Pith Number

pith:XV3VQ25Z

pith:2026:XV3VQ25Z23HOTCMX237T37UAXH

not attested not anchored not stored refs resolved

Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents

Chuxuan Zhang, Haoran Bu, Hui Pang, Litian Zhang, Xi Zhang, Zhanyuan Liu

GraphMind augments LLMs with graph learning so social bots can build human-like global network structures and evade detection.

arxiv:2605.12512 v1 · 2026-03-31 · cs.SI · 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{XV3VQ25Z23HOTCMX237T37UAXH}

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

Experiments on datasets derived from GraphMind-Botnet show that both text-based and graph-based detection models show substantially degraded performance in distinguishing.

C2weakest assumption

That graph augmentation of LLMs can reliably produce social networks statistically indistinguishable from real human ones at global scale, with no details on fitting metrics, validation datasets, or controls for overfitting to specific network properties.

C3one line summary

GraphMind equips LLM agents with graph awareness to construct human-like social networks, producing botnets that substantially degrade performance of both text-based and graph-based detectors.

References

86 extracted · 86 resolved · 8 Pith anchors

[1] Mgtab: A multi-relational graph-based twitter account detection benchmark , author=. Neurocomputing , pages=. 2025 , publisher= 2025

[2] Kronecker graphs: an approach to modeling networks. , author=. Journal of Machine Learning Research , volume=

[3] Generating large scale-free networks with the Chung--Lu random graph model , author=. Networks , volume=. 2021 , publisher= 2021

[4] Lora: Low-rank adaptation of large language models. , author=

[5] OpenAI blog , volume=

Receipt and verification

First computed	2026-05-18T03:10:02.978826Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bd77586bb9d6cee98997d6ff3dfe80b9d930fef040bcda3f98683e186e11e836

Aliases

arxiv: 2605.12512 · arxiv_version: 2605.12512v1 · doi: 10.48550/arxiv.2605.12512 · pith_short_12: XV3VQ25Z23HO · pith_short_16: XV3VQ25Z23HOTCMX · pith_short_8: XV3VQ25Z

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/XV3VQ25Z23HOTCMX237T37UAXH \
  | 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: bd77586bb9d6cee98997d6ff3dfe80b9d930fef040bcda3f98683e186e11e836

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "27676b6af08c35977d6e3cf8a7490bfcbc0194a5ac87783ee21bc182654db2a6",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SI",
    "submitted_at": "2026-03-31T09:10:55Z",
    "title_canon_sha256": "bb89c30c937b89ca30a488d76e5dc2bad5213f12fa3d26623578612814c5b1ff"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12512",
    "kind": "arxiv",
    "version": 1
  }
}