Paper Citation Record · LEDGER

Robustness questions the interpretability of graph neural networks: what to do?

As of 19 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2505.02566.

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

pith.paper-citation-record.v1
2505.02566 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:55:12.845740Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

38 of 38 outbound references displayed

verified exact1
verified fuzzy24
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bfe90cc1-bec3-47e7-ad85-e1d2af700229 · outbound

This paper cites write newline.

Robustness questions the interpretability of graph neural networks: what to do? write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.685476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bcd0c54-88f7-46e4-b701-2919cab8ebee · outbound

This paper cites A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability.

Robustness questions the interpretability of graph neural networks: what to do? A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.387329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 72fd63bf-4077-4013-b86f-8972082c8a02 · outbound

This paper cites Explanations can be manipulated and geometry is to blame.

Robustness questions the interpretability of graph neural networks: what to do? Explanations can be manipulated and geometry is to blame

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.372496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 97c63863-a210-43da-9ec2-febb678b8b1c · outbound

This paper cites Towards A Rigorous Science of Interpretable Machine Learning.

Robustness questions the interpretability of graph neural networks: what to do? Towards A Rigorous Science of Interpretable Machine Learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.698428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d079ac40-a013-4225-a3dd-43da99d48431 · outbound

This paper cites Fast Graph Representation Learning with PyTorch Geometric.

Robustness questions the interpretability of graph neural networks: what to do? Fast Graph Representation Learning with PyTorch Geometric

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.702442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0ee1d3c-30b9-4800-a4b4-4e41ab8df817 · outbound

This paper cites and Oberman, A.

Robustness questions the interpretability of graph neural networks: what to do? and Oberman, A

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.359066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d1ab696e-74c8-4b3e-8dea-d29452ed7743 · outbound

This paper cites Hard masking for explaining graph neural networks.

Robustness questions the interpretability of graph neural networks: what to do? Hard masking for explaining graph neural networks

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.345472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6e7286f2-ddf8-4aa8-ba78-b2c5e0b15e1e · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Robustness questions the interpretability of graph neural networks: what to do? Explaining and Harnessing Adversarial Examples

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.715670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d94b364-c531-4225-a27d-de233ad5321b · outbound

This paper cites A survey of methods for explaining black box models.

Robustness questions the interpretability of graph neural networks: what to do? A survey of methods for explaining black box models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.719961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18a8a50f-8328-4c98-80d1-270aaf56f983 · outbound

This paper cites Countering Adversarial Images using Input Transformations.

Robustness questions the interpretability of graph neural networks: what to do? Countering Adversarial Images using Input Transformations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.724057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2985718-f26c-490f-882e-804daafba89c · outbound

This paper cites C., and Li'o, P.

Robustness questions the interpretability of graph neural networks: what to do? C., and Li'o, P

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.322936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 08c3e3fc-9d89-4eb5-81d8-f03f62f87b65 · outbound

This paper cites an unresolved cited work.

Robustness questions the interpretability of graph neural networks: what to do? Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:55:13.310071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3e1c27f6-2a72-4a4b-ad01-090ee814d040 · outbound

This paper cites Interpretability in graph neural networks.

Robustness questions the interpretability of graph neural networks: what to do? Interpretability in graph neural networks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.295505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d78b656a-1d4d-4bc9-a23a-10ec68dbc26a · outbound

This paper cites Cf-gnnexplainer: Counterfactual explanations for graph neural networks.

Robustness questions the interpretability of graph neural networks: what to do? Cf-gnnexplainer: Counterfactual explanations for graph neural networks

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.282445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b77725c8-478f-47bb-be71-353ebd32b8b8 · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

Robustness questions the interpretability of graph neural networks: what to do? Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.745563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dbb04c9-183a-44df-a55b-779c2daa0c28 · outbound

This paper cites Image-based recommendations on styles and substitutes.

Robustness questions the interpretability of graph neural networks: what to do? Image-based recommendations on styles and substitutes

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.267836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2a4a7ca6-cd6e-49f4-8ff1-d966c2d18cbd · outbound

This paper cites and Chen, H.

Robustness questions the interpretability of graph neural networks: what to do? and Chen, H

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.253704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 510dad87-c009-4d59-83b3-1ac23f215c29 · outbound

This paper cites Explanation in artificial intelligence: Insights from the social sciences.

Robustness questions the interpretability of graph neural networks: what to do? Explanation in artificial intelligence: Insights from the social sciences

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.239050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 90165bf0-57d2-4a78-860e-ffed6a4ffbc4 · outbound

This paper cites Connecting Interpretability and Robustness in Decision Trees through Separation.

Robustness questions the interpretability of graph neural networks: what to do? Connecting Interpretability and Robustness in Decision Trees through Separation

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:55:12.920816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 745bec96-8bf5-4f3b-a905-22bc89c3cc32 · outbound

This paper cites E., Nejdl, W., and Khosla, M.

