Paper Citation Record · LEDGER

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks

As of 20 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2504.16748.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2504.16748 v2

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:04:03.721615Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact1
verified fuzzy14
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9e6bca83-c4e8-4744-992c-1faf5009c574 · outbound

This paper cites We focus on a special case defined as follows: eα(λ,t ) = ∞X n=0 (−1)n λntαn Γ(αn + 1), λ> 0, t≥.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks We focus on a special case defined as follows: eα(λ,t ) = ∞X n=0 (−1)n λntαn Γ(αn + 1), λ> 0, t≥

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.899842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b33d1fd9-1e96-4c52-a8eb-efb3d2d6b5a0 · outbound

This paper cites HGRL relies on graph augmentations, while DSSL assumes a graph generation process, which may not always reflect real-world graphs.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks HGRL relies on graph augmentations, while DSSL assumes a graph generation process, which may not always reflect real-world graphs

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.978686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e7c9cb31-f928-4a79-b122-f8e5660086ee · outbound

This paper cites SP-GCL (Wang et al., 2023), on the other hand, effectively handles heterophilic graphs by capturing both low- and high-frequency components.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks SP-GCL (Wang et al., 2023), on the other hand, effectively handles heterophilic graphs by capturing both low- and high-frequency components

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.965990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5add08eb-2f84-4862-9670-185768389d3c · outbound

This paper cites Building on the BGRL framework, AFGRL eliminates the need for augmentations by generating positive samples directly from the original graph for each node.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Building on the BGRL framework, AFGRL eliminates the need for augmentations by generating positive samples directly from the original graph for each node

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.952828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0bf26a36-5700-4718-aaeb-5d7428dfd481 · outbound

This paper cites It maximizes the correlation between two augmented views of the same input while decorrelating the feature dimensions within a single view’s representation.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks It maximizes the correlation between two augmented views of the same input while decorrelating the feature dimensions within a single view’s representation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.939132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4d8719fb-7d1d-4d5a-b43c-b682a34c4aed · outbound

This paper cites Replacing d/ dt withDα t , one obtains its FDE version as Dα t Y(t) =σ (Fθ(Z(t),t ))−γZ(t)−νY(t) Dα t Z(t) = Y(t).

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Replacing d/ dt withDα t , one obtains its FDE version as Dα t Y(t) =σ (Fθ(Z(t),t ))−γZ(t)−νY(t) Dα t Z(t) = Y(t)

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.912481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f38f780c-20e8-4baf-928a-1bb3574517a4 · outbound

This paper cites (c) For fixed i andj, we havebα1,i,j >b α2,i,j.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks (c) For fixed i andj, we havebα1,i,j >b α2,i,j

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.886718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1f1d09ed-7586-49c2-a6af-c53ee465694b · outbound

This paper cites These datasets are among the most widely used benchmarks for node classification.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks These datasets are among the most widely used benchmarks for node classification

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.873051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 70ef7e20-4e5a-4250-a834-5e55dde673a5 · outbound

This paper cites Each node represents a word (possibly non-unique) in the text, with features based on word embeddings.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Each node represents a word (possibly non-unique) in the text, with features based on word embeddings

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.859579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c716c4a6-2c92-49f3-a189-5541a29bdd59 · outbound

This paper cites Nodes represent papers, and edges indicate citation relationships.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Nodes represent papers, and edges indicate citation relationships

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.845436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6a9484f1-89ed-4bf2-9c8a-b6f77dc847dc · outbound

This paper cites Contrastive Loss Functions In the absence of explicit negative samples, non-contrastive methods focus on maximizing agreement among positive samples.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Contrastive Loss Functions In the absence of explicit negative samples, non-contrastive methods focus on maximizing agreement among positive samples

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.830653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ab07dd09-0b87-4da3-956f-63900b274fe5 · outbound

This paper cites The definitions of Euclidean loss, Cosmean loss, Barlow Twins loss, and VICReg loss are provided below.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks The definitions of Euclidean loss, Cosmean loss, Barlow Twins loss, and VICReg loss are provided below

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.817191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 08bf9eea-154d-4ba9-9aa1-a946ec43fe31 · outbound

This paper cites One can find other approaches and more discussions in Tarasov (2011).

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks One can find other approaches and more discussions in Tarasov (2011)

Reference 2010

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.924815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 00c58fdd-7db3-4304-b16c-3af74154b8e0 · outbound

This paper cites Graph contrastive learning with adaptive augmentation.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Graph contrastive learning with adaptive augmentation

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:04:03.991010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4c777bdf-039d-4176-9c8a-3745b0041769 · outbound

This paper cites Localized Contrastive Learning on Graphs.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Localized Contrastive Learning on Graphs

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-16T11:04:03.659575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aa9f702-5545-4762-9568-9f07f5b68fbc · outbound

This paper cites A Fractional Graph Laplacian Approach to Oversmoothing.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks A Fractional Graph Laplacian Approach to Oversmoothing

Reference 2022

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:04:03.803958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ae0e94c4-32ed-442b-92bb-7396977f65d6 · outbound

This paper cites Fast Training of Convolutional Networks through FFTs.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Fast Training of Convolutional Networks through FFTs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T11:04:03.655332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa5dc74f-b3c6-419f-bbac-5b894866cf9a · outbound

This paper cites Deep Graph Contrastive Representation Learning.

Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Deep Graph Contrastive Representation Learning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T11:04:03.664004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.