{"as_of":"2026-08-18T22:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5e4cecce14d100d3c3cf79ee3dd2d1624682bad2d3fb2c1965d403ab0f0d8d2a","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:21:18.472806Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2504.20848/citation-record","integrity":"/paper/2504.20848/integrity","json":"/paper/2504.20848/citation-record.json","paper":"/paper/2504.20848"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:21:18.964011Z","title":"A comprehensive survey on graph neural networks,","venue":null,"work_id":"25f4afdd-5bd7-4377-bc2e-a1b7a66c2f6b","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.338687Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:7a0e1839bc27edb222787c9966e0f0d6c56e8cfd5963026284811cd5a2d14e8d","observation_id":"5675e575-1b76-4fdc-baeb-d1fd2303c1fc","resolution":{"observed_at":"2026-08-16T05:21:18.967535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.953685Z","title":"Graph neural networks: A review of methods and applications,","venue":null,"work_id":"662c8f56-c98e-4554-bb4c-23a2c1365dd5","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.342520Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:70883bcdd98113d6ac8a059349a9f4a0fb229856900d60aa626e33fdd609a17e","observation_id":"b084d752-1c6f-479d-b5de-2d77531e6703","resolution":{"observed_at":"2026-08-16T05:21:18.957354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.941931Z","title":"Deep learning on graphs: A survey,","venue":null,"work_id":"15ffe0b4-22b3-4662-a845-a200061a8a62","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.345760Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:c14e9c12a2b48f46d5b974994ae201ed2b92523281434b3c1313a1b316e692ef","observation_id":"f28a11e8-42b1-4d1e-a2b4-ce17c1b3aaee","resolution":{"observed_at":"2026-08-16T05:21:18.945670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.11174","last_updated":"2022-02-22T05:46:58Z","snapshot_observed_at":"2026-08-18T02:59:46.802838Z","submitted_at":"2021-01-27T02:35:41Z","title":"Graph Neural Network for Traffic Forecasting: A Survey","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.11174","snapshot_observed_at":"2026-08-16T05:21:18.350510Z","title":"Graph neural network for traffic forecasting: A survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.350510Z"},"links":{"cited_paper":"/paper/2101.11174","citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:5a433c9a35bb36a07706fa31d92b8851afca3ac1786fff7afa67ea5a4040b0fc","observation_id":"6f5e626f-838c-4686-9886-e806081df75b","resolution":{"observed_at":"2026-08-16T05:21:18.350510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.00653","last_updated":"2020-12-12T17:21:00Z","snapshot_observed_at":"2026-08-18T12:50:15.290359Z","submitted_at":"2020-03-02T04:32:38Z","title":"Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies","version":3},"cited_work":{"arxiv_id":"2003.00653","doi":null,"metadata_source":"pith","pith_arxiv_id":"2003.00653","snapshot_observed_at":"2026-08-16T05:21:18.589547Z","title":"Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies","venue":"cs.LG","work_id":"7b4d895c-2ab2-42c4-a97f-e2dcd731f9eb","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.354777Z"},"links":{"cited_paper":"/paper/2003.00653","citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:e2a9edc8b7a0cfd60d5440477931a83681e4adfda5c561c37e7fe51d9d92f2bc","observation_id":"22905088-21af-439b-a70d-6e785c676979","resolution":{"observed_at":"2026-08-16T05:21:18.595768Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.930989Z","title":"Adversarial attacks and defenses in images, graphs and text: A review,","venue":null,"work_id":"41678767-c29f-4478-b289-52a529b2cd0d","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.358624Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:9ddfda12c95411b1ab71c48592a6ca1db7f2f5ccedde20a36f521bff73da40d8","observation_id":"b7e505ab-ea9a-41b4-9a58-67a503432977","resolution":{"observed_at":"2026-08-16T05:21:18.934414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.05730","last_updated":"2022-04-05T12:54:56Z","snapshot_observed_at":"2026-08-07T09:25:51.003050Z","submitted_at":"2020-03-10T12:48:00Z","title":"A Survey of Adversarial Learning on Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.05730","snapshot_observed_at":"2026-08-16T05:21:18.362525Z","title":"A survey of adversarial learning on