Pith Number

pith:WIIXMMCX

pith:2026:WIIXMMCXMQQBDRSVPYTTQANW7H

not attested not anchored not stored refs pending

Degradation-Consistent Paired Training for Robust AI-Generated Image Detection

Xiaokun Yang, Yinghan Hou, Zongyou Yang

Degradation-Consistent Paired Training raises AI-generated image detector accuracy on corrupted inputs by 9.1 percentage points with only a 0.9 percent drop on clean images.

arxiv:2604.10102 v2 · 2026-04-11 · cs.CV · 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{WIIXMMCXMQQBDRSVPYTTQANW7H}

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

Experiments on the Synthbuster benchmark (9 generators, 8 degradation conditions) demonstrate that DCPT improves the degraded-condition average accuracy by 9.1 percentage points compared to an identical baseline without paired training, while sacrificing only 0.9% clean accuracy. The improvement is most pronounced under JPEG compression (+15.7% to +17.9%).

C2weakest assumption

That the specific degradations (JPEG compression, Gaussian blur, resolution downsampling) and consistency losses used during training will generalize to unseen real-world corruptions and that the Synthbuster benchmark sufficiently represents practical deployment conditions.

C3one line summary

DCPT raises average accuracy of AI image detectors under real-world degradations by 9.1 points on the Synthbuster benchmark using paired consistency losses, with only 0.9% drop on clean images and no added parameters or inference cost.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-27T02:05:19.524692Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b211763057642011c6557e273801b6f9ebfe7c12bb673b2c5296a6c87919ff0c

Aliases

arxiv: 2604.10102 · arxiv_version: 2604.10102v2 · doi: 10.48550/arxiv.2604.10102 · pith_short_12: WIIXMMCXMQQB · pith_short_16: WIIXMMCXMQQBDRSV · pith_short_8: WIIXMMCX

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/WIIXMMCXMQQBDRSVPYTTQANW7H \
  | 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: b211763057642011c6557e273801b6f9ebfe7c12bb673b2c5296a6c87919ff0c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "679e6cd445b015a9ac5c897bb4b994e58234da5750bf11aa204c6a06dc273c5c",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-11T08:52:28Z",
    "title_canon_sha256": "4d78d4b4871463890cd4d10ee679dfeadea6c6d68d8914d8d8fe94582af00ee9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.10102",
    "kind": "arxiv",
    "version": 2
  }
}