Pith Number

pith:FJ7JQJMJ

pith:2026:FJ7JQJMJTPBZ76FHXQ62LZFOMD

not attested not anchored not stored refs resolved

Shortcut Mitigation via Spurious-Positive Samples

Christin Seifert, Gemma Roig, J\"org Schl\"otterer, Phuong Quynh Le, Sari Sadiya

Identifying a small set of instances where models rely on spurious attributes and regularizing the associated neurons improves robustness without needing extra annotations or balanced data.

arxiv:2605.13340 v1 · 2026-05-13 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{FJ7JQJMJTPBZ76FHXQ62LZFOMD}

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

This ensures that models learn to depend on informative features rather than being right for the wrong reasons, thereby improving robustness without requiring additional balanced held-out data or annotations.

C2weakest assumption

That a small set of instances can be reliably identified where the model relies on spurious attributes, and that regularizing the corresponding neurons will sufficiently reduce shortcut dependence without harming performance on core features.

C3one line summary

A method uses spurious-positive samples to identify and regularize neurons that rely on spurious features, improving model robustness without extra annotations or balanced data.

References

36 extracted · 36 resolved · 2 Pith anchors

[1] In: Salakhutdinov, R., Kolter, Z., Heller, K., Weller, A., Oliver, N., Scarlett, J., Berkenkamp, F 2024

[2] Advances in Neural Information Processing Systems35, 23284–23296 (2022) 2022

[3] On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer- Wise Relevance Propagation 2015 · doi:10.1371/journal.pone.0130140

[4] Advances in Neural Information Processing Systems37, 106383–106410 (2024) 2024

[5] Advances in Neural Information Processing Systems35, 33618– 33632 (2022) 2022

Receipt and verification

First computed	2026-05-18T02:44:48.407689Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2a7e9825899bc39ff8a7bc3da5e4ae60c20cc745734fe98c14cccd8fa134ce7d

Aliases

arxiv: 2605.13340 · arxiv_version: 2605.13340v1 · doi: 10.48550/arxiv.2605.13340 · pith_short_12: FJ7JQJMJTPBZ · pith_short_16: FJ7JQJMJTPBZ76FH · pith_short_8: FJ7JQJMJ

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/FJ7JQJMJTPBZ76FHXQ62LZFOMD \
  | 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: 2a7e9825899bc39ff8a7bc3da5e4ae60c20cc745734fe98c14cccd8fa134ce7d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "52b6623624810323cd2a359ee1e6ea167135e88edd1af455879897ff13bc84ed",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T11:00:12Z",
    "title_canon_sha256": "9bf62eff53d8e247f44924ae80ef1a15c62fd1c133fbe4bf10786f8f90dc8eda"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13340",
    "kind": "arxiv",
    "version": 1
  }
}