{"as_of":"2026-08-18T14:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fcb72179c921c3cfec54d2105db8b349a704961f211aa5c2cb3b4c9607fbb80f","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:35:01.002065Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.16110/citation-record","integrity":"/paper/2506.16110/integrity","json":"/paper/2506.16110/citation-record.json","paper":"/paper/2506.16110"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:00.782927Z","title":"and Yahav, E","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.782927Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:0aa802e961b995d497fde404b4018af4efa42a2304055c21c16ef4b599181d0c","observation_id":"0d32dcae-93ba-4e60-bc29-6052d2cd1301","resolution":{"observed_at":"2026-08-15T19:35:00.782927Z","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":"2026-08-15T19:35:01.703034Z","title":"Delaunay graph: Addressing over-squashing and over-smoothing using delaunay triangulation","venue":null,"work_id":"02cab274-e29f-42ec-a2c2-d2f2ed1dc58f","year":2024},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.787719Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:180e4e82db521b4720d4bbcce7da65e840c73d7f621e0d56dbf08ee1dcba040c","observation_id":"13ad6199-53d2-48c4-8d4b-2b00f6f8722c","resolution":{"observed_at":"2026-08-15T19:35:01.707577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.690803Z","title":"M., and Giovanni, F","venue":null,"work_id":"57412d40-b3be-465c-809b-bc3d7c400f29","year":2024},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.791999Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:6c3fe5e91fe96174a17f6c11f850514d19eae403f93fffbb0cc98a2665c7d3fd","observation_id":"16b63962-f380-4551-9a79-52f9ac6d9729","resolution":{"observed_at":"2026-08-15T19:35:01.694842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.678505Z","title":"W., Hamrick, J","venue":null,"work_id":"9dafe339-3b6c-4792-a09d-be065050bef9","year":2018},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.796640Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:696ed44a5d63182d06a017dc16a3090605ce551d8c7c206834c23562a84a4a26","observation_id":"0d3da3b7-6f75-4e70-97d9-82915bfefaa8","resolution":{"observed_at":"2026-08-15T19:35:01.682524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.665812Z","title":null,"venue":null,"work_id":"c43e1fc2-d5fd-4fdb-8785-c4f849e9c843","year":1996},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.801049Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:1612cdf7faa0130681768a1ec9b4db3bc73faa808ba7dfbecff364eb1a69147f","observation_id":"fdf2e94b-609c-4492-9710-cafdc0e52954","resolution":{"observed_at":"2026-08-15T19:35:01.669845Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.653113Z","title":"Understanding oversquashing in gnns through the lens of effective resistance","venue":null,"work_id":"4f55ba87-5777-4f84-946a-876820ecdf16","year":2023},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.805222Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:c10ddc3fa383dfd53a01add4a3bfe1ecedfd2fe5d74f0b26650c06cb46bdee44","observation_id":"c454388f-61ba-4e21-a202-77f6ab04c674","resolution":{"observed_at":"2026-08-15T19:35:01.657342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.640586Z","title":"\\\" U ber ein paradoxon aus der verkehrsplanung","venue":null,"work_id":"08e533ab-7ee8-4a55-b494-a7c220584469","year":1968},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.809834Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:d14dac261596ec8c795f889f7eafb11a0084920629345bd91d32133a936307eb","observation_id":"0dbb0ef2-7472-4e3f-92ea-24e25718ceb0","resolution":{"observed_at":"2026-08-15T19:35:01.644730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.628139Z","title":"Measuring and relieving the over-smoothing problem for graph neural networks from the topological view","venue":null,"work_id":"e44133ef-679f-4f23-89b7-66fc43722eb3","year":2020},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.814049Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:adf1d2078422a3c47b715d9ccf3c58e3a184902f650c8adfdc0848bafeddbf0c","observation_id":"8524a16c-0423-4d8b-8d89-d9e248219d7b","resolution":{"observed_at":"2026-08-15T19:35:01.632184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.615687Z","title":"Simple and deep graph convolutional networks","venue":null,"work_id":"bdcc3fd0-15dc-42b1-9302-6d08f6732bb1","year":2020},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.819156Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:7120bd5124e372ad51403781e03f9381d50419197e31b71a7b52734ff6da6b02","observation_id":"5252cf81-d732-4be7-9d99-fd564b20a896","resolution":{"observed_at":"2026-08-15T19:35:01.619738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.601784Z","title":"PANDA: