{"as_of":"2026-08-10T09:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ddce770dc5e21ed33c695dff971cdc6f08a04eb477ff1da1017b7e267df0e186","coverage":[{"denominator":77,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":77,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T15:53:59.520306Z","state":"measured"},{"denominator":77,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":77,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2508.19352/citation-record","integrity":"/paper/2508.19352/integrity","json":"/paper/2508.19352/citation-record.json","paper":"/paper/2508.19352"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:54:20.114866Z","title":"MixHop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","venue":null,"work_id":"5aac90ab-7afb-48aa-965e-f67557300b6d","year":2019},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:46.428400Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:cb4b7b765eaf9ba8698a29572c986f7c9636ee1c1960a316df7897a82d97c7d8","observation_id":"db833f6e-5c70-4292-b1a1-d71d996f1cba","resolution":{"observed_at":"2026-08-05T15:54:20.294429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:19.718142Z","title":"On the bottleneck of graph neural networks and its practical implications","venue":null,"work_id":"20bcebb1-7fac-45f6-992d-7d86a0574827","year":2021},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:46.613994Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:de46e33000978953c51b7587ef1918cd80f109d55ed6eb3c5d2132cbadd3b586","observation_id":"1581e0a8-7c6f-4911-82d8-ea6280fd2b76","resolution":{"observed_at":"2026-08-05T15:54:19.902861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07025","last_updated":"2024-07-01T09:27:34Z","snapshot_observed_at":"2026-08-07T17:08:44.516610Z","submitted_at":"2024-02-10T19:12:31Z","title":"Generalization Error of Graph Neural Networks in the Mean-field Regime","version":3},"cited_work":{"arxiv_id":"2402.07025","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.07025","snapshot_observed_at":"2026-08-05T15:54:01.415964Z","title":"Generalization Error of Graph Neural Networks in the Mean-field Regime","venue":"stat.ML","work_id":"ea378754-a7f7-41e4-a81e-af586d5e9e9b","year":2024},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:46.809584Z"},"links":{"cited_paper":"/paper/2402.07025","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:2ddd9f30e28a518a9ec53ca092a3615b87a16741da09930d131ea17c8faa89c1","observation_id":"6c500caf-1e56-4d2a-83ef-f470921caaf2","resolution":{"observed_at":"2026-08-05T15:54:01.546653Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.08584","last_updated":"2019-05-27T04:22:57Z","snapshot_observed_at":"2026-08-01T13:55:48.495792Z","submitted_at":"2019-01-24T18:58:16Z","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.08584","snapshot_observed_at":"2026-08-05T15:53:47.018860Z","title":"Du, Wei Hu, Zhiyuan Li, and Ruosong Wang","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:47.018860Z"},"links":{"cited_paper":"/paper/1901.08584","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:de6a6a9d472d8333faf917742fee1f15a0fac9732bab155ceb39f3c746edbe0e","observation_id":"c87952d9-f8f2-4efe-a2e3-35f1f1ae49eb","resolution":{"observed_at":"2026-08-05T15:53:47.018860Z","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":"2026-08-05T15:54:19.283579Z","title":"A closer look at memorization in deep networks","venue":null,"work_id":"8b9d834f-4fc9-40e6-897b-20354284e166","year":2017},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:47.218438Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:540c72d74192d0cf4651fad39712d815ebfcd690ba00a84466e528e23801aaa7","observation_id":"23765f1e-eb2c-449f-81c8-cc86150c8b38","resolution":{"observed_at":"2026-08-05T15:54:19.508992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:18.901175Z","title":"Deep learning through the lens of example difficulty","venue":null,"work_id":"cdc0efe4-a2c6-4bae-9772-ac6869bbd83e","year":2021},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:47.440493Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:4e3ebf4d60c56675f26047c08c1e681b77c191f6f49ae187556146b8315b0163","observation_id":"c68541a4-010f-4df2-a8cb-e5b29051f331","resolution":{"observed_at":"2026-08-05T15:54:19.094147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:53:47.632337Z","title":"Emergence of scaling in random networks","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:47.632337Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:80219a8d0bc62f482681a37ecd37310250b5deef84b4635e3e86200afb6c6f46","observation_id":"3bd39413-f573-402d-a29d-c15551cdc4d2","resolution":{"observed_at":"2026-08-05T15:53:47.632337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.07684","last_updated":"2024-12-10T17:18:33Z","snapshot_observed_at":"2026-08-08T05:19:07.225459Z","submitted_at":"2024-12-10T17:18:33Z","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.07684","snapshot_observed_at":"2026-08-05T15:53:47.866817Z","title":"The pitfalls of memorization: When memorization hurts generalization, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:47.866817Z"},"links":{"cited_paper":"/paper/2412.07684","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:8e4c3ee768f29fdf2e6d6737fbcf6c5ce18504b6fc1c3a7e5081345b4e0b09b3","observation_id":"851bddba-058b-4594-91b5-daee5bdf8d7c","resolution":{"observed_at":"2026-08-05T15:53:47.866817Z","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":"2026-08-05T15:54:18.509436Z","title":"Graph