Pith Number

pith:FWHU4GRS

pith:2023:FWHU4GRSIRWQEY3BRZFTGY4SDT

not attested not anchored not stored refs pending

Language Model Self-improvement by Reinforcement Learning Contemplation

Jiacheng Xu, Jing-cheng Pang, Kaiyuan Li, Pengyuan Wang, Xiong-Hui Chen, Yang Yu, Zongzhang Zhang

arxiv:2305.14483 v1 · 2023-05-23 · cs.CL · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{FWHU4GRSIRWQEY3BRZFTGY4SDT}

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

Trust Region On-Policy Distillation

Improving Collaborative Storytelling with a Multi-Agent Framework Based on Large Language Models

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation

Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning

ORPO: Monolithic Preference Optimization without Reference Model

Receipt and verification

First computed	2026-07-05T06:13:24.053657Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2d8f4e1a32446d0263618e4b3363921cfe9d09a154a1579c8b44752c1418205b

Aliases

arxiv: 2305.14483 · arxiv_version: 2305.14483v1 · doi: 10.48550/arxiv.2305.14483 · pith_short_12: FWHU4GRSIRWQ · pith_short_16: FWHU4GRSIRWQEY3B · pith_short_8: FWHU4GRS

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/FWHU4GRSIRWQEY3BRZFTGY4SDT \
  | 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: 2d8f4e1a32446d0263618e4b3363921cfe9d09a154a1579c8b44752c1418205b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bfabae8865a7b066c2eacfbec0fc4a4515a46e7370d81773f634804865b158f8",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-05-23T19:25:52Z",
    "title_canon_sha256": "2a1303631a00857a7874600015655f62142032dd4e71e65801a60ed4374c88a2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.14483",
    "kind": "arxiv",
    "version": 1
  }
}