expanded width-aware message passing beyond rewiring","venue":null,"work_id":"2f7332cd-ad9b-43fa-9596-9fd6c85f3ca6","year":2024},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.823176Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:849ab295f65596a78f963ca3e3ea94a05a5395c221043e86ad547852d99e226d","observation_id":"2d6dcf04-b73f-4452-8589-cc1dba5806ee","resolution":{"observed_at":"2026-08-15T19:35:01.607020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07966","last_updated":"2023-11-14T07:44:46Z","snapshot_observed_at":"2026-08-18T08:23:18.968932Z","submitted_at":"2023-11-14T07:44:46Z","title":"Higher-Order Expander Graph Propagation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07966","snapshot_observed_at":"2026-08-15T19:35:00.827390Z","title":"and He, Y","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.827390Z"},"links":{"cited_paper":"/paper/2311.07966","citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:65e7d166bf7947aa837a34e14bc3e7b52c03b82f3567a28a6f1ffdf0040a5bb8","observation_id":"6b90ffdb-af62-4c5d-82f3-0782725f8dc0","resolution":{"observed_at":"2026-08-15T19:35:00.827390Z","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":"2026-08-15T19:35:01.589231Z","title":null,"venue":null,"work_id":"4d70b277-e4a4-4bd3-b5d7-8b3374837227","year":1997},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.831933Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:7b1d6654b2444bdf24a6c4fdc2ed7e7997b2647e6177cb8cce97a9185991e20a","observation_id":"320ee4d8-ad00-4be7-bf00-474993a47cbe","resolution":{"observed_at":"2026-08-15T19:35:01.593264Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.574807Z","title":"Expander graph propagation","venue":null,"work_id":"4a5749d5-a58c-48c0-9df5-1abad6bdc449","year":2022},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.835892Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:78e24447315a32f2b56073b55d0002580985851213f6f3100fe420aae4ca6371","observation_id":"bc64ae5b-b7b5-4dad-be68-a8c742e0804c","resolution":{"observed_at":"2026-08-15T19:35:01.579378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.560572Z","title":"Graph Theory, 4th Edition, volume 173 of Graduate texts in mathematics","venue":null,"work_id":"83f952b3-47df-49b1-bfc2-246ac04cc036","year":2012},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.839965Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:cd01978b832d1aba1d9f1be50af6b15f1abc6316cb8f78a800239ac70b50a39f","observation_id":"e29e20c4-c860-49ab-ace2-45f5bbcadf49","resolution":{"observed_at":"2026-08-15T19:35:01.564826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.547840Z","title":null,"venue":null,"work_id":"c736458e-3714-4753-92fd-e55b5a4818c1","year":1984},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.844092Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:f8e0e0f9221df4bc0ccc70444df1070b88906db007651e02392662c85bc96bfe","observation_id":"2f214ddb-be2b-4f92-a83e-be57d9e47461","resolution":{"observed_at":"2026-08-15T19:35:01.551891Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.534113Z","title":"and Weber, M","venue":null,"work_id":"7f461d56-6e5b-4090-a221-f91ad07ac6c3","year":2023},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.847949Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:0e1e27699e0d9bdac8cea273986b7752a172191ad7554cad706138a5bd4f6b1a","observation_id":"24963d6f-0e27-4052-bf8d-5fd034565518","resolution":{"observed_at":"2026-08-15T19:35:01.538882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.521079Z","title":"Algebraic connectivity of graphs","venue":null,"work_id":"f57b5fb5-c031-4103-a123-977d1b59e6a8","year":1973},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.851850Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:e2d990417e9c165416e0ebfd10d47dc87730f645dae739a72d715317ab66ad39","observation_id":"f231902e-3833-4b1c-925a-b1fa39e1c4b1","resolution":{"observed_at":"2026-08-15T19:35:01.525311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.507969Z","title":"M., and