neural networks use graphs when they shouldn’t, 2024","venue":null,"work_id":"4a5d9af1-0a14-4cd9-b143-fe3bd30d3fc3","year":2024},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:48.025521Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:80ebbbaa115cc674814500b1c33ca0dccbe16d9785172317c20164a68915e6c6","observation_id":"c317b482-a0f7-4a9d-9596-f097b951e26e","resolution":{"observed_at":"2026-08-05T15:54:18.743594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:18.168362Z","title":"Make heterophily graphs better fit gnn: A graph rewiring approach, 2022","venue":null,"work_id":"94c2ca4b-a098-4509-b1d4-1cab690d701a","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:48.189066Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:6bb36d445abd62395427b97f9ea7c60b43674c1d0d2f5396de54357a44c0914e","observation_id":"e4083dd0-715c-4c03-9a6b-e831673574e4","resolution":{"observed_at":"2026-08-05T15:54:18.354807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:17.776250Z","title":"Memorization and optimization in deep neural networks with minimum over-parameterization","venue":null,"work_id":"e06b1b4b-04b5-499e-9b29-3fbe41fb9081","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:48.432297Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:e9983909719f8788d7f21288df57ae2b53f91e5324e29643cc9092feb635df0d","observation_id":"cba4570e-78ac-4e08-800f-8086d5e5568b","resolution":{"observed_at":"2026-08-05T15:54:17.962166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:17.345929Z","title":"Biognn: How graph neural networks can solve biological problems","venue":null,"work_id":"8d6cf20e-920d-4a3f-958c-080d0ea79c4d","year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:48.619731Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:a0605ae4492b8f86ff593c7148c4622879307b2850a7b07e66969a5250fc6437","observation_id":"e8bd7345-1136-4852-b9df-f9328d9a75ac","resolution":{"observed_at":"2026-08-05T15:54:17.537513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:17.030742Z","title":"How attentive are graph attention networks? In International Conference on Learning Representations, 2022","venue":null,"work_id":"05723b63-2ff0-4f90-a017-61ce9ba739ac","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:48.749225Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:25992aac3baa1bfc05828bc09ab5542d503c6448bdd5cdce7034204cb08b2774","observation_id":"28af3de1-8988-4ec1-9b19-e99d7f53bf05","resolution":{"observed_at":"2026-08-05T15:54:17.171539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.13478","last_updated":"2021-05-02T16:16:03Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-04-27T21:09:51Z","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.13478","snapshot_observed_at":"2026-08-05T15:53:48.907653Z","title":"Bronstein, Joan Bruna, Taco Cohen, and Petar Velickovic","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:48.907653Z"},"links":{"cited_paper":"/paper/2104.13478","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:9fa591e34ecabc15ca9163eff926838084914791306e7a9cc61aa5726a73ae15","observation_id":"69e6de8f-f90d-48ef-9c7a-4004e04674e8","resolution":{"observed_at":"2026-08-05T15:53:48.907653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:53:49.101481Z","title":"Extracting training data from large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:49.101481Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:34b3323c34ec990cceb3b3faa4a1cc7f8def18eb1404f3dfa7ec62bbe4118ba6","observation_id":"042ad211-b56d-4f76-a80f-b23fffa1c35b","resolution":{"observed_at":"2026-08-05T15:53:49.101481Z","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":"2026-08-05T15:54:16.650065Z","title":"Membership inference attacks from first principles","venue":null,"work_id":"62e8d866-ef32-4fc4-bc31-c45deaadaf7e","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:49.321766Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:b30e6a6a2d27cbf969f0edbff0d7cd24c5d6fbdab0f907346789a5e16b8e286c","observation_id":"32cd0d3a-c088-44d5-ac0b-85ec18bbb275","resolution":{"observed_at":"2026-08-05T15:54:16.855986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:16.316310Z","title":"The privacy onion effect: Memorization is relative","venue":null,"work_id":"46b1014c-dbaa-4182-9c49-277e007e9b97","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:49.508676Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:31b1fee2addc394bd685f1977735f876d971434e969dda0b54052ccf4b307a32","observation_id":"399fee7b-768c-4398-acd0-07091048e874","resolution":{"observed_at":"2026-08-05T15:54:16.490686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07646","last_updated":"2023-03-06T06:28:18Z","snapshot_observed_at":"2026-08-03T19:51:05.627063Z","submitted_at":"2022-02-15T18:48:31Z","title":"Quantifying Memorization Across Neural Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07646","snapshot_observed_at":"2026-08-05T15:53:49.879066Z","title":"Quantifying memorization across neural language