{"as_of":"2026-08-12T15:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:97ce531cacce4869d3ba3dedfefb09d55608737c84d900aba3b957b6c7e38f17","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T18:53:15.907924Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2501.10985/citation-record","integrity":"/paper/2501.10985/integrity","json":"/paper/2501.10985/citation-record.json","paper":"/paper/2501.10985"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T18:53:16.623760Z","title":"https://https://github.com/tkipf/gcn","venue":null,"work_id":"53be0b4c-e294-484b-942b-9693359bc513","year":null},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.694727Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:0fe28198b09a54caf12d50be2676203a65474bda800bd4a7ca6346aa266cd5f4","observation_id":"859567cc-cc23-4c6e-ac44-ae7ada09e590","resolution":{"observed_at":"2026-08-10T18:53:16.628706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.610286Z","title":"https://github.com/xinle ihe/link stealing attack","venue":null,"work_id":"e6d7dee7-e286-48da-ad99-131cb8034fc8","year":null},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.699961Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:be64825fdbaf9ecb764ea6c121586eb50d1d924c05212163f4ff4227b0babee0","observation_id":"ec8a9235-3ebc-44ee-9f8d-4735646bc864","resolution":{"observed_at":"2026-08-10T18:53:16.614600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.596829Z","title":"https://github.com/PetarV-/GAT, 2017","venue":null,"work_id":"c5d21815-ddd1-45a1-86f3-985e5f336574","year":2017},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.704622Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:703de10e845ced8f703001925fe8367379a685d2d2b53a4c02436395fa6c1aff","observation_id":"120808fa-bf25-4455-9448-56ad8150e9be","resolution":{"observed_at":"2026-08-10T18:53:16.600863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.583424Z","title":"Deep learning with differential privacy","venue":null,"work_id":"8b35849c-0aa1-4f92-bf70-afeb108d8cc4","year":2016},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.709213Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:3a2a2da5998d824b63eac814570fe445e9897111b5637197ef97ba70ffdc73e5","observation_id":"f1b42a29-bcb4-4d36-b7c9-65b92ba5a44a","resolution":{"observed_at":"2026-08-10T18:53:16.587413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.570379Z","title":"Structural, Syntactic, and Statistical Pattern Recognition","venue":null,"work_id":"9f8ba70a-f10e-405b-9771-bab5e451f273","year":2002},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.714203Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:5ba404ae8d65b7f3979348e02b4df5868a96311aa7c09bdcb0f34ec9eb497030","observation_id":"1821cb71-28be-4a3b-baa9-6a9c907d35a7","resolution":{"observed_at":"2026-08-10T18:53:16.574728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.556424Z","title":"Extracting training data from large language models","venue":null,"work_id":"e4b46b21-89dc-47ba-9ce7-e5913e52ff5d","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.718779Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:868588766172ca243979441160a97d4bb9e33d40fa72d661d4ae4d1e92d2a911","observation_id":"c09b8231-b5d0-4474-93f0-0ee3c158deaf","resolution":{"observed_at":"2026-08-10T18:53:16.561176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.542828Z","title":"Exploring connections between active learning and model extraction","venue":null,"work_id":"1383af83-441c-416e-af0e-6a5f0dc099e7","year":2020},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.723556Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:424d413108db3e9a5ab4df61183a897a1e01d1e5726cc460fd144082cd834a82","observation_id":"7b620eaf-64e4-4cf4-9448-dfe3196fb473","resolution":{"observed_at":"2026-08-10T18:53:16.547289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.528632Z","title":"Label-only membership inference attacks","venue":null,"work_id":"f6bce5f0-adaf-4c72-a7f7-6de9ccfd25e5","year":1964},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.727938Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:34e970b44322326b8674438f1356edf498d3694ad3e16bbc12ddf852a9481982","observation_id":"b8c62a11-7fdc-404d-9f8e-016d23e9119f","resolution":{"observed_at":"2026-08-10T18:53:16.533308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.514136Z","title":"Distinguishing