Pith Number

pith:VS23ZKI7

pith:2026:VS23ZKI7I5LGNNYVPWWSYFHFC2

not attested not anchored not stored refs pending

The Last Human-Written Paper: Agent-Native Research Artifacts

Alex Pentland, Ang Chen, Ao Qu, Baoyu Zhou, Beidi Chen, Carl Chen, Chenglei Si, Chenyu You, Fan Lai, Haizhong Zheng, Haojie Ye, Jiachen Liu, Jiachen Sun, Jianqiao Zeng, Jiaxin Pei, Jintao Huang, John Dianzhuo Wang, Junyuan Hong, Lichang Chen, Maestro Harmon, Mingyuan Wu, Mosharaf Chowdhury, Ruihao Zhu, Runyu Lu, Shangquan Sun, Shijian Lu, Xiangru Tang, Xiaoyan Bai, Yao Li, Yiming Qiu, Yuan Yuan, Yujuan Fu, Zechen Zhang, Zexue He, Zhenyu Zhang, Zhiyang Chen, Zijian Jin

Machine-executable research packages replace narrative papers so AI agents can reproduce and extend work more reliably.

arxiv:2604.24658 v3 · 2026-04-27 · 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{VS23ZKI7I5LGNNYVPWWSYFHFC2}

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.

Claims

C1strongest claim

On PaperBench and RE-Bench, ARA raises question-answering accuracy from 72.4% to 93.7% and reproduction success from 57.4% to 64.4%. On RE-Bench's five open-ended extension tasks, preserved failure traces in ARA accelerate progress, but can also constrain a capable agent from stepping outside the prior-run box depending on the agent's capabilities.

C2weakest assumption

That the specific benchmarks (PaperBench and RE-Bench) and the way ARA was applied to them accurately reflect the general challenges AI agents face when trying to understand, reproduce, and extend real published research.

C3one line summary

The authors introduce Agent-Native Research Artifacts (ARA) as executable research packages with four layers to reduce information loss in papers for AI agents, showing benchmark gains in question-answering and reproduction.

Cited by

1 paper in Pith

Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI

Receipt and verification

First computed	2026-05-20T02:05:43.796735Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

acb5bca91f475666b7157dad2c14e516b3efeb7a63e87452f6a9b8f35f9ea221

Aliases

arxiv: 2604.24658 · arxiv_version: 2604.24658v3 · doi: 10.48550/arxiv.2604.24658 · pith_short_12: VS23ZKI7I5LG · pith_short_16: VS23ZKI7I5LGNNYV · pith_short_8: VS23ZKI7

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/VS23ZKI7I5LGNNYVPWWSYFHFC2 \
  | 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: acb5bca91f475666b7157dad2c14e516b3efeb7a63e87452f6a9b8f35f9ea221

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9e182a2d6995d7e1fbb821933ee888f6cfeb8ca1be3c25cb54fbcf6d549e0747",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/publicdomain/zero/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-27T16:23:09Z",
    "title_canon_sha256": "3e33912c22e8b3dbb00486be2278d65ead8393599fd3ecba3bd7df914af4a187"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.24658",
    "kind": "arxiv",
    "version": 3
  }
}