{"as_of":"2026-08-19T22:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e3adb9c8e97361fad76101cd78fc388b03cb1b0e10659444a4d051880d886254","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:55:12.845740Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.02566/citation-record","integrity":"/paper/2505.02566/integrity","json":"/paper/2505.02566/citation-record.json","paper":"/paper/2505.02566"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:12.685476Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.685476Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:e30769b7de8c1fb1d72407bed21ca4b9a0a8369dd21d8f22e4945f30ed74a16f","observation_id":"bfe90cc1-bec3-47e7-ad85-e1d2af700229","resolution":{"observed_at":"2026-08-16T00:55:12.685476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.381954Z","title":"A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability","venue":null,"work_id":"e4933e51-9425-4aff-93ca-162068ebfa46","year":2022},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.690700Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:a0532ce9405a6d99167c40cfd31a7a36189445ade4b12c6e2bdcf47dbfb77dc7","observation_id":"8bcd0c54-88f7-46e4-b701-2919cab8ebee","resolution":{"observed_at":"2026-08-16T00:55:13.387329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.367650Z","title":"Explanations can be manipulated and geometry is to blame","venue":null,"work_id":"e27eae42-60a1-43cd-9d55-d8ebd94719bd","year":2019},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.694405Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:105b966a4a19914b857c21e6fe11a81114f2ee222604252a30241ae55590c410","observation_id":"72fd63bf-4077-4013-b86f-8972082c8a02","resolution":{"observed_at":"2026-08-16T00:55:13.372496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08608","last_updated":"2017-03-02T19:32:10Z","snapshot_observed_at":"2026-08-17T15:51:42.391912Z","submitted_at":"2017-02-28T02:19:20Z","title":"Towards A Rigorous Science of Interpretable Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.08608","snapshot_observed_at":"2026-08-16T00:55:12.698428Z","title":"and Kim, B","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.698428Z"},"links":{"cited_paper":"/paper/1702.08608","citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:cb51bcfe24e0478ccbd602a3317879cb4a7edcb41a3e594583ccd9d2e29545db","observation_id":"97c63863-a210-43da-9ec2-febb678b8b1c","resolution":{"observed_at":"2026-08-16T00:55:12.698428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.02428","last_updated":"2019-04-25T10:06:09Z","snapshot_observed_at":"2026-08-02T18:54:43.326912Z","submitted_at":"2019-03-06T14:50:02Z","title":"Fast Graph Representation Learning with PyTorch Geometric","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.02428","snapshot_observed_at":"2026-08-16T00:55:12.702442Z","title":"and Lenssen, J","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.702442Z"},"links":{"cited_paper":"/paper/1903.02428","citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:8877fadff6bb21817166d406cc3387adf0b4d84c7ae60f8cdc814863dac83bbd","observation_id":"d079ac40-a013-4225-a3dd-43da99d48431","resolution":{"observed_at":"2026-08-16T00:55:12.702442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.355044Z","title":"and Oberman, A","venue":null,"work_id":"6bed972c-3e55-4248-a8d8-bb275231eeea","year":2021},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.706682Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:5f0e0301de3742b19f97bc1433884b6b7660c1ffafc1e2c6102f9497b591e38b","observation_id":"a0ee1d3c-30b9-4800-a4b4-4e41ab8df817","resolution":{"observed_at":"2026-08-16T00:55:13.359066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.341147Z","title":"Hard masking for explaining graph neural networks","venue":null,"work_id":"2da3e982-22d1-46d0-b6a2-91a29327ed8b","year":2020},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.710949Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:0e3ec9597dfa4d65b4b9bed6b12cf259087afe47d628b9ca8a11e19781da9932","observation_id":"d1ab696e-74c8-4b3e-8dea-d29452ed7743","resolution":{"observed_at":"2026-08-16T00:55:13.345472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-19T07:17:20.004918Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-16T00:55:12.715670Z","title":"J., Shlens, J., and Szegedy, C","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.715670Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:1c1f43e0a4e7a0e8faf085de9fdce56e001e6a68b4caf7bd55de0b3bf0f0bb9e","observation_id":"6e7286f2-ddf8-4aa8-ba78-b2c5e0b15e1e","resolution":{"observed_at":"2026-08-16T00:55:12.715670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:12.719961Z","title":"A survey of methods for explaining black box models","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.719961Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:bca3036f39e082eaa7da16cf5d3649eaa9a68f1db03cff179d4c5299544dafe8","observation_id":"0d94b364-c531-4225-a27d-de233ad5321b","resolution":{"observed_at":"2026-08-16T00:55:12.719961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00117","last_updated":"2018-01-25T19:04:48Z","snapshot_observed_at":"2026-08-14T20:18:12.840327Z","submitted_at":"2017-10-31T21:22:16Z","title":"Countering