Pith Number

pith:WQOYL4D3

pith:2026:WQOYL4D3H47KF4MJUFADZZBLQD

not attested not anchored not stored refs resolved

Informative Graph Structure Learning

Bingde Hu, Canghong Jin, Can Wang, Da Zhong Li, Hai Lin, Jiawei Chen, Sheng Zhou, Shen Han, Zhiyao Zhou

InGSL reduces redundant edges in graph structure learning by balancing similarity and diversity through a mutual-information strategy.

arxiv:2605.16809 v1 · 2026-05-16 · 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{WQOYL4D3H47KF4MJUFADZZBLQD}

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

InGSL achieves significant performance improvements at a reduced number of edges by jointly considering both similarity and diversity in edge construction by incorporating a mutual-information-guided learning strategy.

C2weakest assumption

The assumption that similarity-based edge construction is the primary source of structure redundancy and that a mutual-information term can reliably select informative edges without losing critical connections or adding new computational overhead that offsets the savings.

C3one line summary

InGSL reduces edge redundancy in existing graph structure learning methods by adding a mutual-information-guided diversity term, delivering better results with fewer edges across six tested frameworks.

References

56 extracted · 56 resolved · 1 Pith anchors

[1] Kipf and Max Welling 2017

[2] Neural message passing for quantum chemistry 2017

[3] Convolutional neural networks on graphs with fast localized spectral filtering.Advances in Neural Information Processing Systems, 29, 2016 2016

[4] Hatllm: Hierarchical attention mask- ing for enhanced collaborative modeling in llm-based recommendation.CoRR, abs/2510.10955, 2025 2025

[5] Simplifying graph convolutional networks 2019

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:23.469189Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b41d85f07b3f3ea2f189a1403ce42b80ce152caf69fd597c6c921989ad5af363

Aliases

arxiv: 2605.16809 · arxiv_version: 2605.16809v1 · doi: 10.48550/arxiv.2605.16809 · pith_short_12: WQOYL4D3H47K · pith_short_16: WQOYL4D3H47KF4MJ · pith_short_8: WQOYL4D3

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/WQOYL4D3H47KF4MJUFADZZBLQD \
  | 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: b41d85f07b3f3ea2f189a1403ce42b80ce152caf69fd597c6c921989ad5af363

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1e5a2724d9ce8e3188ceee6ce01543d1bea6fd266a552c72aa24f60d8df75691",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-16T04:46:59Z",
    "title_canon_sha256": "5b8e26913a41a026635d2a556a429b53cbc3b2ffce46a0f825137e17d7e34666"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16809",
    "kind": "arxiv",
    "version": 1
  }
}