Pith Number

pith:T3GPDLNF

pith:2024:T3GPDLNFD5EDOX5BWKP72QIONE

not attested not anchored not stored refs pending

Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation

Lei Meng, Lei Shu, Lei Yu, Meng Cao, Nevan Wichers, Yinxiao Liu, Yun Zhu

arxiv:2401.07382 v2 · 2024-01-14 · cs.CL · 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{T3GPDLNFD5EDOX5BWKP72QIONE}

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

3 papers in Pith

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

CATPO: Critique-Augmented Tree Policy Optimization

PriorZero: Bridging Language Priors and World Models for Decision Making

Receipt and verification

First computed	2026-07-05T07:46:29.591155Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9eccf1ada51f48375fa1b29ffd410e69252ea769642c1a3b605914cff39b8eaf

Aliases

arxiv: 2401.07382 · arxiv_version: 2401.07382v2 · doi: 10.48550/arxiv.2401.07382 · pith_short_12: T3GPDLNFD5ED · pith_short_16: T3GPDLNFD5EDOX5B · pith_short_8: T3GPDLNF

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/T3GPDLNFD5EDOX5BWKP72QIONE \
  | 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: 9eccf1ada51f48375fa1b29ffd410e69252ea769642c1a3b605914cff39b8eaf

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a402d663d78ae53eb762403d3ca82532548f1cb3fa730534eb329b4bdc8d7b46",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-01-14T22:05:11Z",
    "title_canon_sha256": "17420fea09325296a55a18ec04e8618f9ccf6e83890920e904bcc50d7ca6d199"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2401.07382",
    "kind": "arxiv",
    "version": 2
  }
}