Pith Number

pith:BZMMVRF4

pith:2026:BZMMVRF4YT5TOYIJCSDFFMXRAD

not attested not anchored not stored refs resolved

MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse

Donghwan Kim, Hyunsoo Yoon

Class-wise Mahalanobis distance variance distinguishes in-distribution from out-of-distribution samples under Neural Collapse geometry.

arxiv:2605.14413 v1 · 2026-05-14 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BZMMVRF4YT5TOYIJCSDFFMXRAD}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

MahaVar achieves state-of-the-art performance on CIFAR-100 and ImageNet, with consistent improvements in both AUROC and FPR@95 over existing Mahalanobis-based methods across all benchmarks.

C2weakest assumption

The theoretical analysis relies on relaxed Neural Collapse assumptions on within-class compactness and inter-class separation to establish that ID samples structurally exhibit high class-wise distance variance.

C3one line summary

MahaVar augments the Mahalanobis OOD score with class-wise distance variance, which is theoretically higher for in-distribution samples under relaxed Neural Collapse geometry.

References

40 extracted · 40 resolved · 0 Pith anchors

[1] NECO: NEural collapse based out-of-distribution detection 2024

[2] In or out? fixing imagenet out-of- distribution detection evaluation 2023

[3] Describing textures in the wild 2014

[4] Imagenet: A large- scale hierarchical image database 2009

[5] The mnist database of handwritten digit images for machine learning research [best of the web].IEEE signal processing magazine, 29(6):141–142 2012

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:07.339041Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0e58cac4bcc4fb376109148652b2f100e5446b0da99cf8ae69c6d9d8a0a9fd82

Aliases

arxiv: 2605.14413 · arxiv_version: 2605.14413v1 · doi: 10.48550/arxiv.2605.14413 · pith_short_12: BZMMVRF4YT5T · pith_short_16: BZMMVRF4YT5TOYIJ · pith_short_8: BZMMVRF4

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/BZMMVRF4YT5TOYIJCSDFFMXRAD \
  | 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: 0e58cac4bcc4fb376109148652b2f100e5446b0da99cf8ae69c6d9d8a0a9fd82

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "278f8490cab73b8d676a5fa087764f7f15c41047d3f8689c9d9b034f3d931324",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T05:58:19Z",
    "title_canon_sha256": "f3822713da12a3622a8b7784d24a32d9d96184005ac759827cee2cd5a6dc43e1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14413",
    "kind": "arxiv",
    "version": 1
  }
}