Pith Number

pith:HRFP2HBB

pith:2026:HRFP2HBBY3JQ4IYM6BUYUXZP5B

not attested not anchored not stored refs pending

Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution

Jaesik Choi, Kyowoon Lee, Seongwoo Lim, Soyeon Kim

By constructing attribution paths in a variational autoencoder's latent space, MA-GIG produces more faithful feature attributions than standard path-based methods.

arxiv:2605.02167 v3 · 2026-05-04 · cs.LG · cs.AI · 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{HRFP2HBBY3JQ4IYM6BUYUXZP5B}

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

Through qualitative and quantitative evaluations, we demonstrate that MA-GIG produces faithful explanations by aggregating gradients on path features proximal to the input. Consequently, our method reduces off-manifold noise and outperforms prior path-based attribution methods across multiple datasets and classifiers.

C2weakest assumption

A pre-trained variational autoencoder accurately captures the data manifold, and decoded latent-space paths therefore yield gradient aggregations that are more faithful than those obtained from input-space paths.

C3one line summary

MA-GIG improves Integrated Gradients by performing path integration in the latent space of a pre-trained VAE so that decoded points remain closer to the learned data manifold and reduce off-manifold gradient noise.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution

Receipt and verification

First computed	2026-05-20T00:03:13.716203Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3c4afd1c21c6d30e230cf0698a5f2fe87d3b7912208e81c3fdc38be6ebf49322

Aliases

arxiv: 2605.02167 · arxiv_version: 2605.02167v3 · doi: 10.48550/arxiv.2605.02167 · pith_short_12: HRFP2HBBY3JQ · pith_short_16: HRFP2HBBY3JQ4IYM · pith_short_8: HRFP2HBB

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/HRFP2HBBY3JQ4IYM6BUYUXZP5B \
  | 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: 3c4afd1c21c6d30e230cf0698a5f2fe87d3b7912208e81c3fdc38be6ebf49322

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "40716b17f1de3f5223e39557b49855681e82e2a5d7f34e0887b541cf828854e7",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-04T02:56:29Z",
    "title_canon_sha256": "b2fb7701d7f6943f2b83bc3d1e0ea6eefa04b5553b9e6ff82a503821bc002610"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.02167",
    "kind": "arxiv",
    "version": 3
  }
}