models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:49.879066Z"},"links":{"cited_paper":"/paper/2202.07646","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:13256cdaedc7ea45f26bf1121ee392d0e6cd22ef1f6525892134e24c9e04203f","observation_id":"7bc7ee87-4ba5-429e-9e47-35418b5f713b","resolution":{"observed_at":"2026-08-05T15:53:49.879066Z","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":"2026-08-05T15:54:16.006637Z","title":"On kernel-target alignment","venue":null,"work_id":"b37b7eaf-43c0-4c12-bea0-1f6bdda572ee","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:50.060381Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:c9e9835d38ca8f1eeafee70da73e01bf99e787ead75221838fe1603610e5c3f2","observation_id":"5fb7586e-a252-4aa4-8b88-079d27d1408a","resolution":{"observed_at":"2026-08-05T15:54:16.153048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:15.355885Z","title":"Attentive walk-aggregating graph neural networks","venue":null,"work_id":"f43c46af-09f8-41bd-9cbb-9384cbb7a9b2","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:50.513932Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:ce4e8a0c04824b0337b3261d7040abc6cbbf33b9703983bde2b841c5a458bda0","observation_id":"6d44fffb-5237-46cf-9926-2d08c371ddd3","resolution":{"observed_at":"2026-08-05T15:54:15.539616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:53:50.718149Z","title":"Does learning require memorization? a short tale about a long tail","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:50.718149Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:f6369c5d2369ca51867faf402104dc0a2078b35de49eae7f8d1e7b16ccff4da9","observation_id":"f26413f2-2011-4a1f-a6e0-c509ced76552","resolution":{"observed_at":"2026-08-05T15:53:50.718149Z","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":"2026-08-05T15:54:14.932201Z","title":"How powerful are k-hop message passing graph neural networks","venue":null,"work_id":"33354d89-007c-471e-a72e-ac982f8a2acd","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:50.899797Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:fe39601740d162009c826ef9425497cab30dd0f257a0b619948cf4d1e5d44356","observation_id":"592d7fe9-e375-4626-a94b-8565972f91a0","resolution":{"observed_at":"2026-08-05T15:54:15.101672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:14.495236Z","title":null,"venue":null,"work_id":"11e26798-01dd-43a4-acb1-867f0967ead4","year":2019},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:51.065712Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:0de5622510d60e4d606e13b4253c78f6d68cb9862bf85acb266b8fad2454ac3f","observation_id":"418b9f37-accf-4781-bd33-e193fb60d16a","resolution":{"observed_at":"2026-08-05T15:54:14.715291Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:14.151996Z","title":"Schoenholz, Patrick F","venue":null,"work_id":"4ccd2a0c-0333-400b-9cd8-70592a1fd74b","year":2017},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:51.246936Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:e56539231656a21e9fa45274e4c8ad8a8de2b0478e4a9cf57808d28c906c3030","observation_id":"9a5f47e2-5384-4f6d-8d4f-c9fb6c29dfc9","resolution":{"observed_at":"2026-08-05T15:54:14.334321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:53:51.377231Z","title":"Giraldo, Konstantinos Skianis, Thierry Bouwmans, and Fragkiskos D","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:51.377231Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:0f15c5031280e25e25c49401555fe418de1dbd06be071405979f9fd415619445","observation_id":"eda04afc-ef09-4233-8fce-d38c817942a1","resolution":{"observed_at":"2026-08-05T15:53:51.377231Z","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":"2026-08-05T15:54:13.839984Z","title":"Understanding the difficulty of training deep feedforward neural networks","venue":null,"work_id":"1810c353-b9e9-42db-ae0b-5218e24188b3","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:51.580935Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:a1f6da8291bedc60f90d3f17f3af87ed8f15448cb587e754b19b6095da7e8527","observation_id":"a0dbb547-9856-4755-bd7f-ec7ae784fddc","resolution":{"observed_at":"2026-08-05T15:54:13.973440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2005.15559","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:54:00.943583Z","title":null,"venue":null,"work_id":"077b07fd-7d46-4ea1-a6a8-5bcb4f4c727e","year":2005},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:51.991572Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:2b438c1b7e9f81de619f401d19dac0a0511e533a38dceae9ac1ff571f67cc975","observation_id":"d2ee4238-2beb-4aa1-93ba-a4b6144618a9","resolution":{"observed_at":"2026-08-05T15:54:01.080863Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:13.005164Z","title":"Hamilton, Rex Ying, and Jure Leskovec","venue":null,"work_id":"0fd3af32-cfc2-47ec-9a38-792e7f1cad7b","year":2017},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:52.144379Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:3db4c2dc4b37bbeced1e0c4f4443318cb80441ad8c10191dae957eac9a783596","observation_id":"43716b5e-600d-4159-baa4-684f864abb49","resolution":{"observed_at":"2026-08-05T15:54:13.189455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:12.647118Z","title":"Hamilton, Zhitao Ying, and Jure