pith. sign in
Pith Number

pith:I2BCLRTF

pith:2019:I2BCLRTFYZ6HSTZK7QE5CV3YTO
not attested not anchored not stored refs resolved

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

Dan Hendrycks, Thomas Dietterich

Benchmarks for common corruptions show negligible relative robustness gains from AlexNet to ResNet.

arxiv:1903.12261 v1 · 2019-03-28 · cs.LG · cs.CV · stat.ML

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{I2BCLRTFYZ6HSTZK7QE5CV3YTO}

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

We find that there are negligible changes in relative corruption robustness from AlexNet classifiers to ResNet classifiers.

C2weakest assumption

That the 15 chosen corruptions and the perturbations in ImageNet-P sufficiently represent the common real-world image degradations classifiers will encounter in deployment.

C3one line summary

Introduces ImageNet-C and ImageNet-P benchmarks revealing negligible robustness gains from AlexNet to ResNet models on common corruptions and perturbations, plus methods to improve them.

References

62 extracted · 62 resolved · 0 Pith anchors

[1] Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition 2013
[2] Why do deep convolutional networks generalize so poorly to small image transformations? 2018
[3] Measuring neural net robustness with constraints 2016
[4] A non-local algorithm for image denoising 2005
[5] Defensive distillation is not robust to adversarial examples 2016

Formal links

1 machine-checked theorem link

Cited by

72 papers in Pith

Receipt and verification
First computed 2026-07-04T23:30:50.939148Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

468225c665c67c794f2afc09d157789b8056d8fa255c002ecfa5ea2f5ec4fd95

Aliases

arxiv: 1903.12261 · arxiv_version: 1903.12261v1 · doi: 10.48550/arxiv.1903.12261 · pith_short_12: I2BCLRTFYZ6H · pith_short_16: I2BCLRTFYZ6HSTZK · pith_short_8: I2BCLRTF
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO \
  | 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: 468225c665c67c794f2afc09d157789b8056d8fa255c002ecfa5ea2f5ec4fd95
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "80ca9af33ef7b9c092071cdce8a50c5eb7e3132c2263325df4107d2016529076",
    "cross_cats_sorted": [
      "cs.CV",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2019-03-28T20:56:37Z",
    "title_canon_sha256": "23277342ef1585a223722b3849f4825bc5180da3afdc610a297591f55154eba8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1903.12261",
    "kind": "arxiv",
    "version": 1
  }
}