Paper Citation Record · LEDGER

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks

As of 15 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 1 inbound Pith citation observation for arXiv:2502.04224.

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

pith.paper-citation-record.v1
2502.04224 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T23:15:52.376752Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T02:33:34.084111Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

14 of 14 outbound references displayed

verified exact0
verified fuzzy9
unresolved2
parse uncertain0
malformed identifier2
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4c3a5604-c95d-407f-a492-0937c93a67bc · outbound

This paper cites an unresolved cited work.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-08T23:15:52.510125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6701316f-bb96-4b54-b91e-bae826f57952 · outbound

This paper cites For Refine, we set its gamma parameter as 1, beta parameter as 1 and tau parameter as 0.1.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks For Refine, we set its gamma parameter as 1, beta parameter as 1 and tau parameter as 0.1

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.480428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3c24abdb-34db-44cb-8d61-e18b084babf1 · outbound

This paper cites Certified robustness of graph convolution networks for graph classification under topological attacks.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Certified robustness of graph convolution networks for graph classification under topological attacks

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.599519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3bf99a70-8722-4885-8e7e-cacb32c42430 · outbound

This paper cites Certifiably Robust Interpretation in Deep Learning.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Certifiably Robust Interpretation in Deep Learning

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-08-08T23:15:52.418544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e7f18ee9-eeb2-4dd1-9f1f-7b5c3ad5b39f · outbound

This paper cites Explainability methods for graph convolutional neural networks.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Explainability methods for graph convolutional neural networks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.570021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 13ff4dd8-b4b1-457e-86f9-d4ec112c8062 · outbound

This paper cites Reinforcement learning enhanced explainer for graph neural networks.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Reinforcement learning enhanced explainer for graph neural networks

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.556034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8a88358f-e1b0-466a-935b-4827a33fe9d0 · outbound

This paper cites Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.541736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c274b62e-0556-4eaa-a052-4e24ab5069dd · outbound

This paper cites the classifier: Mf = ⌊ ny −nb+I(y<b)−1 2 ⌋.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks the classifier: Mf = ⌊ ny −nb+I(y<b)−1 2 ⌋

Reference 11

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T23:15:52.495579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6782bbd9-6485-479b-a9e6-7c4b495705be · outbound

This paper cites Std” is the Standard Deviation of the explanation accuracy on test data across the 5 runs, and “Change Rate.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Std” is the Standard Deviation of the explanation accuracy on test data across the 5 runs, and “Change Rate

Reference 13

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T23:15:52.466033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2e818aa5-6c02-4f58-bc7b-d2998f6edf35 · outbound

This paper cites This ranges from the classic GSAGE with LSTM to modern graph transformers (Kreuzer et al., 2021; Zhu et al., 2023).

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks This ranges from the classic GSAGE with LSTM to modern graph transformers (Kreuzer et al., 2021; Zhu et al., 2023)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.450955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a7b8df88-d9bd-4624-b66f-0297b157ea2e · outbound

This paper cites Note that the complete graph GC is fixed and all subgraphs built from it are never affected.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Note that the complete graph GC is fixed and all subgraphs built from it are never affected

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.526319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e9ab4081-8cf7-4dbe-8ddd-85978333ca9f · outbound

This paper cites Certified Adversarial Robustness via Randomized Smoothing.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Certified Adversarial Robustness via Randomized Smoothing

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-08T23:15:52.313141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eade07e-62c5-4fad-902f-05bbee90d8a7 · outbound

This paper cites Certified robustness to adversarial examples with differential privacy.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Certified robustness to adversarial examples with differential privacy

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.584922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8fe9c02a-4065-43df-af86-dd387b63465b · outbound

This paper cites Certified robustness of commu- nity detection against adversarial structural perturbation via randomized smoothing.

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks Certified robustness of commu- nity detection against adversarial structural perturbation via randomized smoothing

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T23:15:52.615427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 4d01c195-8e28-4213-ba51-307097b3a7cb · inbound

Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias cites this paper.

Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks

Reference 157

Resolution: unresolved; no resolver link, observed 2026-07-14T02:33:34.084111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.