Pith Number

pith:ZPPNWJBC

pith:2026:ZPPNWJBC6LBU2JE7LF2QEPYHET

not attested not anchored not stored refs resolved

What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition

Danny Wang, Ruihong Qiu, Zi Huang

TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection.

arxiv:2605.13032 v2 · 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{ZPPNWJBC6LBU2JE7LF2QEPYHET}

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

TIDE explicitly decomposes information into feature-specific, structure-specific and joint components, preserving only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information.

C2weakest assumption

That the joint information component can be reliably separated into label-relevant versus spurious parts and that removing the spurious specific components will produce a measurable entropy gap and higher ID confidence without harming ID accuracy.

C3one line summary

TIDE decomposes graph information into feature-specific, structure-specific, and joint components to retain only label-relevant joint signals and improve OOD detection over standard supervised learning.

References

133 extracted · 133 resolved · 0 Pith anchors

[1] Your classifier is secretly an energy based model and you should treat it like one , booktitle =

[2] Srikant , title =

[3] CVPR , year =

[4] NeurIPS , year =

[5] NeurIPS , year =

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:08:59.705804Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2

Aliases

arxiv: 2605.13032 · arxiv_version: 2605.13032v2 · doi: 10.48550/arxiv.2605.13032 · pith_short_12: ZPPNWJBC6LBU · pith_short_16: ZPPNWJBC6LBU2JE7 · pith_short_8: ZPPNWJBC

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/ZPPNWJBC6LBU2JE7LF2QEPYHET \
  | 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: cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "22c3d41c0972e868d92754e2efb08855e5233e59672145b98e89ed6767afa0f6",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T05:36:33Z",
    "title_canon_sha256": "884cfa273ddbca2b3722ab471c4a7852e80f52a8a04ac34f4d0093b6b50ad74e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13032",
    "kind": "arxiv",
    "version": 2
  }
}