enzyme structures from non-enzymes without alignments","venue":null,"work_id":"2a8a7643-beff-41e9-bd5c-23a0ae004c1d","year":2003},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.733098Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:2a36b050de3d221e0f21e217726d022f6024035c432a93e65914d211d31f65d1","observation_id":"dbcbb3da-204e-42b8-9451-969f5f054bd7","resolution":{"observed_at":"2026-08-10T18:53:16.518863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.499913Z","title":"Inductive repre- sentation learning on large graphs","venue":null,"work_id":"93511fb1-77ac-4205-816f-29a6d6151fe4","year":2017},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.737246Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:1c53b80e505ff232b052843e1d129456f30b4328bb08db4e05c3aa9af21acc23","observation_id":"0394d47a-309c-4536-87c5-6b44552aa5b0","resolution":{"observed_at":"2026-08-10T18:53:16.504674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.486043Z","title":"Stealing links from graph neural networks","venue":null,"work_id":"a21cfb7b-fec0-4151-8a42-0a8270c92785","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.741615Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:3453f4dbd4a0ed2c1c456575c06b157b10e8c55c97bd2e8a7ef7d82188333dcd","observation_id":"0882f329-d60a-4d9d-94b2-1fd348afa44e","resolution":{"observed_at":"2026-08-10T18:53:16.490410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05429","last_updated":"2021-02-10T13:51:54Z","snapshot_observed_at":"2026-08-12T10:03:11.480813Z","submitted_at":"2021-02-10T13:51:54Z","title":"Node-Level Membership Inference Attacks Against Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.05429","snapshot_observed_at":"2026-08-10T18:53:15.745884Z","title":"Node-level membership inference attacks against graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.745884Z"},"links":{"cited_paper":"/paper/2102.05429","citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:1c4c1853ea60834fb49d4f679dfbbcb12fa6ca10624a878baa02803a2b3601a5","observation_id":"ac41a6bb-1007-4b66-a2a4-f0575081cf18","resolution":{"observed_at":"2026-08-10T18:53:15.745884Z","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":"2026-08-10T18:53:16.472272Z","title":"Transmia: membership inference attacks using transfer shadow training","venue":null,"work_id":"f8f2df00-b6d7-430f-afca-5ad6cd3a9a01","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.750893Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:07422e3d7b57fbd1eda971f560e8f6f25768745dffecf292df39508f84423cff","observation_id":"050b672a-4f4a-4412-85a4-d97b175c5d9d","resolution":{"observed_at":"2026-08-10T18:53:16.476823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.458869Z","title":"High accuracy and high fidelity extraction of neural networks","venue":null,"work_id":"60f6b592-20b6-4ee5-acc6-ddd4ea2b081d","year":2020},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.754981Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:a5b5442ddf8025093909545385df54c61d21aa966f638f197ef8898be3f63759","observation_id":"9507c598-f29a-41d6-85af-55058cbd7bc5","resolution":{"observed_at":"2026-08-10T18:53:16.463254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.445165Z","title":"Memguard: Defending against black-box membership inference attacks via adversarial examples","venue":null,"work_id":"acf10fd9-5c01-426a-b99b-b305ce256e30","year":2019},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.759298Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:c9e6f57d1a45cb6d70efb898d9aa28afc896f9614f06e18e7a90e306ea4706ae","observation_id":"2d025f7a-0e0a-4619-aad4-8b13e2bd23d7","resolution":{"observed_at":"2026-08-10T18:53:16.449897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.432176Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":"2b0878eb-d296-4301-ac81-2209339aa895","year":2017},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.763648Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:8e03549fe4be1b6395c91803ba401bb195ca19fa56c138c7c43cf7bf41ba5c2b","observation_id":"e1b478fa-22ba-4680-815d-d01fd60011fe","resolution":{"observed_at":"2026-08-10T18:53:16.436221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.419361Z","title":"Stolen memories: Leveraging model memorization for calibrated {White-Box} membership inference","venue":null,"work_id":"7e6c43dc-917c-4b1e-8917-32e92cc7630d","year":2020},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.767971Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:145d17b99f9b844aeea9a5ed04a3ba03d74d6a8cca0e0e9f30ae678baae67033","observation_id":"fbba1405-11b9-48ce-9cf0-2561366e9c34","resolution":{"observed_at":"2026-08-10T18:53:16.423474Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.405429Z","title":"Membership inference attacks and defenses in classification models","venue":null,"work_id":"4b53096c-a871-480f-a064-485613224a0e","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.772312Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:dcb5faa6628a28f413ca391dbb4a575e91840d7ff6b24bc4751e2347ddc6be9e","observation_id":"49a3d0fd-2e0e-440d-afbc-50966cddc216","resolution":{"observed_at":"2026-08-10T18:53:16.410176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.391514Z","title":"Membership leakage in label-only exposures","venue":null,"work_id":"975f0789-0bc7-43a1-984e-a9d72e3880cd","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.776594Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:087d5c567bd7b44cc078da677b38ebf1f96d63fba2175559f3b0721914b990b4","observation_id":"8131b299-e17e-4d43-bdc9-a44eb29f4b13","resolution":{"observed_at":"2026-08-10T18:53:16.396383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.377524Z","title":"Encodermi: Membership inference against pre-trained encoders in contrastive learning","venue":null,"work_id":"8b350fcd-d773-4a16-993a-caf72f8c408c","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.780998Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:ed1e01ced28a96347420324d3f02e81c59a7e4b38daa964c6e6fcdcc9765bd80","observation_id":"b01168dd-7a72-4e5e-8600-19240d1b6ced","resolution":{"observed_at":"2026-08-10T18:53:16.382238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.363620Z","title":"Devil in disguise: Breaching graph neural networks privacy through infiltration","venue":null,"work_id":"b6e560c3-9f00-4ec4-94d9-b77b4218ad57","year":2023},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.785873Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:8aa3c2c8a57bc9ada46a018036a6118a81595b33b8d194f033207e2d562db9ec","observation_id":"8d35d4e7-a166-4c00-b39c-e34cce40191f","resolution":{"observed_at":"2026-08-10T18:53:16.368233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.348799Z","title":"Comprehensive pri- vacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","venue":null,"work_id":"b4281314-b624-4a41-a755-a8bdc307f6f1","year":null},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.790273Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:2459fcec33af79f19e5ca8663049409e7160d02cb19ce819f40111150eb1768b","observation_id":"4a7b7c8d-2f36-48e4-a957-26b9e1e967c9","resolution":{"observed_at":"2026-08-10T18:53:16.353546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.334244Z","title":"Machine learning with membership privacy using adversarial regularization","venue":null,"work_id":"4f0cbde9-e4f3-41e8-89a7-17c827bfc6a6","year":2018},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.794860Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:865b4e67684d51af28deeec89879e28b283ff0cdc9d808aaef20f9d90705f9ae","observation_id":"e1108a70-6c65-4259-8ceb-3d16b9555098","resolution":{"observed_at":"2026-08-10T18:53:16.339234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.318703Z","title":"Membership inference attack on graph neural networks","venue":null,"work_id":"bc2add7a-e80f-493a-a267-ab67513db9e7","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.799323Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:8d2f8bb26acb36e91ebfdd347560d713704809d09454a54f160b3bfc5b8662ff","observation_id":"0c76d516-9628-4637-b207-bd256fd72477","resolution":{"observed_at":"2026-08-10T18:53:16.323815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.302873Z","title":"White-box vs black-box: Bayes optimal strategies for membership inference","venue":null,"work_id":"2be60217-d2b3-46b0-9e84-e2c4527e255f","year":2019},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.803582Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:ada830e2261d50ea70d49de0ce26a16797786e107c06277f9c957c68039c12b5","observation_id":"7a9d8cf0-5082-4499-8488-c6b325039568","resolution":{"observed_at":"2026-08-10T18:53:16.307562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.288239Z","title":"Gap: