Pith Number

pith:KKSRF7L2

pith:2026:KKSRF7L2D2ZTTAZF5CCMZ5UBGE

not attested not anchored not stored refs resolved

Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

Gao Li, Wenhao Wang, Yang Yang, Yiheng Li, Zhen Lei, Zichang Tan

A GAN-based upsampling method plus Separate Expert Fusion reduces artifact bias and improves generalization in AI-generated image detection.

arxiv:2605.14486 v1 · 2026-05-14 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{KKSRF7L2D2ZTTAZF5CCMZ5UBGE}

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

Rather than merely benefiting GAN-generated image detection, this design introduces diverse and complementary artifact patterns that enable SEF to learn a more robust decision boundary and improve generalization across broader generative methods.

C2weakest assumption

That the proposed GAN-based upsampling produces artifact patterns that are both aligned (content/size/format) with reconstruction fakes and sufficiently distinct to provide complementary information without introducing new unmodeled biases.

C3one line summary

SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.

References

68 extracted · 68 resolved · 8 Pith anchors

[1] Synthbuster: Towards detection of diffusion model generated images.IEEE Open Journal of Signal Processing, 5:1–9, 2023 2023

[2] Large Scale GAN Training for High Fidelity Natural Image Synthesis 2018 · arXiv:1809.11096

[3] Zooming in on fakes: A novel dataset for localized ai-generated image detection with forgery amplification approach 2026

[4] Emerging properties in self-supervised vision transformers 2021

[5] Real-time deepfake detection in the real-world 2024

Receipt and verification

First computed	2026-05-17T23:39:06.491082Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

52a512fd7a1eb3398325e884ccf681310dd978b2bcc34f0b9b3d3cd60e4cfe7a

Aliases

arxiv: 2605.14486 · arxiv_version: 2605.14486v1 · doi: 10.48550/arxiv.2605.14486 · pith_short_12: KKSRF7L2D2ZT · pith_short_16: KKSRF7L2D2ZTTAZF · pith_short_8: KKSRF7L2

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/KKSRF7L2D2ZTTAZF5CCMZ5UBGE \
  | 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: 52a512fd7a1eb3398325e884ccf681310dd978b2bcc34f0b9b3d3cd60e4cfe7a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "af00a987f526544a55c242081c7793d22a1c6cd33e663967795a2bbf9c2e78c4",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T07:26:36Z",
    "title_canon_sha256": "a5721bcdbda68f2ae458540a32576325134eae2024e93b465728b57ac27f0a02"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14486",
    "kind": "arxiv",
    "version": 1
  }
}