Pith Number

pith:NDFU7LT7

pith:2026:NDFU7LT7BTHDNNGYV54MVJJVSD

not attested not anchored not stored refs resolved

PreFIQs: Face Image Quality Is What Survives Pruning

Andrea Atzori, Fadi Boutros, Guray Ozgur, Jan Niklas Kolf, Naser Damer, Vitomir \v{S}truc, \v{Z}iga Babnik

Face image quality equals the embedding shift that occurs when a face recognition model is pruned.

arxiv:2605.13396 v1 · 2026-05-13 · 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{NDFU7LT7BTHDNNGYV54MVJJVSD}

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

PreFIQs quantifies image utility as the Euclidean distance between L2-normalized embeddings extracted from a pre-trained FR model and its pruned counterpart... achieves competitive or superior performance compared to state-of-the-art FIQA methods, including establishing new state-of-the-art results on several benchmarks, without any training or supervision.

C2weakest assumption

We hypothesize that low-utility face images rely disproportionately on fragile network parameters, resulting in larger geometric displacement of their embeddings under model sparsification.

C3one line summary

Face image quality is quantified as the Euclidean distance between embeddings from a pre-trained face recognition model and its pruned version, achieving competitive or superior results without training or supervision.

References

56 extracted · 56 resolved · 2 Pith anchors

[1] Deep network pruning: A comparative study on cnns in face recognition 2025

[2] Vit- fiqa: Assessing face image quality using vision trans- formers 2025

[3] Faceqan: Face image quality assessment through adversarial noise exploration 2022

[4] Diffiqa: Face image quality assessment using denoising dif- fusion probabilistic models 2023

[5] eDifFIQA: Towards Efficient Face Image Quality Assessment based on Denoising Diffusion Probabilistic Models 2024

Receipt and verification

First computed	2026-05-18T02:44:47.651886Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

68cb4fae7f0cce36b4d8af78caa53590e46729fd458e07a8b3a715fb575cd129

Aliases

arxiv: 2605.13396 · arxiv_version: 2605.13396v1 · doi: 10.48550/arxiv.2605.13396 · pith_short_12: NDFU7LT7BTHD · pith_short_16: NDFU7LT7BTHDNNGY · pith_short_8: NDFU7LT7

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/NDFU7LT7BTHDNNGYV54MVJJVSD \
  | 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: 68cb4fae7f0cce36b4d8af78caa53590e46729fd458e07a8b3a715fb575cd129

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9e4cdcaee995b076a8ff0dec95a8c56b9d0790d1ac75b6b49333f09945cb0f66",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T11:53:19Z",
    "title_canon_sha256": "f5d0e16b63a6af67a943f55eefeeb4a9ba81386f2424d207404c05bfb85ba27d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13396",
    "kind": "arxiv",
    "version": 1
  }
}