Pith Number

pith:6J3KM6BT

pith:2026:6J3KM6BTRJNWMAZ2OILOY7ZZUF

not attested not anchored not stored refs resolved

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models

Hui Xue, Jialing Tao, Jiaqi Weng, Licheng Pan, Shuqiang Wang, Wei Cao, Zhixuan Chu

A hierarchical genetic algorithm can force large reasoning models to generate up to 26 times longer outputs by perturbing input logic.

arxiv:2605.13338 v2 · 2026-05-13 · cs.CR · 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{6J3KM6BTRJNWMAZ2OILOY7ZZUF}

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

Across four state-of-the-art reasoning models, the proposed method substantially amplifies output length, achieving up to a 26.1x increase on the MATH benchmark and consistently outperforming benign and manually crafted missing-premise baselines.

C2weakest assumption

That the composite fitness function reliably captures genuine overthinking rather than simply maximizing length through superficial perturbations, and that this behavior generalizes beyond the tested benchmarks and models.

C3one line summary

A hierarchical genetic algorithm induces overthinking in black-box large reasoning models by perturbing logical structure, achieving up to 26.1x longer outputs on the MATH benchmark.

References

37 extracted · 37 resolved · 7 Pith anchors

[1] 2021 IEEE Symposium on Security and Privacy (SP) , pages = 2021

[2] arXiv e-prints , year =

[3] Do NOT Think That Much for 2+ 3=? On the Overthinking of o1-Like LLMs , author=. CoRR , year=

[4] Missing premise exacerbates overthink- ing: Are reasoning models losing critical thinking skill? arXiv preprint arXiv:2504.06514

[5] The danger of overthinking: Examining the reasoning-action dilemma in agentic tasks 2025

Receipt and verification

First computed	2026-05-18T02:44:48.431739Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f276a678338a5b66033a7216ec7f39a16f48d314dc6498f972e05fe61c4d47fc

Aliases

arxiv: 2605.13338 · arxiv_version: 2605.13338v2 · doi: 10.48550/arxiv.2605.13338 · pith_short_12: 6J3KM6BTRJNW · pith_short_16: 6J3KM6BTRJNWMAZ2 · pith_short_8: 6J3KM6BT

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/6J3KM6BTRJNWMAZ2OILOY7ZZUF \
  | 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: f276a678338a5b66033a7216ec7f39a16f48d314dc6498f972e05fe61c4d47fc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "16da960ce40f9207b110b95258bdc1c8e59d5596940826c8f025fe43ab320c00",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-05-13T10:57:10Z",
    "title_canon_sha256": "fd67d03e17b1f101a529f09dba06fbc002802c7506bbc83c35e0f7af4acc5ec5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13338",
    "kind": "arxiv",
    "version": 2
  }
}