Differentially private graph neural net- works with aggregation perturbation","venue":null,"work_id":"838f2957-6536-46e9-908d-bf94e8e4378b","year":2023},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.807633Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:92a961479054863bdded7a9af1f82e2266ab7ab7cc30408f6e2832403cd259a2","observation_id":"7d4a92d8-eed6-4f47-943d-a7da326aea72","resolution":{"observed_at":"2026-08-10T18:53:16.293015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.274158Z","title":"Gap: Differentially private graph neural net- works with aggregation perturbation","venue":null,"work_id":"c637c748-1315-4875-89fb-e0669d96c9b4","year":2023},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.811940Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:596558dbd030e408870b6b1be27e46798bfa1fc432b7731b9fd1a6f4e78994be","observation_id":"dc8a0da1-8c50-413a-9129-c908bde357ca","resolution":{"observed_at":"2026-08-10T18:53:16.278948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.259588Z","title":"Updates-leak: Data set inference and reconstruction attacks in online learning","venue":null,"work_id":"60c4a78b-e5d8-47fd-8289-7835fbeffcb6","year":2020},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.815983Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:a0c4096d6a68509d41d53a54377767c66fa89317ec1cf1b8d61882bdb9533d31","observation_id":"832e6fa3-b5e1-406e-8c5c-86c1b483c757","resolution":{"observed_at":"2026-08-10T18:53:16.264394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.245062Z","title":"Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models","venue":null,"work_id":"0183e61c-9bad-4c6e-9e80-ee756d6ff913","year":2019},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.820498Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:12bcf4a2d40bc0d5071ff43a7e08eda3bb8a1a365792dd9105ab1eb581d03ca8","observation_id":"09245560-9fbe-468e-8e7d-187b7a30b1f2","resolution":{"observed_at":"2026-08-10T18:53:16.249700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:15.824428Z","title":"The graph neural network model","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.824428Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:8508dea038f1107564bd98756a761e50e86258579cf8924584f6fb84c4c22dd1","observation_id":"221438e5-e3ce-491c-85b6-82d462af4bf1","resolution":{"observed_at":"2026-08-10T18:53:15.824428Z","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":"2026-08-10T18:53:16.220011Z","title":"Privacy-preserving deep learning","venue":null,"work_id":"e08bd7cf-733d-42f1-8dd3-1b0eaaa26e6c","year":2015},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.828477Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:c808293accda8977d548f5ece5f685a8d3a9e5e8a9cd4aed052308122db9214c","observation_id":"d82605bf-397d-4c1a-9a69-f718c106564c","resolution":{"observed_at":"2026-08-10T18:53:16.224845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.206687Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"fe568271-4396-4269-8a45-4ee4bd8651d8","year":2017},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.832258Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:5bf45af6391056c6f48c9f68cb0600d2865fcb561fd6658de1ad11562a0331f8","observation_id":"df2fdb86-613c-4f51-8620-ce4524cc2115","resolution":{"observed_at":"2026-08-10T18:53:16.210878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.192210Z","title":"Information leakage in embedding models","venue":null,"work_id":"ced8992b-9747-4031-973f-b4036c10e40d","year":2020},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.836226Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:9b9cc5a9857ee279837d7c030a4f08e3a6c4b56ed883af2304cb3864dcdd0b84","observation_id":"155e0289-5145-43fd-8ea6-1fec7a705fde","resolution":{"observed_at":"2026-08-10T18:53:16.197047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.178327Z","title":"Systematic evaluation of privacy risks of machine learning models","venue":null,"work_id":"7cd4ec7f-d3a6-425a-bc94-e06d48b79ab5","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.840074Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:5aa1dc5ee49999cc538ba649327b4ad69c3d222e1c11342625ceb95885564e29","observation_id":"928cf93c-e313-4891-98ec-ddaa63316e1a","resolution":{"observed_at":"2026-08-10T18:53:16.182774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.164385Z","title":"Privacy