Pith Number

pith:J5ZOWQD5

pith:2026:J5ZOWQD5VWHPS4UOCOV7SXQYRK

not attested not anchored not stored refs resolved

Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models

Haonan Yuan, Jianxin Li, Junhua Shi, Philip S. Yu, Qingyun Sun, Xingcheng Fu

DyGFM decouples semantic and temporal patterns in dynamic graphs and uses divergence-conditioned prompts to enable effective multi-domain pre-training without negative transfer.

arxiv:2605.13540 v1 · 2026-05-13 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{J5ZOWQD5VWHPS4UOCOV7SXQYRK}

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

DyGFM consistently outperforms 12 state-of-the-art baselines on both node classification and link prediction tasks, achieving superior effectiveness and efficiency.

C2weakest assumption

The assumption that semantic-temporal decoupling plus divergence-aware expert selection will reliably prevent negative transfer across arbitrary domains without introducing new biases or requiring extensive hyperparameter tuning per domain pair.

C3one line summary

DyGFM introduces decoupled pre-training and divergence-conditioned prompts to create the first multi-domain dynamic graph foundation model that outperforms baselines on node classification and link prediction.

References

122 extracted · 122 resolved · 5 Pith anchors

[1] Random graph models of social networks, 2002

[2] Graph neural networks for social recommendation, 2019

[3] Graph neural networks for friend ranking in large-scale social platforms, 2021

[4] Graph convolutional neural networks for web-scale recommender systems, 2018

[5] Session-based recommendation with graph neural networks, 2019

Receipt and verification

First computed	2026-05-18T02:44:24.057293Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4f72eb407dad8ef9728e13abf95e188a9dc58646360acc0bf705b0444bb60fdc

Aliases

arxiv: 2605.13540 · arxiv_version: 2605.13540v1 · doi: 10.48550/arxiv.2605.13540 · pith_short_12: J5ZOWQD5VWHP · pith_short_16: J5ZOWQD5VWHPS4UO · pith_short_8: J5ZOWQD5

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/J5ZOWQD5VWHPS4UOCOV7SXQYRK \
  | 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: 4f72eb407dad8ef9728e13abf95e188a9dc58646360acc0bf705b0444bb60fdc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0a9739fbea1ccaec48cc3bc52a1cdf220a7fcca8d38981d0b000bd0319dc3989",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T13:50:03Z",
    "title_canon_sha256": "887ecaf0a67b021a20cab2fbc1d0a1adc0dabbb7aa1ba6e05dff9e2b22358658"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13540",
    "kind": "arxiv",
    "version": 1
  }
}