Pith Number

pith:IQUOJVRD

pith:2026:IQUOJVRDDXINXQVA35WDGTNAYW

not attested not anchored not stored refs resolved

Venus-DeFakerOne: Unified Fake Image Detection & Localization

GuangJian Team

DeFakerOne integrates InternVL2 and SAM2 into one model that detects and localizes image forgeries across many generation types at once.

arxiv:2605.14091 v1 · 2026-05-13 · 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{IQUOJVRDDXINXQVA35WDGTNAYW}

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

DeFakerOne achieves state-of-the-art performance, outperforming baselines on 39 forgery detection benchmarks and 9 localization benchmarks.

C2weakest assumption

That integrating InternVL2 and SAM2 with fine-grained supervision sufficiently captures cross-domain artifact transfer and interference without domain-specific adaptations.

C3one line summary

DeFakerOne integrates InternVL2 and SAM2 into a single model that achieves state-of-the-art results on 39 detection and 9 localization benchmarks for unified fake image detection and localization.

References

240 extracted · 240 resolved · 13 Pith anchors

[1] Findings of the Association for Computational Linguistics: EMNLP 2025 , pages= 2025

[2] Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection · arXiv:2506.00979

[3] Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detection , year=

[4] The Fourteenth International Conference on Learning Representations , year=

[5] Effort: Efficient Orthogonal Modeling for Generalizable AI-Generated Image Detection , author=. ICML , year=

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:12.210632Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4428e4d6231dd0dbc2a0df6c334da0c58c5ba6a9f05750658916873fb6ccb1ba

Aliases

arxiv: 2605.14091 · arxiv_version: 2605.14091v1 · doi: 10.48550/arxiv.2605.14091 · pith_short_12: IQUOJVRDDXIN · pith_short_16: IQUOJVRDDXINXQVA · pith_short_8: IQUOJVRD

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/IQUOJVRDDXINXQVA35WDGTNAYW \
  | 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: 4428e4d6231dd0dbc2a0df6c334da0c58c5ba6a9f05750658916873fb6ccb1ba

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1adb4fcd9e84da8667fe0d5f77a829cb4da772bd2be76eb965b901e490e441fb",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T20:20:33Z",
    "title_canon_sha256": "526ac25e496562b5d0b373f5d0d12e857027f8b2d4d4e1c2a0c895e9706f4d4d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14091",
    "kind": "arxiv",
    "version": 1
  }
}