graphs,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.362525Z"},"links":{"cited_paper":"/paper/2003.05730","citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:433706a7f5b9f0b31ecb6c0975f4755e9318dcb8472396e0a9c2791af6cd0263","observation_id":"811c4a91-8e43-44f2-955e-68621d62629c","resolution":{"observed_at":"2026-08-16T05:21:18.362525Z","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":"2026-08-16T05:21:18.919684Z","title":"Adversarial attacks on neural networks for graph data,","venue":null,"work_id":"2158a402-1fff-49a8-8484-9840584bada6","year":2018},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.365780Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:4b5da5a641344027679b19248c5ed6208e459d24f0f424057c7b1beb9f834ac9","observation_id":"8c35f9f0-0415-40a2-b54b-4346fe46ca49","resolution":{"observed_at":"2026-08-16T05:21:18.922954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.907139Z","title":"Adversarial examples for graph data: Deep insights into attack and defense,","venue":null,"work_id":"4694dae5-979c-47b4-bcd4-78a2605f3655","year":2019},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.369404Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:f32a6c9fabc288588a2f4dee72d0edde135d6f0c761ce5e3e11a05701e9c57d6","observation_id":"3837b1dd-8cc5-4a4e-a079-d1d95107a63c","resolution":{"observed_at":"2026-08-16T05:21:18.911540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.895506Z","title":"Adversarial attack on graph structured data,","venue":null,"work_id":"fe2969b4-c4c8-4d4e-9fd0-9754a10788d0","year":2018},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.372298Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:074ac7e18db8f7a3a37986fe6663e6035bf328322435bf0d4db6841ceffff93c","observation_id":"41160d92-b668-4c38-a1c4-d945f032f3f5","resolution":{"observed_at":"2026-08-16T05:21:18.899950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02797","last_updated":"2018-09-15T08:31:50Z","snapshot_observed_at":"2026-08-15T14:17:45.666459Z","submitted_at":"2018-09-08T13:08:26Z","title":"Fast Gradient Attack on Network Embedding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.02797","snapshot_observed_at":"2026-08-16T05:21:18.375580Z","title":"Fast gradient attack on network embedding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.375580Z"},"links":{"cited_paper":"/paper/1809.02797","citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:4bc5dbbfe615cdffd99fc1483fa9dba927f46c5847f3d27c84d07c08a9994893","observation_id":"6833c652-b089-4569-aa96-6a61f2c9da31","resolution":{"observed_at":"2026-08-16T05:21:18.375580Z","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":"2026-08-16T05:21:18.883637Z","title":"Single node injection attack against graph neural networks,","venue":null,"work_id":"8b6f1809-0752-489e-a54f-3bcf79017974","year":2021},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.379464Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:ddcf5284b128b6c44e66f77ea187314c9af14b631a1238e2535b79e4e8392bf5","observation_id":"f4c79cd9-66f3-443f-93ee-34466c37d965","resolution":{"observed_at":"2026-08-16T05:21:18.887596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.382459Z","title":"All you need is low (rank) defending against adversarial attacks on graphs,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.382459Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:b9b7cb316fc8f41f4ad8ec11ccae4cf074de521a8f89ba81943bde308edfc82b","observation_id":"3d4cec8b-859b-4bad-be84-c65fe1683aab","resolution":{"observed_at":"2026-08-16T05:21:18.382459Z","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":"2026-08-16T05:21:18.864466Z","title":"Robust graph convolutional networks against adversarial attacks,","venue":null,"work_id":"d4d5f257-abff-4b65-a5ff-82bf7aee8fd1","year":2019},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.385748Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:d12a456aeee5c749fd0953d95bcd9b09da7ae6d142b59d724d55e9c1b5ddbc01","observation_id":"b5eab0bb-3b0d-4cd6-9a5f-9365f822c459","resolution":{"observed_at":"2026-08-16T05:21:18.869676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.854235Z","title":"Understanding structural vulnerability in graph convolutional networks,","venue":null,"work_id":"579a00e1-2a0b-4aff-a6b0-c6ff6ad3236e","year":2021},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.388633Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:a47f63600904f2f5b768e624932c0621a1cff8ed957d32f7ac4ba4840bfd6817","observation_id":"c8486d6c-9e99-43a1-a6e1-12d7f0e9a97f","resolution":{"observed_at":"2026-08-16T05:21:18.857577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.843592Z","title":"Batch