Leskovec","venue":null,"work_id":"ea6cbee9-0961-4097-b59c-60e9b03fed47","year":2017},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:52.315987Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:29a4e2d94519d1c35926484cd1ad12fa64bb5e642e45f6f67c85d5317138d483","observation_id":"44039cf1-bc86-4c56-8505-a1267e638287","resolution":{"observed_at":"2026-08-05T15:54:12.841788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00687","last_updated":"2021-02-25T02:06:27Z","snapshot_observed_at":"2026-08-09T05:17:43.055948Z","submitted_at":"2020-05-02T03:09:50Z","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00687","snapshot_observed_at":"2026-08-05T15:53:52.465158Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:52.465158Z"},"links":{"cited_paper":"/paper/2005.00687","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:b7b73289b21cf55bb8b82281edd54e72794d4f11ed48dec4096627ae4753401b","observation_id":"61baf7f2-f2ab-4736-b375-469c944253b7","resolution":{"observed_at":"2026-08-05T15:53:52.465158Z","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":"2026-08-05T15:54:12.228628Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"0b897ca3-d1c7-4cbf-b200-b6eef1ff9e78","year":2018},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:52.570976Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:30809abb1a62f556e8f360dd334a9d92e73b86a7e948dead72ea21c85f15270a","observation_id":"eb1ee335-1069-4d00-9056-6adc4fdb0e38","resolution":{"observed_at":"2026-08-05T15:54:12.448973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:11.902746Z","title":"Spectral graph pruning against over-squashing and over-smoothing","venue":null,"work_id":"7b41a1c5-8125-4de8-b0f7-e12ee3b098c6","year":2024},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:52.761893Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:bbbfba2d42be4a72dbace7e0e0077b7606643b8f52d742a70a106fd25229aa82","observation_id":"1225bdcf-24d7-4318-83b1-dcb2296be331","resolution":{"observed_at":"2026-08-05T15:54:12.056280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:11.499045Z","title":"Banerjee, and Guido Montufar","venue":null,"work_id":"690f06ac-41a9-4e73-a95f-09656dc34599","year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:52.893674Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:b6bf7b131760a8a972af4d29c204f97b2e43bc263bd4316f846bcc1c27cbdbba","observation_id":"e5166a8b-6823-4a7a-a47b-751e6d5eaf22","resolution":{"observed_at":"2026-08-05T15:54:11.668342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:11.102273Z","title":"Homophily influences ranking of minorities in social networks","venue":null,"work_id":"b418ea1f-8d50-4869-8d08-8e9985c0c884","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:53.061868Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:ae1350e2ad22bd1dda140d8e603957e7bf511ce09fab6fb004cccf9f3e17aded","observation_id":"40012159-d636-4321-b225-8beaad422dcc","resolution":{"observed_at":"2026-08-05T15:54:11.249025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:10.703691Z","title":"Not too little, not too much: a theoretical analysis of graph (over)smoothing","venue":null,"work_id":"99065018-6913-4cf9-afb5-1c2ee083351c","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:53.364689Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:e964dbb5ce99b880f3247a2cde708ec6d07c37650a884a64277c874361f9058f","observation_id":"0df95029-86fb-4698-bf9d-c9c900188647","resolution":{"observed_at":"2026-08-05T15:54:10.883676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.01868","last_updated":"2020-10-23T13:17:58Z","snapshot_observed_at":"2026-08-06T09:12:02.265165Z","submitted_at":"2020-06-02T18:36:19Z","title":"Convergence and Stability of Graph Convolutional Networks on Large Random Graphs","version":2},"cited_work":{"arxiv_id":"2006.01868","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.01868","snapshot_observed_at":"2026-08-05T15:54:00.570563Z","title":"Convergence and Stability of Graph Convolutional Networks on Large Random Graphs","venue":"stat.ML","work_id":"22498d48-0c76-4740-b054-a01d22b05ed7","year":2020},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:53.528985Z"},"links":{"cited_paper":"/paper/2006.01868","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:d4f6fdd82e1b4794cef1aea21ed6b092994d2fe896b8862bde9cfecfe8251622","observation_id":"13fd615d-cb1e-4f53-9f96-132233add437","resolution":{"observed_at":"2026-08-05T15:54:00.656704Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:10.297954Z","title":"Kipf and Max Welling","venue":null,"work_id":"b4510d19-0760-4e19-87e6-e453d45d83e7","year":2017},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:53.720397Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:1f297ef1a31ed04d88cbcdf23e986aeac30df0307e2977dddb1002be4aa9fb24","observation_id":"283f999e-b217-488e-aeee-01b0fafce216","resolution":{"observed_at":"2026-08-05T15:54:10.524633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.07501","last_updated":"2025-03-10T16:20:29Z","snapshot_observed_at":"2026-08-07T17:16:13.058054Z","submitted_at":"2025-03-10T16:20:29Z","title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.07501","snapshot_observed_at":"2026-08-05T15:53:53.901347Z","title":"Trustworthy machine learning via memorization and the granular long-tail: A survey on interactions, tradeoffs, and beyond, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:53.901347Z"},"links":{"cited_paper":"/paper/2503.07501","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:85dbdc91a5168c6861e3653660ff6882d2f96eb0254fa6f2e0a72b128987d07a","observation_id":"5cc8453d-7084-4837-ba77-3d783ddf0fe3","resolution":{"observed_at":"2026-08-05T15:53:53.901347Z","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":"2026-08-05T15:54:09.947233Z","title":"Towards