Pith Number

pith:JPSMKDCK

pith:2025:JPSMKDCKL4R2ODSQMYZPR2DOLQ

not attested not anchored not stored refs pending

DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection

Boyu Wang, Fan Wang, Jiazhen Yan, Zhangjie Fu, Ziqiang Li, Ziwen He

By projecting task gradients onto the orthogonal complement of harmful directions and aligning with beneficial ones distilled from a frozen CLIP encoder, DGS-Net fine-tunes for AI-generated image detection without catastrophic forgetting.

arxiv:2511.13108 v4 · 2025-11-17 · 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{JPSMKDCKL4R2ODSQMYZPR2DOLQ}

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

By projecting task gradients onto the orthogonal complement of harmful directions and aligning with beneficial ones distilled from a frozen CLIP encoder, DGS-Net achieves unified optimization of prior preservation and irrelevant suppression, outperforming state-of-the-art approaches by an average margin of 6.6% across 50 generative models.

C2weakest assumption

That the proposed gradient-space decomposition can reliably and consistently separate harmful from beneficial descent directions without introducing instability or requiring extensive hyperparameter tuning specific to each dataset.

C3one line summary

DGS-Net applies distillation-guided gradient surgery during CLIP fine-tuning to preserve pre-trained knowledge and suppress irrelevant features, reporting 6.6% average gains over prior methods on 50 generative models.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:37.038776Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4be4c50c4a5f23a70e506632f8e86e5c37e99067b3615799171250c76b69623a

Aliases

arxiv: 2511.13108 · arxiv_version: 2511.13108v4 · doi: 10.48550/arxiv.2511.13108 · pith_short_12: JPSMKDCKL4R2 · pith_short_16: JPSMKDCKL4R2ODSQ · pith_short_8: JPSMKDCK

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/JPSMKDCKL4R2ODSQMYZPR2DOLQ \
  | 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: 4be4c50c4a5f23a70e506632f8e86e5c37e99067b3615799171250c76b69623a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "806867118c0399c7bb6e2c7cce660173b78777d4da839bd3617d37e03fa008b9",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-11-17T08:05:31Z",
    "title_canon_sha256": "2d78b257e76acbfa33b1786eed5643fdad5f34dd38b4ae3aa304544e03a5c6c8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.13108",
    "kind": "arxiv",
    "version": 4
  }
}