Pith Number

pith:UVPIYMV3

pith:2026:UVPIYMV3HKKAHCRSEJQNIXGUPU

not attested not anchored not stored refs resolved

DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts

Dongjin Song, Guiquan Sun, Jingchao Ni, Xikun Zhang

Many existing continual graph learning methods implicitly depend on task boundaries and degrade under continuous distribution shifts in task-free streams.

arxiv:2605.12998 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{UVPIYMV3HKKAHCRSEJQNIXGUPU}

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

Our findings indicate that many existing approaches implicitly rely on task boundary information and struggle under realistic task-free graph streams.

C2weakest assumption

The Gaussian parameterization of transition dynamics between latent task distributions accurately captures the spectrum of real-world continuous distribution shifts in graph data.

C3one line summary

DRIFT benchmark shows substantial performance degradation for continual graph learning methods under task-free continuous distribution shifts modeled via Gaussian mixtures.

References

51 extracted · 51 resolved · 4 Pith anchors

[1] Inductive representation learning on large graphs 2017

[2] Open graph benchmark: Datasets for machine learning on graphs 2020

[3] Knowledge graph embedding: A survey of approaches and applications.IEEE transactions on knowledge and data engineering, 29:2724– 2743, 2017 2017

[4] Overcoming catastrophic forgetting in neural networks.Proceedings of the national academy of sciences, 114(13):3521–3526 2017

[5] Chaudhry et al 1902 · arXiv:1902.10486

Receipt and verification

First computed	2026-05-18T03:09:00.468382Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a55e8c32bb3a94038a322260d45cd47d3e9ad589772390d3e9b512f1c7135cdf

Aliases

arxiv: 2605.12998 · arxiv_version: 2605.12998v2 · doi: 10.48550/arxiv.2605.12998 · pith_short_12: UVPIYMV3HKKA · pith_short_16: UVPIYMV3HKKAHCRS · pith_short_8: UVPIYMV3

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/UVPIYMV3HKKAHCRSEJQNIXGUPU \
  | 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: a55e8c32bb3a94038a322260d45cd47d3e9ad589772390d3e9b512f1c7135cdf

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2e085b0040a60160621ff1492320a58627da50bec6e5a08459d01650b8ecc192",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T04:54:46Z",
    "title_canon_sha256": "e66405226b3f233c78297d8164d3ad69b66251c9a8344dce723edb5bb20a71b1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12998",
    "kind": "arxiv",
    "version": 2
  }
}