virtual adversarial training for graph convolutional networks,","venue":null,"work_id":"be332b12-f1d1-495d-9527-42414ef3c947","year":2023},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.392065Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:4dfab99fd23600e72d7a59d91368e38da417813a2885ef6bca5dfebbc179d188","observation_id":"18e2e82f-450e-459f-8b6d-bebac24db458","resolution":{"observed_at":"2026-08-16T05:21:18.847523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.832988Z","title":"Towards locality- aware meta-learning of tail node embeddings on networks,","venue":null,"work_id":"23aa5494-20ea-4bb0-8762-662d4a9b2fa9","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.394988Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:f4ae00447e20f1e5213e757768e75089faadc1af8faccc4ad768f70822e1b017","observation_id":"aa034663-f4ce-4071-b3e1-dd7cbcaca124","resolution":{"observed_at":"2026-08-16T05:21:18.836387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.822204Z","title":"Investigating and mitigating degree-related biases in graph convoltuional networks,","venue":null,"work_id":"a2141196-d9a8-463f-84a4-6cdb51c1b8df","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.398425Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:2794475d7362a88938a1e8759d0e1b556748abcdd540e96ed25cbd93b66c7d16","observation_id":"c173e031-166f-4eb0-85b9-2ed2b1c47e20","resolution":{"observed_at":"2026-08-16T05:21:18.825682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.811664Z","title":"Tail-gnn: Tail-node graph neural networks,","venue":null,"work_id":"36d8b187-e2f0-4f17-a082-d77ee82fb3e0","year":2021},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.401519Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:5899646541a54baf1b6bc38c421a0c599a9f75c0334e20d467dc55bbe1dfe04e","observation_id":"e7e5897a-18f0-44ee-9326-505566c7b6ba","resolution":{"observed_at":"2026-08-16T05:21:18.815172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.800487Z","title":"Lte4g: Long-tail experts for graph neural networks,","venue":null,"work_id":"9a863567-2c36-418a-b1aa-52efebd45a54","year":2022},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.404696Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:78e738be4ce9477a07013eb300c99474881ca79a2adfb5f7cbe3af08d2052ef2","observation_id":"3ffc1171-52e5-40c5-9142-15505b71a4f0","resolution":{"observed_at":"2026-08-16T05:21:18.803865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.791487Z","title":"Rawlsgcn: Towards rawlsian difference principle on graph convolutional network,","venue":null,"work_id":"ce7c5c6d-34d7-44db-9e67-80f350df3a4e","year":2022},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.407835Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:453f69e8deb345484f5c51a85ae59df583537b590b056d01e8a7dbeabfff740e","observation_id":"333d6259-dbbe-4b14-9b68-856ae3d81ac1","resolution":{"observed_at":"2026-08-16T05:21:18.794639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.781431Z","title":"On generalized degree fairness in graph neural networks,","venue":null,"work_id":"6e906c10-3f04-442c-a638-6f0db87854e9","year":2023},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.410911Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:68b2be10725638747f6b8c8370126368d1ae1ec2e0dc195b67a32026838dbcfa","observation_id":"f6472a65-ed5b-40ea-859c-1d5ac4cf3e7d","resolution":{"observed_at":"2026-08-16T05:21:18.784486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.770705Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":"ad82cbb5-80e4-45b8-be91-57a31b2aab44","year":2017},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.415227Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:ddef7e08e3bb5bed614220e75ab1296047de97e54a28e01406a9fd616affacb5","observation_id":"8b647e45-ee1f-40a2-8fb0-344f5fe03aef","resolution":{"observed_at":"2026-08-16T05:21:18.773894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.761471Z","title":"Inductive representation learning on large graphs,","venue":null,"work_id":"43bc31ca-787b-45f1-b864-c3d3f836bdc4","year":2017},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.418246Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:fa7a109f6cf886c92392757871616cf5146b1cc90b4d4c6e3061bd44b8086d68","observation_id":"edff1286-1719-42a6-a24d-788665d35a3c","resolution":{"observed_at":"2026-08-16T05:21:18.764745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.749937Z","title":"Graph