Pith Number

pith:3OADC3LL

pith:2023:3OADC3LLRV5IVHQHZYVUDOFCNN

not attested not anchored not stored refs pending

Reward Design with Language Models

Dorsa Sadigh, Kalesha Bullard, Minae Kwon, Sang Michael Xie

arxiv:2303.00001 v1 · 2023-02-27 · 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{3OADC3LLRV5IVHQHZYVUDOFCNN}

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

13 papers in Pith

Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output

Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning

ARKD: Adaptive Reinforcement Learning-Guided Bidirectional KL Divergence Distillation for Text Generation

What Is Preference Optimization Doing, and Why?

DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition

Receipt and verification

First computed	2026-07-05T05:46:53.538431Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

db80316d6b8d7a8a9e07ce2b41b8a26b50f70cb98981427634a9823bff668e8e

Aliases

arxiv: 2303.00001 · arxiv_version: 2303.00001v1 · doi: 10.48550/arxiv.2303.00001 · pith_short_12: 3OADC3LLRV5I · pith_short_16: 3OADC3LLRV5IVHQH · pith_short_8: 3OADC3LL

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/3OADC3LLRV5IVHQHZYVUDOFCNN \
  | 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: db80316d6b8d7a8a9e07ce2b41b8a26b50f70cb98981427634a9823bff668e8e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1c3bbe2f7549b011bc3d641d32ad5eaa7169a8cbb0ea4f5f2ef568c695489427",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2023-02-27T22:09:35Z",
    "title_canon_sha256": "874d4a3eccabe2573d69ea329ca57b4c2bf816cc519545d72109a07cec4fe318"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2303.00001",
    "kind": "arxiv",
    "version": 1
  }
}