-05T07:08:59.356127Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

09c8445ac08b30ceffc43881edd4f257b658acca5c3f45d2f9ae4004fb062ea5

Aliases

arxiv: 2306.14111 · arxiv_version: 2306.14111v2 · doi: 10.48550/arxiv.2306.14111 · pith_short_12: BHEEIWWARMYM · pith_short_16: BHEEIWWARMYM576E · pith_short_8: BHEEIWWA

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/BHEEIWWARMYM576EHCA63VHSK6 \
  | 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: 09c8445ac08b30ceffc43881edd4f257b658acca5c3f45d2f9ae4004fb062ea5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9f77f3bed07806e97f39a6837375d2af903d0c855ac6fc13d342179de84504b4",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2023-06-25T03:18:15Z",
    "title_canon_sha256": "28195d3291c25f21e48733d9edaf4a797d445b9fb05f979b59fe792a95fe8813"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2306.14111",
    "kind": "arxiv",
    "version": 2
  }
}