attention networks,","venue":null,"work_id":"9c53868c-fb4b-4113-998f-7bbb5779aae5","year":2018},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.421958Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:4c443dca724796c8ed79a14a32852025e0afbce8f110a2221b92b7d2dd3ac0c6","observation_id":"86127692-505e-4cb5-960c-4c3aca69c31a","resolution":{"observed_at":"2026-08-16T05:21:18.753763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.736768Z","title":"Simplifying graph convolutional networks,","venue":null,"work_id":"ebe45f62-ec62-4a61-ae29-d39e9e7d9963","year":2019},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.425257Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:43479ab787575c370591ad6cd3017c359e15730fa79444c4abe6177c07b719c9","observation_id":"ce999898-d205-4c33-80c8-c2566a300419","resolution":{"observed_at":"2026-08-16T05:21:18.741398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.724771Z","title":"Towards deeper graph neural networks,","venue":null,"work_id":"65bfd6fb-a786-4917-9b90-2219b3d1cf96","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.428435Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:2b4b255675a9af5a21d6757148f6c0c39dbbdfe61c87cbd984221c909a8ff2f2","observation_id":"806cf05a-b3af-4964-9423-6e1f50c7e55c","resolution":{"observed_at":"2026-08-16T05:21:18.729336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07739","last_updated":"2020-06-13T23:00:22Z","snapshot_observed_at":"2026-08-16T06:19:36.364672Z","submitted_at":"2020-06-13T23:00:22Z","title":"DeeperGCN: All You Need to Train Deeper GCNs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07739","snapshot_observed_at":"2026-08-16T05:21:18.431791Z","title":"Deepergcn: All you need to train deeper gcns,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.431791Z"},"links":{"cited_paper":"/paper/2006.07739","citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:290801bc3fa134210bccf076d7bac2900fc083154b57e874ea1d3b7faeed74aa","observation_id":"03841d30-e9dc-4f7b-a83a-7e86eeb4bdbb","resolution":{"observed_at":"2026-08-16T05:21:18.431791Z","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":"2026-08-16T05:21:18.714863Z","title":"Scalable graph neural network training: The case for sampling,","venue":null,"work_id":"46194860-541f-4fbc-b802-0d811527e272","year":2021},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.435734Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:f98a9102bab9cb388e9eee6fed85cdfb238ccf847b8d48cc42206868dabda99f","observation_id":"47e4ecc8-8048-4298-b8dd-d817dc0cb245","resolution":{"observed_at":"2026-08-16T05:21:18.718541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.702485Z","title":"Distgnn: Scalable distributed training for large-scale graph neural networks,","venue":null,"work_id":"36b0be6b-a2f5-4384-a0b0-32d2450b485a","year":2021},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.439764Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:0b14a416f5929b06cde3b5ae2a3e40d55cf35bfba496e709e8e8d25f6f417148","observation_id":"e47c18a8-d552-4010-a932-5631cb099cf1","resolution":{"observed_at":"2026-08-16T05:21:18.707167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.690000Z","title":"Scalable and efficient full-graph gnn training for large graphs,","venue":null,"work_id":"858aaab1-8acb-4551-a209-fd6cab72243a","year":2023},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.443485Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:0ef48d79db302be4a9c441a271b7a4b8229bb017db468655a8235f3e04ce8b94","observation_id":"f02f839a-6612-43f7-933d-ab9bed3a6c77","resolution":{"observed_at":"2026-08-16T05:21:18.693908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.676864Z","title":"Adversarial attacks on graph neural networks via meta learning,","venue":null,"work_id":"42c0193a-a62d-480a-bb8b-5dd3e798fa3b","year":2018},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.446936Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:d643adead6a46036ec0044cd3d1fcd218ca577485aaa9b1a80623cc7b145a057","observation_id":"5494f943-554d-4cdc-9da1-ca2f37671b26","resolution":{"observed_at":"2026-08-16T05:21:18.681353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.450245Z","title":"Adversarial attack on large scale