Adversarial Images using Input Transformations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00117","snapshot_observed_at":"2026-08-16T00:55:12.724057Z","title":"Countering adversarial images using input transformations","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.724057Z"},"links":{"cited_paper":"/paper/1711.00117","citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:b57f058916b9fbf767df6c0d87ef522c6599ff065b1e763d9ed6e384ecf10994","observation_id":"18a8a50f-8328-4c98-80d1-270aaf56f983","resolution":{"observed_at":"2026-08-16T00:55:12.724057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.318767Z","title":"C., and Li'o, P","venue":null,"work_id":"31090e0c-9e1f-41a4-9410-ac77620a6bf1","year":2022},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.728581Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:766d06ab9111124ae5d7d2eb2560187837fd3a6946d22833a31682ad4ab5f079","observation_id":"c2985718-f26c-490f-882e-804daafba89c","resolution":{"observed_at":"2026-08-16T00:55:13.322936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.304966Z","title":null,"venue":null,"work_id":"6e3ef328-9964-4d10-87c8-1e126e6790b3","year":2018},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.733144Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:e03b8d75d730bb5802d63932d781b88400c9d226cc7f92cc143c37f3ef4bc1e2","observation_id":"08c3e3fc-9d89-4eb5-81d8-f03f62f87b65","resolution":{"observed_at":"2026-08-16T00:55:13.310071Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.291252Z","title":"Interpretability in graph neural networks","venue":null,"work_id":"f4eaf859-247b-4a30-92b0-ff14a78c64ab","year":2022},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.737411Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:a9194cfca0db5bf626cec44cfb57b2643c143f43861da9db1a98b1dc5a434194","observation_id":"3e1c27f6-2a72-4a4b-ad01-090ee814d040","resolution":{"observed_at":"2026-08-16T00:55:13.295505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.278445Z","title":"Cf-gnnexplainer: Counterfactual explanations for graph neural networks","venue":null,"work_id":"adc28964-ef1c-4f63-93fb-42d04bb4bf82","year":2021},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.741556Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:cc44ffedb9c242123a8b96feab0d2d39d8785688390284dfe3b68901b4d252d9","observation_id":"d78b656a-1d4d-4bc9-a23a-10ec68dbc26a","resolution":{"observed_at":"2026-08-16T00:55:13.282445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-16T00:55:12.745563Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.745563Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:fceab7089a4446941f8693a6785fd64e6111f61cbf1ac2fe2a9d21ba2f7dd7c1","observation_id":"b77725c8-478f-47bb-be71-353ebd32b8b8","resolution":{"observed_at":"2026-08-16T00:55:12.745563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.263106Z","title":"Image-based recommendations on styles and substitutes","venue":null,"work_id":"d5158cb7-5745-46ac-8845-78e4d08c4aa1","year":2015},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.750115Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:546e982d50674478a16c5d3c183775f538fe9c2db72a6cc946152f04517a763b","observation_id":"4dbb04c9-183a-44df-a55b-779c2daa0c28","resolution":{"observed_at":"2026-08-16T00:55:13.267836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.248992Z","title":"and Chen, H","venue":null,"work_id":"0896a7c2-2647-41f1-b085-2a1098d41aa4","year":2017},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.754363Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:cf9879d0d5e160a09d263fdb181679da33d46774445db200d476f1bf5be12d2f","observation_id":"2a4a7ca6-cd6e-49f4-8ff1-d966c2d18cbd","resolution":{"observed_at":"2026-08-16T00:55:13.253704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.234160Z","title":"Explanation in artificial intelligence: Insights from the social sciences","venue":null,"work_id":"3c35c544-5f86-4af2-b0a4-f0d1908c03ca","year":2019},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.758525Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:e9d163c064978d8e081267fd4ef1f66c6f115865fd72882c3a3cc810db3e2f6c","observation_id":"510dad87-c009-4d59-83b3-1ac23f215c29","resolution":{"observed_at":"2026-08-16T00:55:13.239050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.07048","last_updated":"2021-02-14T02:08:01Z","snapshot_observed_at":"2026-08-16T18:45:45.191789Z","submitted_at":"2021-02-14T02:08:01Z","title":"Connecting Interpretability and Robustness in Decision Trees through Separation","version":1},"cited_work":{"arxiv_id":"2102.07048","doi":null,"metadata_source":"pith","pith_arxiv_id":"2102.07048","snapshot_observed_at":"2026-08-16T00:55:12.913287Z","title":"Connecting Interpretability and Robustness in Decision Trees through