bridging generalization and expressivity of graph neural networks, 2024","venue":null,"work_id":"526a83e5-8ac1-424d-8754-e7fe2fe6a60e","year":2024},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:54.041266Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:29142a89892f8456e56c6cac4499d3fd1e4eadaed95c336c5e7cacd5ecd03e6a","observation_id":"f1b371d0-c53f-40a9-b021-a2e916881856","resolution":{"observed_at":"2026-08-05T15:54:10.094950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09542","last_updated":"2023-07-18T18:36:29Z","snapshot_observed_at":"2026-08-01T15:25:14.552585Z","submitted_at":"2023-07-18T18:36:29Z","title":"Can Neural Network Memorization Be Localized?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09542","snapshot_observed_at":"2026-08-05T15:53:54.132399Z","title":"Can neural network memorization be localized? arXiv preprint arXiv:2307.09542, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:54.132399Z"},"links":{"cited_paper":"/paper/2307.09542","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:351da51c89fdc5c006ff5a49a9ca4f4d65db59ac58621e798c8d4de82a8ce8fb","observation_id":"dcac8884-8a25-412c-9418-120dac162732","resolution":{"observed_at":"2026-08-05T15:53:54.132399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:53:54.297775Z","title":"Automat- ing the construction of internet portals with machine learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:54.297775Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:922600bef2286b06b407a1572f95a693b4be708ecacfb4119a357b88338a2013","observation_id":"b7b5cb8a-4162-4b84-b9fb-81605edcd12f","resolution":{"observed_at":"2026-08-05T15:53:54.297775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:53:54.451673Z","title":"Schoenholz, Muratahan Aykol, Gowoon Cheon, and Ekin Dogus Cubuk","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:54.451673Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:4e9bd1a8159d0d6fa0b91a308dbcc397db2c023e26405ef0a72f30b13d9e6d8b","observation_id":"f99f9859-6ddc-4ec2-b567-adbc0d4f94bf","resolution":{"observed_at":"2026-08-05T15:53:54.451673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.08663","last_updated":"2020-07-16T21:46:33Z","snapshot_observed_at":"2026-08-06T13:06:20.395369Z","submitted_at":"2020-07-16T21:46:33Z","title":"TUDataset: A collection of benchmark datasets for learning with graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.08663","snapshot_observed_at":"2026-08-05T15:53:54.671282Z","title":"Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and Marion Neumann","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:54.671282Z"},"links":{"cited_paper":"/paper/2007.08663","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:eb31b0b17705b85c37a0e8f1c773939db265de716fa2e0c0b2fedc93bce03ce6","observation_id":"699c6722-b5cb-4898-88d1-77e0604a7850","resolution":{"observed_at":"2026-08-05T15:53:54.671282Z","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":"2026-08-05T15:54:09.557575Z","title":"Are GATs out of balance? In Thirty-seventh Conference on Neural Information Processing Systems, 2023","venue":null,"work_id":"67d3bff8-7f1f-4025-b943-17cefb78bd2b","year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:54.836744Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:c4aaca857dbee17c48cd2fada8dcc413de92fccfb7d0766fee26239098b4539e","observation_id":"f8a88748-6dd9-42ca-bd0c-2454feee6f87","resolution":{"observed_at":"2026-08-05T15:54:09.711553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:09.235231Z","title":"Query-driven active surveying for collective classification","venue":null,"work_id":"065bb6d9-dd4d-43c3-a489-98c2e7c6e76d","year":2012},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:55.038309Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:3bc7c2cc1497d82a82b60184ae28e0009bc6879fdcd2772001879f5205dc26d7","observation_id":"ffded4b2-efaa-4f3c-ba91-24d0e48e991a","resolution":{"observed_at":"2026-08-05T15:54:09.399298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:08.926611Z","title":"Revisiting over-smoothing and over-squashing using ollivier-ricci curvature, 2023","venue":null,"work_id":"aecb2a3a-7221-4c1e-897c-121427bb3f6c","year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:55.219756Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:07cf21e9cb024623348bcf1924727c85ea979d72882b5dc1a6bb67f27ef02ad3","observation_id":"3e0c7961-428e-44ca-90c4-df6c8e951015","resolution":{"observed_at":"2026-08-05T15:54:09.086150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:08.504672Z","title":"k-hop graph neural networks,","venue":null,"work_id":"844e8bc6-d46a-4e06-9566-80e6d28586b9","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:55.445264Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:10aa362aced3b4c117ba7dc08055e9f6302cc7a6f2c4aa58b7ec274f80370ad2","observation_id":"7c5db356-5921-49cd-a005-913b251abbae","resolution":{"observed_at":"2026-08-05T15:54:08.653590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:08.122096Z","title":"Geom-gcn: Geo- metric graph convolutional