Ceylan, \\.I","venue":null,"work_id":"9bb7ef2c-be60-4fea-853e-f5f801e8cc46","year":2024},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.856070Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:01be17b55a0e1441e83beda9ef69efbab9e4e68ad10120e0fe9e5f9dc8002f43","observation_id":"176dd100-5308-4f2f-acc1-79c8b57dce1d","resolution":{"observed_at":"2026-08-15T19:35:01.512140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:00.860311Z","title":"S., Riley, P","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.860311Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:141c96347926f2c86bd54761e248e1fa192fa597b3a9e75687f444b20ee411e7","observation_id":"dde9c182-1de6-423d-964a-7e4926b77533","resolution":{"observed_at":"2026-08-15T19:35:00.860311Z","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":"2026-08-15T19:35:01.486590Z","title":"D., Giusti, L., Barbero, F., Luise, G., Lio, P., and Bronstein, M","venue":null,"work_id":"762c9c07-00c5-4dc8-9a70-f128d0d1675c","year":2023},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.864603Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:27b4591561ab292527dab0f0acdcefc539720e537c4ad054b067907d1b050ef0","observation_id":"4da1a6b6-77f5-403f-84fa-522ebbf342f3","resolution":{"observed_at":"2026-08-15T19:35:01.490819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.473607Z","title":"Graph Theory","venue":null,"work_id":"d6a6aa9c-5dc4-43ab-a15e-309ce78a351d","year":1969},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.868647Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:1517be1e08bc17ee37de3127a82730ec62ca2f3143b621a15f825fea27786a8d","observation_id":"8e9a58bf-475d-435a-b534-74ba6ba07374","resolution":{"observed_at":"2026-08-15T19:35:01.477639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.04612","last_updated":"2024-10-30T14:17:02Z","snapshot_observed_at":"2026-08-16T14:03:08.460071Z","submitted_at":"2024-04-06T12:40:21Z","title":"Spectral Graph Pruning Against Over-Squashing and Over-Smoothing","version":2},"cited_work":{"arxiv_id":"2404.04612","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.04612","snapshot_observed_at":"2026-08-15T19:35:01.075556Z","title":"Spectral Graph Pruning Against Over-Squashing and Over-Smoothing","venue":"cs.LG","work_id":"d34811bb-e36c-494c-9883-071614e47854","year":2024},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.872757Z"},"links":{"cited_paper":"/paper/2404.04612","citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:0c443e03e3a6e6797623a1a17d5232c0422cfc15e532195b7a7772196193433a","observation_id":"d0e373af-9cc3-4845-b8c7-1737b05d8ae5","resolution":{"observed_at":"2026-08-15T19:35:01.080124Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.460297Z","title":"K., and Mont \\' u far, G","venue":null,"work_id":"fb2080ff-2f21-4606-97eb-4805dd1eef9e","year":2023},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.877103Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:78609237a047d9d15d0513aaf56f13d54eb88d1ddc4dc44dfddd4623b8e755e4","observation_id":"c315f964-c148-4bd3-b6c0-3be7133b695b","resolution":{"observed_at":"2026-08-15T19:35:01.464428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:00.881203Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.881203Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:abfe6e69dfd7c8d3b1a7a3d7369a7f3fcf7bb14b860dca0bcdaadd221ba02cb0","observation_id":"1c3f2722-2b94-4b83-a8be-080f6704797e","resolution":{"observed_at":"2026-08-15T19:35:00.881203Z","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":"2026-08-15T19:35:01.438646Z","title":"Y., Nguyen, A","venue":null,"work_id":"d7e41896-153d-4fe2-bfc9-75f4d7e9f927","year":2024},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.884924Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:6bd2e4210bc1a0360be46ccc7242150aee426554f4ec0e2ffca857ea3d296b4b","observation_id":"4eb5b1a1-180d-412d-9ecc-a0c910aa388f","resolution":{"observed_at":"2026-08-15T19:35:01.442943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.425693Z","title":"L., and Peng, R","venue":null,"work_id":"b1b8905b-69cb-40d0-b39c-5b68e74375bd","year":2014},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.888915Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:ddcfc99cd26cc3c44e6f2e57a09fe705a57eb0b73fc8844a6ad2e5f79c5f50ad","observation_id":"64349c45-9fc0-49bc-b10a-c7b14e51de7f","resolution":{"observed_at":"2026-08-15T19:35:01.429917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:00.892669Z","title":"L., L \\' e tourneau, V., and Tossou, P","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.892669Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:05c5909643f167feb4910ed2a411804af4d07ebc47b39484dfe2e91d7489eb16","observation_id":"f1071176-4731-431b-8f2e-5b4278410406","resolution":{"observed_at":"2026-08-15T19:35:00.892669Z","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":"2026-08-15T19:35:00.896888Z","title":"Crafting papers on machine learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.896888Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:898be048e089904fd22659d8aee2472fe52e456efbafe3914b418f8b596c223f","observation_id":"d7e5d4c5-e843-40a1-93f9-6dc12461978a","resolution":{"observed_at":"2026-08-15T19:35:00.896888Z","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":"2026-08-15T19:35:01.394669Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":"82cdafdb-5580-4b8b-a1db-bd10ea123044","year":2018},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.900834Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:6fca487de313b92e9580e42911b0861245215c89dffcaa9f0e94fa915e1789f1","observation_id":"a34081b6-f80b-44a9-b70b-e5b59e3a83c4","resolution":{"observed_at":"2026-08-15T19:35:01.399005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.381228Z","title":"Predicting global label relationship matrix for graph neural networks under heterophily","venue":null,"work_id":"715f51f8-f28c-47e2-8d3d-6e29a8c31563","year":2023},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.904712Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:325c89e99e7b539db6398afac9162cbfe9a0fcdef606796ff5a27daf62de8926","observation_id":"1d88e272-8710-48b3-85da-8393864843e2","resolution":{"observed_at":"2026-08-15T19:35:01.385444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.366801Z","title":"Tackling long-tailed distribution issue in graph neural networks via normalization","venue":null,"work_id":"c0d4e44d-78de-4d38-b588-ed3a380c3afe","year":2023},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.908645Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:058ed3f085e0dd24239c9b045e22c3bab4605d9a9e861e3ed323b2709b09c97d","observation_id":"33106a75-0368-4bae-af46-bd2832e4354a","resolution":{"observed_at":"2026-08-15T19:35:01.371349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.352000Z","title":"Sign is not a remedy: Multiset-to-multiset message passing for learning on heterophilic graphs","venue":null,"work_id":"99c3830a-4871-4835-bcbe-c5f31ce202a0","year":2024},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.912656Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:eb50f0f0fe8a907b35d3a528638802d909809ad13d7ef2478fa1ecd7db9f36af","observation_id":"f9e434c8-b8d3-4496-b1e1-481e8a23329b","resolution":{"observed_at":"2026-08-15T19:35:01.356975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.338668Z","title":"Revisiting heterophily for graph neural networks","venue":null,"work_id":"4ff47734-cdb1-4f12-811f-656227c94b05","year":2022},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.916719Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:433be3df5a6766d8309efc6f8f61ef7c7f288562ce1bd426f909973267084bf6","observation_id":"f7084575-b2f1-443b-8e88-f3ea42d083db","resolution":{"observed_at":"2026-08-15T19:35:01.343174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.325324Z","title":"Learning to drop: Robust graph neural network via topological denoising","venue":null,"work_id":"c7deb8d4-100e-464a-92f6-5216acaf7487","year":2021},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.920620Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:1f5c6e3b5ba32162c1341f487e5cecb05e9a88f6b7fc988872ec8f8e98e04f51","observation_id":"51f055bb-ac3f-4d31-9dfe-ad406bab9cfb","resolution":{"observed_at":"2026-08-15T19:35:01.329651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.312331Z","title":"L., Lenssen, J","venue":null,"work_id":"d959e563-2092-4d1f-8867-441c0eb820fd","year":2019},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.924409Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:66f54e59bc61269a2fcee232320a603d0b33a4addf5d8caf453adf783532a62e","observation_id":"140d0299-689f-41b5-a8bb-274d36f98642","resolution":{"observed_at":"2026-08-15T19:35:01.316376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.298787Z","title":"M., Nguyen, V","venue":null,"work_id":"bdae175d-3dc4-43fa-a134-5d3e7fcb2671","year":2023},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.928644Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:89769860427c6167db51c1406cd236d5fd4b10d4b992614d39400cdf22d7a714","observation_id":"fb5f1eeb-8e05-45f9-8073-2ad4b603712c","resolution":{"observed_at":"2026-08-15T19:35:01.303278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:00.932687Z","title":"C., Lei, Y., and Yang, B","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.932687Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:aa492d7428f808425a0559709b599e118df481318c724e07d5296c0eb02a78f7","observation_id":"cc356093-c086-458c-9b7d-cb8847dc6f3b","resolution":{"observed_at":"2026-08-15T19:35:00.932687Z","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":"2026-08-15T19:35:01.275162Z","title":"Local