Robustness questions the interpretability of graph neural networks: what to do? E., Nejdl, W., and Khosla, M

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.220287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 20b7c9ef-4b6d-4ccd-9a49-a5f3a5982247 · outbound

This paper cites K., and Ganapathy, V.

Robustness questions the interpretability of graph neural networks: what to do? K., and Ganapathy, V

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.206589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7c447c27-6c6b-47f4-b934-14d1e0b6002b · outbound

This paper cites Distillation as a defense to adversarial perturbations against deep neural networks.

Robustness questions the interpretability of graph neural networks: what to do? Distillation as a defense to adversarial perturbations against deep neural networks

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.193550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 85d7eff5-a6ed-414e-a27e-945382dcb4b4 · outbound

This paper cites why should i trust you?.

Robustness questions the interpretability of graph neural networks: what to do? why should i trust you?

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.179338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f08cc690-9b82-40c0-aa2f-284022607603 · outbound

This paper cites Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking.

Robustness questions the interpretability of graph neural networks: what to do? Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.783777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 457debe8-ecd8-46fe-82ea-7f5fcdaed710 · outbound

This paper cites Collective classification in network data.

Robustness questions the interpretability of graph neural networks: what to do? Collective classification in network data

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.788091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d62dc79b-6852-438c-b02a-8e1e4ef734ab · outbound

This paper cites A study of graph neural networks for link prediction on vulnerability to membership attacks.

Robustness questions the interpretability of graph neural networks: what to do? A study of graph neural networks for link prediction on vulnerability to membership attacks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.156819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bc51764c-8a62-465f-becd-f58f2478864c · outbound

This paper cites and Asokan, N.

Robustness questions the interpretability of graph neural networks: what to do? and Asokan, N

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.141014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8210999e-f287-4824-9019-1f8f0ec093a0 · outbound

This paper cites E., Dickerson, J.

Robustness questions the interpretability of graph neural networks: what to do? E., Dickerson, J

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.127471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 86101773-1017-4bd0-b57f-ffc0028b749f · outbound

This paper cites Adversarial Examples on Graph Data: Deep Insights into Attack and Defense.

Robustness questions the interpretability of graph neural networks: what to do? Adversarial Examples on Graph Data: Deep Insights into Attack and Defense

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.808568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c61274bb-b963-4d30-86ee-ea06f5d21f05 · outbound

This paper cites Gnnexplainer: Generating explanations for graph neural networks.

Robustness questions the interpretability of graph neural networks: what to do? Gnnexplainer: Generating explanations for graph neural networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.813580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b64bc2f-6046-44eb-90fe-eb6fc226dc66 · outbound

This paper cites On explainability of graph neural networks via subgraph explorations.

Robustness questions the interpretability of graph neural networks: what to do? On explainability of graph neural networks via subgraph explorations

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.098523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1b506778-ecdc-4855-99eb-b82709a4031a · outbound

This paper cites Unsupervised graph poisoning attack via contrastive loss back-propagation.

Robustness questions the interpretability of graph neural networks: what to do? Unsupervised graph poisoning attack via contrastive loss back-propagation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.083245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1db22f7c-c441-43b2-bb9d-4ded76573b66 · outbound

This paper cites and Zitnik, M.

Robustness questions the interpretability of graph neural networks: what to do? and Zitnik, M

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.069336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6c162a17-8b7e-4a36-9ca9-0bc8913a7737 · outbound

This paper cites Protgnn: Towards self-explaining graph neural networks.

Robustness questions the interpretability of graph neural networks: what to do? Protgnn: Towards self-explaining graph neural networks

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.055262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ac36a4a7-c405-405e-9b2a-5bc5c976ec84 · outbound

This paper cites Motif-backdoor: Rethinking the backdoor attack on graph neural networks via motifs.

Robustness questions the interpretability of graph neural networks: what to do? Motif-backdoor: Rethinking the backdoor attack on graph neural networks via motifs

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.040808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 909c4e2a-b255-40c6-a105-775d036b17af · outbound

This paper cites Graph neural networks: A review of methods and applications.

Robustness questions the interpretability of graph neural networks: what to do? Graph neural networks: A review of methods and applications

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:12.838245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d244444-b468-4591-b641-ff62ff8aa74f · outbound

This paper cites Robust graph convolutional networks against adversarial attacks.

Robustness questions the interpretability of graph neural networks: what to do? Robust graph convolutional networks against adversarial attacks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.017773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7b413952-d1ed-4541-8942-e25115656426 · outbound

This paper cites u gner, D., Akbarnejad, A., and G \.

Robustness questions the interpretability of graph neural networks: what to do? u gner, D., Akbarnejad, A., and G \

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:55:13.003261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

No inbound Pith citation observations are available.