Pith Number

pith:6GXPO7TY

pith:2026:6GXPO7TYHXCQJ3FYDSZC2RYRE5

not attested not anchored not stored refs resolved

From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks

Denia Kanellopoulou, Thodoris Lymperopoulos

Perturbing weights attached to input features produces reliable attributions that avoid bias and out-of-distribution problems in occlusion methods for fully connected neural networks.

arxiv:2605.15328 v1 · 2026-05-14 · 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{6GXPO7TYHXCQJ3FYDSZC2RYRE5}

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

Applying perturbation to the features' attached weights instead of their values leads to novel attribution methods XWP and XWP_c that mitigate common limitations in Occlusion techniques such as Added Bias and Out-of-Distribution data and achieve competitive performance in identifying image signals for simple DNNs on standard baseline metrics.

C2weakest assumption

That perturbing weights attached to features produces a valid and unbiased measure of feature importance that directly addresses the added bias and out-of-distribution problems of value perturbation without introducing new artifacts or requiring additional validation on the specific network architecture.

C3one line summary

XWP and XWP_c are novel attribution methods for FCNNs that estimate feature importance by perturbing attached weights to avoid added bias and out-of-distribution issues in occlusion approaches.

References

31 extracted · 31 resolved · 4 Pith anchors

[1] Shreyash Arya, Sukrut Rao, Moritz Böhle, and Bernt Schiele. 2024. B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable. InAdvances in Neural Information Processing Systems, 2024 · doi:10.52202/079017-2007

[2] Beyza Nur Aydoğan and Tevfik Aytekin. 2025. An in-depth analysis of KernelSHAP and SamplingSHAP: assessing robustness, error, and efficiency. Knowledge and Information Systems67 (2025), 10545 – 10579. 2025

[3] (2020).Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI 2020 · doi:10.1016/j.inffus.2019.12.012

[4] 2024 , month = aug, number = 2024

[5] Alexander Binder, Sebastian Bach, Gregoire Montavon, Klaus-Robert Muller, and Wojciech Samek. 2016. Layer-Wise Relevance Propagation for Deep Neural Network Architectures. InInformation Science and Ap 2016

Receipt and verification

First computed	2026-05-20T00:00:52.863358Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f1aef77e783dc504ecb81cb22d471127656d161b32e8c45d1571795dc54fe012

Aliases

arxiv: 2605.15328 · arxiv_version: 2605.15328v1 · doi: 10.48550/arxiv.2605.15328 · pith_short_12: 6GXPO7TYHXCQ · pith_short_16: 6GXPO7TYHXCQJ3FY · pith_short_8: 6GXPO7TY

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/6GXPO7TYHXCQJ3FYDSZC2RYRE5 \
  | 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: f1aef77e783dc504ecb81cb22d471127656d161b32e8c45d1571795dc54fe012

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8affd006240198081e9e1e873defc1f774e44d8aa21a11cc40a8d8c39394603b",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T18:41:20Z",
    "title_canon_sha256": "f65c768779d6cb738d715e32f5197ef56db657971b418f670f3d5743873ce9ed"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15328",
    "kind": "arxiv",
    "version": 1
  }
}