risks of securing machine learning models against adversarial examples","venue":null,"work_id":"11110373-6202-4d6c-82f3-260d8a1e3516","year":2019},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.844420Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:8c78fca976ce6c07dde2f0ec8af6fe03ff1fa5c332fb8cb2a8ad6970ed460028","observation_id":"35c97d71-cbb6-4115-94f8-6156f2a458d4","resolution":{"observed_at":"2026-08-10T18:53:16.168866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:15.848999Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.848999Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:c9168a2cf0c190113276f557c5c2049d99a2f069092dfcfafb0d4d58f243a2e9","observation_id":"587865f1-24dc-400b-941b-2668c68164c4","resolution":{"observed_at":"2026-08-10T18:53:15.848999Z","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":"2026-08-10T18:53:16.141183Z","title":"Stealing machine learning models via prediction {APIs}","venue":null,"work_id":"3f5b9a7f-006f-422d-9e13-2780ccba578d","year":2016},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.853605Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:70c6aeb25ed4d476df38219e4beaa53f3c92771e4791c32aace16ab6a0066354","observation_id":"6c5a411f-a7a0-43b7-9e20-a1ad7fd426ad","resolution":{"observed_at":"2026-08-10T18:53:16.146090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.126917Z","title":"Graph attention networks","venue":null,"work_id":"66326cc0-cc9c-47b6-be17-87ac1d462c37","year":2018},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.857776Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:a9911e82e0313d1395bc6ffc45bcd64c3b5e885b21720a432014d0154c407482","observation_id":"24763788-55c0-490f-aacd-818432e42799","resolution":{"observed_at":"2026-08-10T18:53:16.131340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.111947Z","title":"Stealing hyperparameters in machine learning","venue":null,"work_id":"d3037a72-2309-40bd-b98e-2d35fb6b0332","year":2018},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.862008Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:c3a5fb92bd86780d705b8f64b6797250fb07def67796ef02b878877278596b5e","observation_id":"3726bf0a-b429-4758-8a99-ca2502e91e3d","resolution":{"observed_at":"2026-08-10T18:53:16.117030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.097114Z","title":"Differentially private empirical risk minimization revisited: Faster and more general","venue":null,"work_id":"4faf493e-6d86-4dd5-a77d-f69797d67b06","year":2017},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.866099Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:c9207d5ecb793fce946ef8dd2520bb6a6abc9d42d62a894e01ff8022d8073f9a","observation_id":"90359d8b-7d8d-4e90-8e82-cf2cf7b698ae","resolution":{"observed_at":"2026-08-10T18:53:16.102174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.082511Z","title":"Link membership inference at- tacks against unsupervised graph representation learning","venue":null,"work_id":"41a541dd-af42-4a22-9276-6c9e18fac64c","year":2023},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.870072Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:809734306a9a5c6f371e07d2689d7b78f0032c4aaecf1805435dbe1a9d6de558","observation_id":"9a26f239-2a31-471a-8cb5-eb46d11a6c95","resolution":{"observed_at":"2026-08-10T18:53:16.087529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.068211Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":"bf0cecc4-3b93-4d6b-a7e3-ce9cbbabac24","year":2017},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.874129Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:7c7a10e7fcb431b3c1f36db3b4422d9cb5a27279b6fe10cfba7f199a0669be49","observation_id":"4ca12d4f-e14e-4025-8824-b13accd41646","resolution":{"observed_at":"2026-08-10T18:53:16.072740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.053454Z","title":"Vertex cover","venue":null,"work_id":"eb13f1d2-9df9-447c-b14a-7c6fc24ae783","year":null},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.878187Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:d98c779ce5fee85d46273950786fe2a523be58457084747307749ecbebd926a3","observation_id":"585f4f94-b7c6-422b-8fab-da6f4a667820","resolution":{"observed_at":"2026-08-10T18:53:16.057800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.039256Z","title":"Adapting