pith. sign in
Pith Number

pith:VW7GUEVK

pith:2026:VW7GUEVKB2B5FHYM3W53XFX7XG
not attested not anchored not stored refs resolved

Paraphrasing Attack Resilience of Various AI-Generated Text Detection Methods

Andrii Shportko, Inessa Verbitsky

Binoculars-inclusive ensembles detect AI text most accurately but lose the largest share of that accuracy when text is paraphrased.

arxiv:2605.14240 v1 · 2026-05-14 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{VW7GUEVKB2B5FHYM3W53XFX7XG}

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

We discovered that Binoculars-inclusive ensembles yield the strongest results, but they also suffer the most significant losses during attacks.

C2weakest assumption

That the paraphrasing attacks and evaluation datasets used are representative of real-world evasion attempts and that the reported performance differences generalize beyond the specific test conditions.

C3one line summary

Binoculars-inclusive ensembles detect AI text best overall but suffer the largest performance drops under paraphrasing attacks.

References

14 extracted · 14 resolved · 1 Pith anchors

[1] https:// www.gptinf.com/ 2025
[2] arXiv preprint arXiv:2309.07755 (2023)
[3] On the possibilities of ai-generated text detection
[4] Epub 2023 Jun 2023
[5] Xiaomeng Hu, Pin-Yu Chen, and Tsung-Yi Ho
Receipt and verification
First computed 2026-05-17T23:39:10.659749Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

adbe6a12aa0e83d29f0cddbbbb96ffb990d7c7bd2d6d5c49b9745477283e772e

Aliases

arxiv: 2605.14240 · arxiv_version: 2605.14240v1 · doi: 10.48550/arxiv.2605.14240 · pith_short_12: VW7GUEVKB2B5 · pith_short_16: VW7GUEVKB2B5FHYM · pith_short_8: VW7GUEVK
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/VW7GUEVKB2B5FHYM3W53XFX7XG \
  | 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: adbe6a12aa0e83d29f0cddbbbb96ffb990d7c7bd2d6d5c49b9745477283e772e
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "7db814a6ef223f5f9f1aca2780bb091586e7f526b363973b21691e363e2f8253",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T01:12:34Z",
    "title_canon_sha256": "b821678c4f2c03efd2dc8f0b723d3c97c9afd611b1132d621868118df7a207cc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14240",
    "kind": "arxiv",
    "version": 1
  }
}