Pith Number

pith:6HZPQNGD

pith:2026:6HZPQNGDOJTIEJ5M5OEIWSOZ7R

not attested not anchored not stored refs resolved

How to Evaluate and Refine your CAM

Alessandra Stramiglio, Luca Domeniconi, Michele Lombardi, Samuele Salti

RefineCAM produces higher-resolution attribution maps for CNN decisions by aggregating multiple layers.

arxiv:2605.14641 v1 · 2026-05-14 · cs.CV · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6HZPQNGDOJTIEJ5M5OEIWSOZ7R}

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

RefineCAM consistently outperforms existing methods according to the proposed evaluation.

C2weakest assumption

The synthetic dataset's ground-truth attributions accurately capture what constitutes faithful explanations in real-world image classification scenarios.

C3one line summary

Introduces synthetic ground-truth dataset for CAM evaluation, proposes ARCC composite metric, and RefineCAM method that aggregates layers for higher-resolution maps outperforming baselines.

References

32 extracted · 32 resolved · 3 Pith anchors

[1] Nature Machine Intelligence5(9), 1006– 1019 (2023) 2023

[2] Bohle, M., Fritz, M., Schiele, B.: Convolutional dynamic alignment networks for interpretableclassifications.In:ProceedingsoftheIEEE/CVFConferenceonCom- puter Vision and Pattern Recognition. pp. 10029 2021

[3] The Visual Computer 41(10), 7249–7267 (Jan 2025) 2025 · doi:10.1007/s00371-025-03803-1

[4] https://universe.roboflow.com/carddataset/ whereswaldy (2023) 2023

[5] In: 2018 IEEE winter conference on applications of computer vision (WACV) 2018

Receipt and verification

First computed	2026-05-17T23:39:03.885487Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f1f2f834c372668227aceb888b49d9fc6629c0b4701c77474f79655e86f449fd

Aliases

arxiv: 2605.14641 · arxiv_version: 2605.14641v1 · doi: 10.48550/arxiv.2605.14641 · pith_short_12: 6HZPQNGDOJTI · pith_short_16: 6HZPQNGDOJTIEJ5M · pith_short_8: 6HZPQNGD

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/6HZPQNGDOJTIEJ5M5OEIWSOZ7R \
  | 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: f1f2f834c372668227aceb888b49d9fc6629c0b4701c77474f79655e86f449fd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fa4fe9d92c10cc2ee5c34b63bf138133d5268575f98f24d1709155486f664264",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T09:57:21Z",
    "title_canon_sha256": "6ff34a2526a747f9d1ade6be5c818ed2eb4f7cbc4f33e21b9b27d186ac15a3fe"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14641",
    "kind": "arxiv",
    "version": 1
  }
}