Pith Number

pith:NQZJRTWS

pith:2026:NQZJRTWSZ2VM4SY6TMLB63JZHB

not attested not anchored not stored refs resolved

AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps

Chia-Ying Hsieh, Chun-Shu Wei, Hsin-Yuan Fang

AIM uses adversarial feature replacement to evaluate saliency map faithfulness with less masking bias.

arxiv:2605.16905 v1 · 2026-05-16 · 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{NQZJRTWSZ2VM4SY6TMLB63JZHB}

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

Experiments on image, audio, and EEG tasks suggest that AIM reduces masking-induced bias compared with zero and interpolation-based masking, while revealing modality-dependent differences between signed and unsigned attributions.

C2weakest assumption

The adversarial counterpart of the input can be generated such that feature replacement removes predictive information without introducing new confounding artifacts or residual signals that affect the faithfulness measurement.

C3one line summary

AIM is a new saliency-guided adversarial feature replacement method to evaluate faithfulness of saliency maps and reliability of masking operators on image, audio, and EEG tasks.

References

76 extracted · 76 resolved · 5 Pith anchors

[1] Visualizing and understanding convolutional networks 2014

[2] Evaluating the visualization of what a deep neural network has learned.IEEE Transactions on Neural Networks and Learning Systems, 28(11):2660–2673, 2016 2016

[3] A unified approach to interpreting model predictions 2017

[4] Towards better understanding of gradient-based attribution methods for deep neural networks.arXiv preprint arXiv:1711.06104 2017 · arXiv:1711.06104

[5] right to explanation 2017

Receipt and verification

First computed	2026-05-20T00:03:29.423937Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6c3298ced2ceaace4b1e9b161f6d3938572d3b8f8867fc08f4cde8aa2aa6e1cb

Aliases

arxiv: 2605.16905 · arxiv_version: 2605.16905v1 · doi: 10.48550/arxiv.2605.16905 · pith_short_12: NQZJRTWSZ2VM · pith_short_16: NQZJRTWSZ2VM4SY6 · pith_short_8: NQZJRTWS

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/NQZJRTWSZ2VM4SY6TMLB63JZHB \
  | 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: 6c3298ced2ceaace4b1e9b161f6d3938572d3b8f8867fc08f4cde8aa2aa6e1cb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ffd5883723a437c8abd061a48a0b81d191c37533a5a979ccf60315c28a06ae4f",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-16T09:36:58Z",
    "title_canon_sha256": "90f7693c2b15925555eff1cde3d9680db6f0c9bc1f0bb9169094e4a9f28777f3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16905",
    "kind": "arxiv",
    "version": 1
  }
}