algorithms for estimating effective resistance","venue":null,"work_id":"d4cd55d5-a162-4e9a-b71a-065fcf7be4aa","year":2021},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.936598Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:d904bcc925edc4d1815b670f7a6a628ba74bdcbea1ba116d30db321d0eec6022","observation_id":"a2ee3751-4bc6-466c-be3a-245868b39de9","resolution":{"observed_at":"2026-08-15T19:35:01.279869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.260811Z","title":"V., Niepert, M., and Morris, C","venue":null,"work_id":"5a01d925-bdf2-40d1-ba39-e43273aba7d0","year":2024},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.940492Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:10e3248897ec58d29996f8b67762e2e5a4dac5512a966770d6b8ca332e6ec490","observation_id":"b1cce866-fdce-4282-ad5e-01963019f20b","resolution":{"observed_at":"2026-08-15T19:35:01.264935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.247681Z","title":"Multi-scale attributed node embedding","venue":null,"work_id":"e62f0930-8ca1-4c75-b378-e7bfd4a90b13","year":2021},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.944196Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:e0c9e57624d02f3afa913b9133f410890d314d339f45df79d629fd824c084442","observation_id":"1098c422-1bc4-4d56-824c-f0f49d9055ff","resolution":{"observed_at":"2026-08-15T19:35:01.251786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.234207Z","title":"T., Merel, J., Riedmiller, M., Hadsell, R., and Battaglia, P","venue":null,"work_id":"cec99617-73c8-4da4-b2a2-d003862b326b","year":2018},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.948299Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:b197e686f9a648442128b84e6637a9ef0490600aacbb2baebeea2b550b766ad0","observation_id":"d3922f5c-3e5c-473c-a3da-54b2c2193858","resolution":{"observed_at":"2026-08-15T19:35:01.238862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.221014Z","title":"C., Hagenbuchner, M., and Monfardini, G","venue":null,"work_id":"2d1e07e5-d822-4b91-b966-3d16c92d7ad9","year":2009},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.952387Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:9d12d59e3302d699a904d4fabffac5ab77ec54be2244aba94183d0caff510fb5","observation_id":"860c292e-85f0-4e65-bd19-2370e3af06d8","resolution":{"observed_at":"2026-08-15T19:35:01.225635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1307.5675","last_updated":"2013-07-22T12:19:05Z","snapshot_observed_at":"2026-08-15T00:09:34.704059Z","submitted_at":"2013-07-22T12:19:05Z","title":"Models, Entropy and Information of Temporal Social Networks","version":1},"cited_work":{"arxiv_id":"1307.5675","doi":null,"metadata_source":"pith","pith_arxiv_id":"1307.5675","snapshot_observed_at":"2026-08-15T19:35:01.057044Z","title":"Models, Entropy and Information of Temporal Social Networks","venue":"physics.soc-ph","work_id":"3980b2ad-016b-464b-9f70-70b1060f13e4","year":2013},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.956471Z"},"links":{"cited_paper":"/paper/1307.5675","citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:099816868ea5531bbbb7223dee2eae6e8a3796b0fd8966e4d52bb6f44c1fa43a","observation_id":"f5662233-bddb-4926-b1a1-cbf6d3eea48a","resolution":{"observed_at":"2026-08-15T19:35:01.061519Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.208136Z","title":null,"venue":null,"work_id":"1ab3c2de-bdee-488a-89ca-f8d9a05d2a2e","year":2008},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.960961Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:c29cf504d4c900cfa32d7e4974a9b41b76f14ff9ff1ecb70407f2e67d6ca290b","observation_id":"aae0827b-7397-4eb8-ba53-ece3eea1b5fa","resolution":{"observed_at":"2026-08-15T19:35:01.212334Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:00.965009Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.965009Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:d27562db3a163b3bd6b57b9cd4226e712a53ff6ea0e34311ab8ea0f34260ba9b","observation_id":"04860d57-e647-435f-9b72-fce0125b9299","resolution":{"observed_at":"2026-08-15T19:35:00.965009Z","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":"2026-08-15T19:35:01.186333Z","title":"D., Chamberlain, B","venue":null,"work_id":"39f1963e-a2c5-48a0-ab61-d2ab3ee52109","year":2022},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.969044Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:d660c30e3286aefef2ae5e85c5dfe0a0f30677e65924b1b931b994204ed9a807","observation_id":"6239e9ff-f5fc-43e4-8f12-904e52080c59","resolution":{"observed_at":"2026-08-15T19:35:01.190788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06538","last_updated":"2022-12-13T12:42:35Z","snapshot_observed_at":"2026-08-16T16:09:01.728412Z","submitted_at":"2022-12-13T12:42:35Z","title":"Leave