networks","venue":null,"work_id":"0d624c37-6adf-468b-ae3a-fb8d57eb6836","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:55.801261Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:332ebbac2643902aa1926131baa8dc3adc48491cee304d4f29f48a5885223bb5","observation_id":"389f3d85-6b83-4911-b2c5-9ac7e0f5e838","resolution":{"observed_at":"2026-08-05T15:54:08.343396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:07.346094Z","title":"Charac- terizing graph datasets for node classification: Homophily-heterophily dichotomy and be- yond","venue":null,"work_id":"0ca1462c-a0f7-4d07-a060-0cc758d8d6a7","year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:56.126280Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:49cadfa7ccc8d8722d377d62ca560d94e521af15a6ed7f469948ca23c4b38b2f","observation_id":"298621f7-5650-4af2-8d2a-b7c94c15d152","resolution":{"observed_at":"2026-08-05T15:54:07.549789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:06.968397Z","title":"A critical look at evaluation of gnns under heterophily: Are we really making progress? In The Eleventh International Conference on Learning Representations, 2023","venue":null,"work_id":"a846663f-46b1-420a-81ff-47519e843c53","year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:56.256820Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:73f99b1b05a920050d06b803f300ba126e1098ee465ca95a26b7ac67f19f5a25","observation_id":"255f522f-5aa8-4212-8b54-7d4e7e91e6df","resolution":{"observed_at":"2026-08-05T15:54:07.194125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:06.621029Z","title":"Recipe for a General, Powerful, Scalable Graph Transformer","venue":null,"work_id":"8e8b6587-87f3-4b0c-8aac-28846389d80a","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:56.388986Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:318173a9f7f63879c4b0c08410e2e451ed32da1b88f66ffee8854ac5d82ac237","observation_id":"71bdcd82-dee2-417a-b92b-343e7cdcc764","resolution":{"observed_at":"2026-08-05T15:54:06.769275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:53:56.493215Z","title":"Graph neural networks for materials science and chemistry","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:56.493215Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:b04f205692fc773e72a9bf7226d3f2198accf7ad251d0aa73650121de4229059","observation_id":"96345e88-9695-47d6-89de-741ad81afd7e","resolution":{"observed_at":"2026-08-05T15:53:56.493215Z","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":"2026-08-05T15:54:07.791274Z","title":null,"venue":null,"work_id":"9a055b1d-243b-4296-87ee-34d54052785d","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:55.979967Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:fe81fea8b47ec90d728bdc569c9b978bdd80bb965a44b4d3d4089a37cd491593","observation_id":"96157cbc-b8d2-4e66-a014-2a9fea372085","resolution":{"observed_at":"2026-08-05T15:54:07.953432Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:06.290985Z","title":"GNNs getting comfy: Com- munity and feature similarity guided rewiring","venue":null,"work_id":"65b307f7-8a79-4f15-a39f-50778c7d50ae","year":2025},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:56.709105Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:976526c6399bc27f57dcd75d088a4648320febb19dca55e213423760e64f5c36","observation_id":"6fd88c90-f208-412f-bd6e-004f8715756a","resolution":{"observed_at":"2026-08-05T15:54:06.416221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:53:56.825872Z","title":"The graph neural network model","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:56.825872Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:ceef9003a1f27cfaf16f2d6e9ed2269484d569863e9f1cbeb94e22d62a6b8b83","observation_id":"31ad7bd0-f81e-43dd-a65f-92f558cff1d1","resolution":{"observed_at":"2026-08-05T15:53:56.825872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:53:56.916261Z","title":"Collective classification in network data","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:56.916261Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:7b4c15e822355971e7cc2c128acb746016ab52153302ad7498631dc69349a255","observation_id":"07f606d3-e1ac-44a5-b63d-4f3b22d78d82","resolution":{"observed_at":"2026-08-05T15:53:56.916261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:53:57.035916Z","title":"Pitfalls of graph neural network evaluation, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:57.035916Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:8af70bc4bca1f51ae6ff363cd342a119ad0f0e7cf8bef1c6f5ec571f1988adae","observation_id":"aed1751b-b935-4f22-86ff-0f6fcf7a9e49","resolution":{"observed_at":"2026-08-05T15:53:57.035916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.13021","last_updated":"2021-03-21T22:05:08Z","snapshot_observed_at":"2026-08-10T06:46:48.009859Z","submitted_at":"2019-09-28T04:13:33Z","title":"Multi-scale Attributed Node Embedding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.13021","snapshot_observed_at":"2026-08-05T15:53:56.575424Z","title":"Multi-scale attributed node