Pith Number

pith:UD2KRHFF

pith:2025:UD2KRHFF5PZLSMPZ2QOKFUAJQD

not attested not anchored not stored refs pending

Post-Training Augmentation Invariance

Keenan Eikenberry, Lizuo Liu, Yoonsang Lee

Lightweight adapter networks trained with Wasserstein-based losses can add approximate invariance to augmentations in a frozen pretrained network while preserving its original behavior.

arxiv:2505.11702 v3 · 2025-05-16 · cs.LG · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UD2KRHFF5PZLSMPZ2QOKFUAJQD}

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

Both Markov-Wasserstein minimization and Wasserstein correlation maximization can be used to train lightweight one-hidden-layer MLP adapter networks E_theta that, when appended to the latent space of a pretrained network F, lead to approximate post-training augmentation invariance, as evidenced by achieving 94% classification accuracy on arbitrarily rotated STL10 images (vs 71% without adapter) and 86% on noisy images (vs 58%) with F frozen and little corruption to original features.

C2weakest assumption

That the proposed losses can enforce invariance on augmented inputs while keeping the adapter nearly isometric on the non-augmented latent distribution of F, which is presented as an empirical outcome but depends on the probabilistic definition of augmented encoders and the specific training procedure for E_theta.

C3one line summary

Develops post-training augmentation invariance via augmented encoders and two Wasserstein-based losses to train lightweight MLP adapters that boost robustness on DINOv2 features for STL10 without fine-tuning.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-06-10T01:08:27.806891Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a0f4a89ca5ebf2b931f9d41ca2d00980f30c45f62127eaa27745e2ac0c6c9b15

Aliases

arxiv: 2505.11702 · arxiv_version: 2505.11702v3 · doi: 10.48550/arxiv.2505.11702 · pith_short_12: UD2KRHFF5PZL · pith_short_16: UD2KRHFF5PZLSMPZ · pith_short_8: UD2KRHFF

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/UD2KRHFF5PZLSMPZ2QOKFUAJQD \
  | 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: a0f4a89ca5ebf2b931f9d41ca2d00980f30c45f62127eaa27745e2ac0c6c9b15

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5c7e3eda383fab1c9747577a4579bd106745419c7f73787b03f7600e080f4a46",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-05-16T21:11:51Z",
    "title_canon_sha256": "95605576500ade19f4f7fcf2608591878a8478c711575f43e210b420f71c33c1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.11702",
    "kind": "arxiv",
    "version": 3
  }
}