Pith Number

pith:K2JESIJM

pith:2026:K2JESIJMMCAWY6SGEYDUMKLIEW

not attested not anchored not stored refs resolved

Can LLM Agents Simulate Dynamic Networks? A Case Study on Email Networks with Phishing Synthesis

Hans Hao-Hsun Hsu, Kaiqing Zhang, Mufei Li, Pan Li, Siqi Miao, Yuhong Luo, Ziyang Chen

LLM multi-agent systems simulate realistic email network dynamics when extended with event triggers and Hawkes processes.

arxiv:2605.12507 v1 · 2026-03-20 · cs.SI · cs.AI · cs.MA

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{K2JESIJMMCAWY6SGEYDUMKLIEW}

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

Our approach allows LLM MAS to capture both plausible micro-level patterns and macroscopic topologies.

C2weakest assumption

That the two proposed extensions (data-driven event triggers and Hawkes processes) can be added to existing LLM MAS frameworks without breaking the agents' ability to produce plausible micro-level interactions while also producing macroscopic topologies that match real email network data.

C3one line summary

LLM multi-agent systems augmented with data-driven event triggers and Hawkes processes simulate both micro-level interactions and macroscopic topologies in dynamic email networks for realistic phishing synthesis.

References

24 extracted · 24 resolved · 3 Pith anchors

[1] Eric Bonabeau 2002

[2] InEuropean conference on information retrieval, pages 684–691

[3] Differentiable agent-based epidemiology 2024

[4] Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security 2023 · arXiv:2401.05459

[5] InProceedings of the tenth ACM international conference on web search and data mining, pages 601–610 2020

Receipt and verification

First computed	2026-05-18T03:10:03.106197Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

569249212c60816c7a46260746296825a3598a13bc3bc833537a8c590b79aacf

Aliases

arxiv: 2605.12507 · arxiv_version: 2605.12507v1 · doi: 10.48550/arxiv.2605.12507 · pith_short_12: K2JESIJMMCAW · pith_short_16: K2JESIJMMCAWY6SG · pith_short_8: K2JESIJM

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/K2JESIJMMCAWY6SGEYDUMKLIEW \
  | 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: 569249212c60816c7a46260746296825a3598a13bc3bc833537a8c590b79aacf

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "58b9c06f9d5483722dd6b70b96d9ca7a61a5f2f552bda82e841442b15de61c9c",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.MA"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SI",
    "submitted_at": "2026-03-20T15:23:43Z",
    "title_canon_sha256": "c20672106063f2d576681525963bb662559f628af79dcaef5726a452786e7ee2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12507",
    "kind": "arxiv",
    "version": 1
  }
}