embedding","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:56.575424Z"},"links":{"cited_paper":"/paper/1909.13021","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:8c8d03f2ad3a02f77fd314b8f186f5123cedb923841453d0c882d80012fa6ccb","observation_id":"1b8f7a16-6c1a-4ff8-817c-93f83dbdd0a9","resolution":{"observed_at":"2026-08-05T15:53:56.575424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:53:57.272780Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:57.272780Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:f20f8a4f6848d5d113413ab29b33d3e906589c77816bab464b926797973c0267","observation_id":"0e5b8678-65a7-492e-9fb8-74ad0f2c2f1c","resolution":{"observed_at":"2026-08-05T15:53:57.272780Z","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":"2026-08-05T15:54:05.829164Z","title":"Towards understanding generalization of graph neural networks","venue":null,"work_id":"7b5e15a3-76a6-4c1c-9717-6d0b7be8e7de","year":2023},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:57.376107Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:fc1d1173e48de2aa13e6f378e75373b3079d47b2aa5f1aaf06084325a7c01a44","observation_id":"4ad4f228-bd30-4970-aa6f-406ff446aa63","resolution":{"observed_at":"2026-08-05T15:54:06.096498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:05.392634Z","title":"Bronstein","venue":null,"work_id":"330fd6ba-b746-4e1d-b4b5-d27dab4f7ecd","year":2022},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:57.493234Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:99116919e285638a5267f2d5b7e9d90a334e4774b2b2b59e92cf04af8109dbf5","observation_id":"51850cc4-92e8-4db4-8cc0-04afdc54bee5","resolution":{"observed_at":"2026-08-05T15:54:05.608901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:05.006101Z","title":"Graph Attention Networks","venue":null,"work_id":"9ee5d9e5-6a27-4f06-bc9a-380192e9a99b","year":2018},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:57.595083Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:ca9dc1329727f7ed91b6b9bd1a464baf43ce411b8e945dbd2479cd1bf0465724","observation_id":"2b2cea8c-f514-4242-a8ae-c2b759b8ce1b","resolution":{"observed_at":"2026-08-05T15:54:05.199623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:53:57.140213Z","title":"Graph neural networks in particle physics","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:57.140213Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:2e77c1e5d36292ce2f1470ba384e48f4234fcc16444e19056f9af05fc6216379","observation_id":"8b903f9f-d5b4-4ca1-b1b1-224c17a21c4a","resolution":{"observed_at":"2026-08-05T15:53:57.140213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05225","last_updated":"2025-06-06T22:52:34Z","snapshot_observed_at":"2026-08-03T17:36:28.918965Z","submitted_at":"2024-06-07T19:25:02Z","title":"A Manifold Perspective on the Statistical Generalization of Graph Neural Networks","version":6},"cited_work":{"arxiv_id":"2406.05225","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.05225","snapshot_observed_at":"2026-08-05T15:53:59.792363Z","title":"A Manifold Perspective on the Statistical Generalization of Graph Neural Networks","venue":"cs.LG","work_id":"03fa3f17-7d2e-4542-b662-508597b53f58","year":2024},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:57.949017Z"},"links":{"cited_paper":"/paper/2406.05225","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:4975300dca6741e3d8d3915d20c5c3a92f2a92fa6e33b9468abd580295ed4a05","observation_id":"a1a0e9b9-8abf-43b8-be62-120bb45be956","resolution":{"observed_at":"2026-08-05T15:53:59.900314Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:04.326263Z","title":"Simplifying graph convolutional networks","venue":null,"work_id":"5a90aeeb-29da-46f2-97d8-9f270ae4a47c","year":2019},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:58.216533Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:b506acc5dc66457c9f376d0b6ac95afb45d1136e2935b852f6fbb09e639078d3","observation_id":"5647f6ca-0b5c-454a-a883-50296a25b3a6","resolution":{"observed_at":"2026-08-05T15:54:04.483379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:04.035118Z","title":"How graph neural networks learn: Lessons from training dynamics in function space, 2024","venue":null,"work_id":"2f4211eb-6196-414c-9b7d-593679756820","year":2024},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:58.379399Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:0192768ec2293b5f0e6fc206b33680dd33426d7e08dbda7fc7749c977e973277","observation_id":"2e83f67b-8f99-40c9-8204-6ad84e385750","resolution":{"observed_at":"2026-08-05T15:54:04.168047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:03.667165Z","title":"Understanding deep learning requires rethinking generalization","venue":null,"work_id":"d0e0507e-8777-4845-8478-ad20dc27efe6","year":2017},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:58.600810Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:139e24ee8f1eeb630ec1bb9152e517f27b73a6c1ca30ce104745141ad34f4267","observation_id":"79ba0b58-b477-4ff5-968b-7fb503f086e9","resolution":{"observed_at":"2026-08-05T15:54:03.820739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:04.703306Z","title":"Memorization in self-supervised learning improves downstream generalization","venue":null,"work_id":"f73bc923-5913-42df-aa72-66864333b7fd","year":2024},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:57.776819Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:7905973e2714f1e3fe845eccb415e5497c0b4c11227655736a4a44ef617153cc","observation_id":"a08c7bd9-0559-4894-89b5-d44820b377f8","resolution":{"observed_at":"2026-08-05T15:54:04.842169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:03.360369Z","title":"Be- yond homophily in graph neural