Separation","venue":"cs.LG","work_id":"8a1bd894-055d-48a0-814b-b19cf7f0595f","year":2021},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.762425Z"},"links":{"cited_paper":"/paper/2102.07048","citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:8c265fa44bcee56088aa37ef74f08ea027eb2d0d84afc4b41957e3f5c49ea939","observation_id":"90165bf0-57d2-4a78-860e-ffed6a4ffbc4","resolution":{"observed_at":"2026-08-16T00:55:12.920816Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.215773Z","title":"E., Nejdl, W., and Khosla, M","venue":null,"work_id":"e6c4f429-c89c-4d90-9eb2-607c5920396a","year":2021},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.767593Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:0164164b41613f4e1067c63dc874eec9ead7991e8277f9c4b72bea71536aef88","observation_id":"745bec96-8bf5-4f3b-a905-22bc89c3cc32","resolution":{"observed_at":"2026-08-16T00:55:13.220287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.202289Z","title":"K., and Ganapathy, V","venue":null,"work_id":"b3fcfa10-51b5-4894-829b-04dd3d721865","year":2020},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.771709Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:de4891dfc07a33aadbc1b3de4ef2eb8e07ca6e362bc818f84eb7725361da9d9a","observation_id":"20b7c9ef-4b6d-4ccd-9a49-a5f3a5982247","resolution":{"observed_at":"2026-08-16T00:55:13.206589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.188981Z","title":"Distillation as a defense to adversarial perturbations against deep neural networks","venue":null,"work_id":"183e85e9-67f1-4e29-9c65-e785005af348","year":2016},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.775700Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:ceb2dde13a7cad56131d132de5464955f660fadb3a77b36b2c0185b9ca0fa317","observation_id":"7c447c27-6c6b-47f4-b934-14d1e0b6002b","resolution":{"observed_at":"2026-08-16T00:55:13.193550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.175235Z","title":"why should i trust you?","venue":null,"work_id":"d5e63be3-d722-4d65-a245-19e3ab31fa80","year":2016},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.779592Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:16aa41e0dd98002a705ee4db7f09702678a55325856a3e78a1850ea187365ffa","observation_id":"85d7eff5-a6ed-414e-a27e-945382dcb4b4","resolution":{"observed_at":"2026-08-16T00:55:13.179338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.00577","last_updated":"2022-10-03T10:22:35Z","snapshot_observed_at":"2026-08-16T19:16:29.949677Z","submitted_at":"2020-10-01T17:51:19Z","title":"Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.00577","snapshot_observed_at":"2026-08-16T00:55:12.783777Z","title":"S., De Cao, N., and Titov, I","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.783777Z"},"links":{"cited_paper":"/paper/2010.00577","citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:5389c4ef8f77ebd053d4d321bbd459b917f2f909c2e1a87261734b896f9dcdd8","observation_id":"f08cc690-9b82-40c0-aa2f-284022607603","resolution":{"observed_at":"2026-08-16T00:55:12.783777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:12.788091Z","title":"Collective classification in network data","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.788091Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:67a0e77b70ad0aaf87a3937a686463ed3e8405cb92b0fec58eb71f7e8cc443f0","observation_id":"457debe8-ecd8-46fe-82ea-7f5fcdaed710","resolution":{"observed_at":"2026-08-16T00:55:12.788091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.151641Z","title":"A study of graph neural networks for link prediction on vulnerability to membership attacks","venue":null,"work_id":"cd1035dc-b783-471e-bc14-4957c9d12613","year":2024},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.794397Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:ab54a725176b706a022d409de3370dc67c2acef8a945f0f9d5c836885667b64f","observation_id":"d62dc79b-6852-438c-b02a-8e1e4ef734ab","resolution":{"observed_at":"2026-08-16T00:55:13.156819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.136860Z","title":"and Asokan, N","venue":null,"work_id":"b76b5ea6-81f9-4929-9708-bf8b57bb1cfd","year":2022},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.798450Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:37c5b104d5d5638fdef94fe8e844cad2ab54772c667a5ec6bf48006cb52c6348","observation_id":"bc51764c-8a62-465f-becd-f58f2478864c","resolution":{"observed_at":"2026-08-16T00:55:13.141014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.122534Z","title":"E., Dickerson, J","venue":null,"work_id":"fe3282f0-0d83-4b3b-b819-26152b98eb55","year":2020},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.803421Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:c15402d9a0fdd93e991e20f2e63a8732b040c07ab6614dfb5c63f57e9aa49a06","observation_id":"8210999e-f287-4824-9019-1f8f0ec093a0","resolution":{"observed_at":"2026-08-16T00:55:13.127471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.01610","last_updated":"2019-05-22T08:45:44Z","snapshot_observed_at":"2026-08-14T17:07:27.904740Z","submitted_at":"2019-03-05T00:43:48Z","title":"Adversarial Examples on Graph Data: Deep Insights into Attack and Defense","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.01610","snapshot_observed_at":"2026-08-16T00:55:12.808568Z","title":"Adversarial examples on graph data: Deep insights into attack and