Pith Number

pith:E4XUT7DC

pith:2026:E4XUT7DCORXNTYCWPBSMFOIO6R

not attested not anchored not stored refs pending

Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models

Bilal Faye, Djamel Bouchaffra, Hanane Azzag, Mustapha Lebbah, Nadjib Lazaar, Tom Devynck

Embedding a differentiable energy minimization layer inside convolutional networks lets them autonomously select sparse, coherent spatial features for improved robustness and interpretability.

arxiv:2604.06893 v3 · 2026-04-08 · cs.CV · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{E4XUT7DCORXNTYCWPBSMFOIO6R}

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

We validate ERSM on convolutional architectures and demonstrate that it produces emergent sparsity, improved robustness to structured occlusion, and highly interpretable spatial masks, while preserving classification accuracy. Furthermore, we show that the learned energy ranking significantly outperforms magnitude-based pruning in deletion-based robustness tests.

C2weakest assumption

That the proposed unary importance cost and pairwise spatial coherence penalty can be combined into a differentiable energy function whose minimization inside standard backbones yields stable training and semantically meaningful masks without additional supervision or post-hoc tuning.

C3one line summary

ERSM reformulates spatial feature selection in vision models as energy minimization with unary importance and pairwise coherence terms, producing emergent sparsity and better occlusion robustness.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-06-09T02:08:41.779309Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

272f49fc62746ed9e0567864c2b90ef47d3aa4298c4cd439809b1e85a3890bd3

Aliases

arxiv: 2604.06893 · arxiv_version: 2604.06893v3 · doi: 10.48550/arxiv.2604.06893 · pith_short_12: E4XUT7DCORXN · pith_short_16: E4XUT7DCORXNTYCW · pith_short_8: E4XUT7DC

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/E4XUT7DCORXNTYCWPBSMFOIO6R \
  | 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: 272f49fc62746ed9e0567864c2b90ef47d3aa4298c4cd439809b1e85a3890bd3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5586c1b3fa59b57633a4bdb5f4448cfa91bb0f12ba54c89eda943f7420264279",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-08T09:48:31Z",
    "title_canon_sha256": "07683473bfea90c02f26fa281ab5069e6c583591810975e203374feafd9e0a4f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.06893",
    "kind": "arxiv",
    "version": 3
  }
}