networks: Current limitations and effective designs","venue":null,"work_id":"985ac61c-4b0d-40e4-b42e-c51e4429efb0","year":2020},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:58.785264Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:5911099d8d30fb5e953f0f346ffd6c8f7532fae2f8629234f50ac62afe48b185","observation_id":"f42514a7-9365-41eb-86e0-322a8f0cf943","resolution":{"observed_at":"2026-08-05T15:54:03.493496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:02.976109Z","title":null,"venue":null,"work_id":"30c42a46-22df-42e4-b3cf-5cf4da5031e1","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:58.973355Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:ab82bdceecc2ede99c1d776aabe10ecc62167db74360722a4655a8a7e1f2f03f","observation_id":"e577da71-9499-4ab5-adc5-f0021cdf1a1b","resolution":{"observed_at":"2026-08-05T15:54:03.138915Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:02.591191Z","title":null,"venue":null,"work_id":"56cf07ef-cf5d-4998-96ac-0bfc8533ec0c","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:59.168344Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:71d6fdb42b309da18c81e6d98f0438e5fc7d5b673914912a25546c3e87f4f767","observation_id":"c02dcdf5-beab-4cd5-bbc8-6324c46e7b02","resolution":{"observed_at":"2026-08-05T15:54:02.760978Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:02.161476Z","title":"Inequality 10 states that γ must be greater than or equal to this large angle (δ − ϵ)","venue":null,"work_id":"f7f90988-fe82-46b5-8db0-162aca38f854","year":1993},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:59.316219Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:7f9f8e5347488ce76ba26a5cf182c0e11172802afd3ca51e33373a50795bdf7e","observation_id":"bf839a4a-4644-4b89-b4bc-f4399689689c","resolution":{"observed_at":"2026-08-05T15:54:02.387902Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:01.766213Z","title":"Our theoretical results in Section 4 demonstrate that one of the key factors influencing memorization in GNNs is the graph homophily","venue":null,"work_id":"1cb9e1c6-1b34-478a-b4e5-90fbf1da2857","year":2029},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:59.520306Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:66b8acfd56bece7c52dc4bad09cbda7463745af0d164d0cb07953527c12eae44","observation_id":"3375b53a-6a4c-4c6e-88c0-933df55386f4","resolution":{"observed_at":"2026-08-05T15:54:01.925640Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:15.713239Z","title":null,"venue":null,"work_id":"31325477-74c6-4b13-971d-42dc41711bc3","year":2001},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":2001,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:50.215222Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:d541728bc7dbc458f15c74cdc26ab07352dbd5a9bb4b1e94518f71928241ac6e","observation_id":"5f08ca9b-ceed-4c83-befe-26773f38c018","resolution":{"observed_at":"2026-08-05T15:54:15.853047Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:54:13.391816Z","title":"URL https://proceedings.mlr.press/v9/glorot10a.html","venue":null,"work_id":"8929e09f-a455-4995-a25e-9482cf81459d","year":null},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:51.800978Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:aa927dad7f20811adad2e05f5d4e2c9d7964bb7eae5ad260218145b516c51cc9","observation_id":"d9470b05-5a76-4c75-b610-b59cde8f8470","resolution":{"observed_at":"2026-08-05T15:54:13.578059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T15:53:53.230001Z","title":"doi: 10.1038/s41598-018-29405-7","venue":null,"work_id":null,"year":2045},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:53.230001Z"},"links":{"citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:e456c5464918e4ff7c5deb9ac3176641c860623914ce6ff7e93145f4f3bfb320","observation_id":"47f9c5ff-09b4-4383-83f2-708f6401f4d8","resolution":{"observed_at":"2026-08-05T15:53:53.230001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.06051","last_updated":"2020-08-09T21:50:43Z","snapshot_observed_at":"2026-08-01T07:52:57.052480Z","submitted_at":"2019-07-13T11:31:57Z","title":"k-hop Graph Neural Networks","version":2},"cited_work":{"arxiv_id":"1907.06051","doi":null,"metadata_source":"pith","pith_arxiv_id":"1907.06051","snapshot_observed_at":"2026-08-05T15:54:00.262149Z","title":"k-hop Graph Neural Networks","venue":"stat.ML","work_id":"ccbe5648-65e7-4576-834c-ca08c0155f79","year":2019},"citing_paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-05T15:53:55.659437Z"},"links":{"cited_paper":"/paper/1907.06051","citing_paper":"/paper/2508.19352"},"observation_digest":"sha256:16d95013919999f009de47318e538276b7694a63cded3d1fd8dad0c039267484","observation_id":"44bb15bb-e1f3-41ca-8ff6-72f2b5db5ee6","resolution":{"observed_at":"2026-08-05T15:54:00.366113Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.19352","last_updated":"2025-09-03T08:38:08Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T20:31:53.352101Z","submitted_at":"2025-08-26T18:25:54Z","title":"Memorization in Graph Neural Networks"},"reference_resolution":{"displayed":77,"state_counts":{"malformed_identifier":2,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":27,"verified_exact":4,"verified_fuzzy":43},"total_outbound_references":77},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 0 inbound Pith citation observations for arXiv:2508.19352."}