Pith Number

pith:7FCGEHMV

pith:2026:7FCGEHMVFMDDBUE6UEJY4LR4XK

not attested not anchored not stored refs resolved

Architecture-Aware Explanation Auditing for Industrial Visual Inspection

Kunrong Li, Sibo Jia, Zihang Zhao

The faithfulness of heatmap explanations is bounded by structural distance to the model's native decision mechanism.

arxiv:2605.14255 v1 · 2026-05-14 · cs.LG · 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{7FCGEHMVFMDDBUE6UEJY4LR4XK}

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

the perturbation-based faithfulness of an explanation method is bounded by its structural distance from the model's native decision mechanism

C2weakest assumption

that the chosen perturbation protocols (zero-fill and blur-fill) provide an unbiased measure of faithfulness without introducing artifacts that favor certain readout structures over others

C3one line summary

Explanation faithfulness for deep classifiers on wafer maps is highest when the explainer matches the model's native readout structure, with ViT-Tiny plus Attention Rollout achieving lower Deletion AUC than mismatched methods despite lower accuracy.

References

23 extracted · 23 resolved · 6 Pith anchors

[1] He, K., Zhang, X., Ren, S., & Sun, J.Deep Residual Learning for Image Recognition. CVPR, 2016.https://www.cv-foundation.org/openaccess/content_cvpr_2016/pap ers/He_Deep_Residual_Learning_CVPR_2016_pap 2016

[2] CBAM: Convolutional Block Attention Module 2018 · arXiv:1807.06521

[3] Q.Densely Connected Convo- lutional Networks 2017

[4] et al.An Image Is Worth 16×16 Words: Transformers for Image Recogni- tion at Scale 2021

[5] Selvaraju, R. R. et al.Grad-CAM: Visual Explanations from Deep Networks via Gradient- Based Localization. ICCV, 2017.https://openaccess.thecvf.com/content_ICCV_201 7/papers/Selvaraju_Grad-CAM_Visual_E 2017

Receipt and verification

First computed	2026-05-17T23:39:10.533624Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f944621d952b0630d09ea1138e2e3cbaa83c20390634c07e695c30dac9a9ab48

Aliases

arxiv: 2605.14255 · arxiv_version: 2605.14255v1 · doi: 10.48550/arxiv.2605.14255 · pith_short_12: 7FCGEHMVFMDD · pith_short_16: 7FCGEHMVFMDDBUE6 · pith_short_8: 7FCGEHMV

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/7FCGEHMVFMDDBUE6UEJY4LR4XK \
  | 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: f944621d952b0630d09ea1138e2e3cbaa83c20390634c07e695c30dac9a9ab48

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bf584e94415a4a18dddeb0950e52b2e6bd6b570cd5f4dd42fc0e646e177d3fe3",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T01:48:00Z",
    "title_canon_sha256": "fb37a9d63783518cce028b3252d0f0e1113bf99f0fb9060c2fad4af617028ee8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14255",
    "kind": "arxiv",
    "version": 1
  }
}