defense","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.808568Z"},"links":{"cited_paper":"/paper/1903.01610","citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:0443a853a7c044aed4268e745486b483a38ae35238a8f4c98dcb0f0b4160434d","observation_id":"86101773-1017-4bd0-b57f-ffc0028b749f","resolution":{"observed_at":"2026-08-16T00:55:12.808568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:12.813580Z","title":"Gnnexplainer: Generating explanations for graph neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.813580Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:6ed87728cf7d087f388dec4e9435538c0ffcd1d718268d8bc4f8b0389c4d0c4f","observation_id":"c61274bb-b963-4d30-86ee-ea06f5d21f05","resolution":{"observed_at":"2026-08-16T00:55:12.813580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.094404Z","title":"On explainability of graph neural networks via subgraph explorations","venue":null,"work_id":"f6465e19-b717-48f2-bb26-3b80adbfb372","year":2021},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.817706Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:796c51fac503499d72e2d8536556e90365ca76d1d9e506811fd42854f2a928a7","observation_id":"2b64bc2f-6046-44eb-90fe-eb6fc226dc66","resolution":{"observed_at":"2026-08-16T00:55:13.098523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.078284Z","title":"Unsupervised graph poisoning attack via contrastive loss back-propagation","venue":null,"work_id":"db6a12c8-d2be-48ff-b9af-054afd28298c","year":2022},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.821710Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:eab5943162a7721572767ccf2cf663397771f4edb94eab146b2bd473641be95f","observation_id":"1b506778-ecdc-4855-99eb-b82709a4031a","resolution":{"observed_at":"2026-08-16T00:55:13.083245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.064837Z","title":"and Zitnik, M","venue":null,"work_id":"54f3b860-62ba-4eab-97db-3aced66996b7","year":2020},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.826382Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:3764c24e74f9c08250a03fd53994e09078cfc11cf1c50078b4ff55e6d80c7af5","observation_id":"1db22f7c-c441-43b2-bb9d-4ded76573b66","resolution":{"observed_at":"2026-08-16T00:55:13.069336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.050355Z","title":"Protgnn: Towards self-explaining graph neural networks","venue":null,"work_id":"c4172a6e-e9c9-4573-a6a8-9f186cf95c10","year":2022},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.830507Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:dd09b92eeca488804197c40d9bb3df735f20c0b39c4b1479f2b9cc4c1a0b5ef6","observation_id":"6c162a17-8b7e-4a36-9ca9-0bc8913a7737","resolution":{"observed_at":"2026-08-16T00:55:13.055262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.036187Z","title":"Motif-backdoor: Rethinking the backdoor attack on graph neural networks via motifs","venue":null,"work_id":"c054062d-3492-4314-a67b-5e2dbd7f5950","year":2022},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.834410Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:0b7dd53173b9aa181c0c23c9bf83c47677ddc909cb1ea8b00587caef5afa4266","observation_id":"ac36a4a7-c405-405e-9b2a-5bc5c976ec84","resolution":{"observed_at":"2026-08-16T00:55:13.040808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:12.838245Z","title":"Graph neural networks: A review of methods and applications","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.838245Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:1d24e596497ceca6a2c46280bbd45af9a32021772ceffa0c37f7fdaa18ba0f40","observation_id":"909c4e2a-b255-40c6-a105-775d036b17af","resolution":{"observed_at":"2026-08-16T00:55:12.838245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:13.012995Z","title":"Robust graph convolutional networks against adversarial attacks","venue":null,"work_id":"41b5d5d0-9e18-43f7-89e1-c3eb4a7d3991","year":2019},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.842097Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:21abfb3daf0ff993a56cb8bc9d3abe04d8cfe136e0e2bcd9435141c1ba1605ae","observation_id":"8d244444-b468-4591-b641-ff62ff8aa74f","resolution":{"observed_at":"2026-08-16T00:55:13.017773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:55:12.997759Z","title":"u gner, D., Akbarnejad, A., and G \\","venue":null,"work_id":"ed3feec5-7e76-4d6f-b3b7-10b70a58f8a1","year":2018},"citing_paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-16T00:55:12.845740Z"},"links":{"citing_paper":"/paper/2505.02566"},"observation_digest":"sha256:e331493fea0cc488e11a4b0aea1b8ef49382a06b10f1cac0eee465b4e6fc3488","observation_id":"7b413952-d1ed-4541-8942-e25115656426","resolution":{"observed_at":"2026-08-16T00:55:13.003261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.02566","last_updated":"2025-05-05T11:14:56Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T16:31:20.734582Z","submitted_at":"2025-05-05T11:14:56Z","title":"Robustness questions the interpretability of graph neural networks: what to do?"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":24},"total_outbound_references":38},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"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."}