graph,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.450245Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:cfec7acca8d1311668a1189e9f21bb0048632a1bb16234279f70163da69f87f1","observation_id":"b3554fdd-d62d-43e2-82ed-758331680a3a","resolution":{"observed_at":"2026-08-16T05:21:18.450245Z","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":"2026-08-16T05:21:18.666775Z","title":"Adversarial attacks on graph neural networks via node injections: A hierarchical reinforcement learning approach,","venue":null,"work_id":"2ac56082-db19-4a39-8203-8bf749a29093","year":2020},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.453578Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:c9e6da9336e66fbf83631270a12ec08f208b21963b69a0c1baae8fc1bf8fea7c","observation_id":"cadc0b37-a826-4ec7-b322-bc4a48c97a3e","resolution":{"observed_at":"2026-08-16T05:21:18.670163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.656051Z","title":"Gani: Global attacks on graph neural networks via imperceptible node injections,","venue":null,"work_id":"883252c6-c9d5-42b3-a792-302ce8185697","year":2024},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.456222Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:b78c22714ae20f792d040473c991b0a7417f8227ee59f30d20fa42053faedeab","observation_id":"6128ee49-fdb1-403f-8ac2-f11910e1c4b9","resolution":{"observed_at":"2026-08-16T05:21:18.659697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.644723Z","title":"Robust training of graph convolutional networks via latent perturbation,","venue":null,"work_id":"765dcd12-8a22-4273-bc25-c59cbaf80d17","year":2021},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.460052Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:19220a8352a8d3e87cfd16da260f3e79429c4c9f112630c6a377650e0e031d12","observation_id":"01eb7128-65e0-4970-8924-ced9d79631d4","resolution":{"observed_at":"2026-08-16T05:21:18.648658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.04214","last_updated":"2019-10-14T22:09:35Z","snapshot_observed_at":"2026-08-14T16:17:54.647770Z","submitted_at":"2019-06-10T18:20:09Z","title":"Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.04214","snapshot_observed_at":"2026-08-16T05:21:18.463072Z","title":"Topology attack and defense for graph neural networks: An optimization perspective,","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.463072Z"},"links":{"cited_paper":"/paper/1906.04214","citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:ef97e41433395993226db5fdc64cfd3deef97684736e08151785ed4c2feb9552","observation_id":"5684824c-9c42-4014-b076-7fda0929e63d","resolution":{"observed_at":"2026-08-16T05:21:18.463072Z","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":"2026-08-16T05:21:18.633788Z","title":"Certifiable robustness to graph perturbations,","venue":null,"work_id":"18a9ffba-86f3-4464-affc-8c8efbad40cc","year":2019},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.466487Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:9077c67aaf9f611091fc6da2db50faa15aacdcb829ca1ddaf32018f7ba0d63b3","observation_id":"2616244f-5708-4769-92d4-59433aae5933","resolution":{"observed_at":"2026-08-16T05:21:18.638350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:21:18.469283Z","title":"K-nearest neighbor,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.469283Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:722644a23e5cba468b940166693e4ae1fa49ed8974b13ba91d5a6a9210a3043a","observation_id":"bdb8029e-2daf-4bc8-8345-237f630587b3","resolution":{"observed_at":"2026-08-16T05:21:18.469283Z","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":"2026-08-16T05:21:18.616559Z","title":"Collective classification in network data,","venue":null,"work_id":"ebfc231b-c5a1-4dd0-b9dd-c5d42a0077b5","year":2008},"citing_paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:18.472806Z"},"links":{"citing_paper":"/paper/2504.20848"},"observation_digest":"sha256:a0cea2cf09e6bc60d1841bab213b450cd9996e50de92b0a70672e630bd865027","observation_id":"09e32d5c-bbff-44cd-aa85-50a744e534ef","resolution":{"observed_at":"2026-08-16T05:21:18.620559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.20848","last_updated":"2025-04-29T15:19:05Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T11:28:53.310050Z","submitted_at":"2025-04-29T15:19:05Z","title":"Mitigating the Structural Bias in Graph Adversarial Defenses"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":31},"total_outbound_references":40},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2504.20848."}