membership inference attacks to gnn for graph classification: Ap- proaches and implications","venue":null,"work_id":"6a3fa6e7-06af-419d-a561-75e9b1d629ed","year":2021},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.882278Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:634257832dd207b7de461c1657cb7eb5236f1216e999114bd582a03a68c0c942","observation_id":"c091bcee-2c9d-4510-949d-b9a16171c08b","resolution":{"observed_at":"2026-08-10T18:53:16.043869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:16.025104Z","title":"Linkteller: Recovering private edges from graph neural networks via influence analysis","venue":null,"work_id":"40370d31-25ac-4eac-8e0c-392c59d8fa79","year":2005},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.886467Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:9ed1e08cf01d0a4ce34e637dc16618a7c6372d4470110e861646c7f718769636","observation_id":"8a3a91d1-aaeb-44c6-8c31-9376b755ad20","resolution":{"observed_at":"2026-08-10T18:53:16.029541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05784","last_updated":"2024-05-09T14:03:52Z","snapshot_observed_at":"2026-08-12T07:44:34.516357Z","submitted_at":"2024-05-09T14:03:52Z","title":"Link Stealing Attacks Against Inductive Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.05784","snapshot_observed_at":"2026-08-10T18:53:15.890584Z","title":"Link stealing attacks against inductive graph neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.890584Z"},"links":{"cited_paper":"/paper/2405.05784","citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:816eb512630f0cb8de2adfc8264b8d8e79511d2d350d38534ba8225e1e0a4ebc","observation_id":"3e6d8192-7608-46df-a698-24196fde3cfc","resolution":{"observed_at":"2026-08-10T18:53:15.890584Z","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":"2026-08-10T18:53:16.010082Z","title":"How powerful are graph neural networks? In International Conference on Learning Representations (ICLR) , 2019","venue":null,"work_id":"43cd8c97-b4c5-4d53-a8c7-1780199b1cb0","year":2019},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.894998Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:f87e788aefd5c1a118e049438b8098fc8b249e4255f3b9c190784f42812b54a4","observation_id":"61670f12-b490-450a-8f77-6dbcf0e91afe","resolution":{"observed_at":"2026-08-10T18:53:16.015151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:15.994250Z","title":"Differentially private model publishing for deep learning","venue":null,"work_id":"aa6fbdf7-ce40-4976-afc5-81e484d49450","year":2019},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.899067Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:cd6f13af9009f4579f7c1aeda0cd148f1342c81180a95baa4398723e516f571c","observation_id":"1df095e6-0dc3-403e-8309-85c1e65fadd1","resolution":{"observed_at":"2026-08-10T18:53:15.999261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T18:53:15.903618Z","title":"Graph transformer networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.903618Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:15f827b1ffb07660a0c03810411a4c2b7ba2bb1aaddae44f7112128d82d7e9d9","observation_id":"d63a667c-6c81-4a76-8c0c-7425d25be10f","resolution":{"observed_at":"2026-08-10T18:53:15.903618Z","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":"2026-08-10T18:53:15.968897Z","title":"Demystifying uneven vulnerability of link stealing attacks against graph neural networks","venue":null,"work_id":"739c74d2-3082-4945-958e-5cf7bb5ad6b3","year":2023},"citing_paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:15.907924Z"},"links":{"citing_paper":"/paper/2501.10985"},"observation_digest":"sha256:78ce1868cc8e0304aecb477870d454adb3c98fa3261f15d6e235dc69f282a30e","observation_id":"a9583594-08aa-4f6e-a205-58bbf49e65d3","resolution":{"observed_at":"2026-08-10T18:53:15.975143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.10985","last_updated":"2025-05-13T06:32:32Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T13:28:02.594700Z","submitted_at":"2025-01-19T08:39:22Z","title":"GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":45},"total_outbound_references":50},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2501.10985."}