Graphs Alone: Addressing Over-Squashing without Rewiring","version":1},"cited_work":{"arxiv_id":"2212.06538","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.06538","snapshot_observed_at":"2026-08-15T19:35:01.036340Z","title":"Leave Graphs Alone: Addressing Over-Squashing without Rewiring","venue":"cs.LG","work_id":"29f49ec2-cccc-4f4f-a404-854b0d610beb","year":2022},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.972977Z"},"links":{"cited_paper":"/paper/2212.06538","citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:190198e4c5c2d3f86ee60f52643dcabb9fef7a1cfdd82ac31134b3d65e7b3168","observation_id":"0fe72965-24cc-4e53-848c-7e08a77e9cf9","resolution":{"observed_at":"2026-08-15T19:35:01.042950Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.172799Z","title":"N., and Welling, M","venue":null,"work_id":"f52f8740-922c-4795-a5d6-89d136ac6f51","year":2017},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.977222Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:9d40c47b58d58e5f5ded92bc639e0dcfef84acd44b72e21cd8471eab63adfcf0","observation_id":"3d606120-4cd0-4bec-9fea-d7674c6478f5","resolution":{"observed_at":"2026-08-15T19:35:01.176908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.159269Z","title":"Graph attention networks","venue":null,"work_id":"2fd2f2c3-aacf-4e80-b46e-0ebbfcaa78c2","year":2018},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.981430Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:551f5eb6aee1a2ba10068ea81436c776cb54c3837ec1d96fbca9849b1c15d622","observation_id":"6b6c81ee-558a-45ce-ba5b-d31f17310685","resolution":{"observed_at":"2026-08-15T19:35:01.163670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:00.985468Z","title":"How powerful are graph neural networks? In ICLR, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.985468Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:2f0819f41f422cc06be7b6bfde995c75d59b3896a2e81b6386fdb3e64e7f4efd","observation_id":"1752ac13-288d-4c9c-9bb7-1fd952784818","resolution":{"observed_at":"2026-08-15T19:35:00.985468Z","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":"2026-08-15T19:35:01.135735Z","title":"W., and Salakhutdinov, R","venue":null,"work_id":"8aeb0ace-11af-4742-8db2-ae70c7372274","year":2016},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.989627Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:2e49759eef17d74bcd0ea455ee5c0bcd332629372c5729370c46008f649b3378","observation_id":"74cd8837-e4dd-43bd-ad63-e9ac8156ba87","resolution":{"observed_at":"2026-08-15T19:35:01.140783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:00.993939Z","title":"Do transformers really perform badly for graph representation? In NeurIPS, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.993939Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:f399355ca60d6b94d760288b2b6c3c0656f075d5a0e9f73d2adfded11aa9da6b","observation_id":"aa5b59eb-3150-4e17-b844-a634bdf14672","resolution":{"observed_at":"2026-08-15T19:35:00.993939Z","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":"2026-08-15T19:35:01.112182Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","venue":null,"work_id":"43e19721-1af4-4fd1-821e-bc826d9fd313","year":2020},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:00.998011Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:4600a5f3261ffbb11ed309761d59f0fdbd2696c68f319e70d5d1f71e7e1ff4a2","observation_id":"ead29531-7063-4f6d-98e3-73f0d67d1a54","resolution":{"observed_at":"2026-08-15T19:35:01.117675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:35:01.002065Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T19:35:01.002065Z"},"links":{"citing_paper":"/paper/2506.16110"},"observation_digest":"sha256:03d05640d12a483cf5ea8ea9d1428c39a71aaad2560fa6b120f44fc601f88970","observation_id":"207c8771-9732-409b-9b6c-969b1af35fa6","resolution":{"observed_at":"2026-08-15T19:35:01.002065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.16110","last_updated":"2025-06-19T08:01:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T15:43:34.564895Z","submitted_at":"2025-06-19T08:01:00Z","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":3,"verified_fuzzy":36},"total_outbound_references":54},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2506.16110."}