{"as_of":"2026-08-21T13:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:72932d49d000751d78a23e169684192533f5601ff25d2b421ef8d15e6c8cc9ac","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:04:08.203440Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.11346/citation-record","integrity":"/paper/2505.11346/integrity","json":"/paper/2505.11346/citation-record.json","paper":"/paper/2505.11346"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:04:09.051527Z","title":"Beyond low-frequency information in graph convolutional networks","venue":null,"work_id":"040dfe7c-76f2-4f64-a4b5-c52b08f4ece2","year":2021},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:07.962993Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:43741cee9933302f7dcf1e4a30388eeb05882379ca3768520048f991814835e8","observation_id":"02d7169d-3aed-4d68-b38f-184763a2873d","resolution":{"observed_at":"2026-08-15T21:04:09.057985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:09.000952Z","title":"Spectral networks and locally connected networks on graphs","venue":null,"work_id":"45fa46fd-1d4f-4ed4-802a-372f85809130","year":2014},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:07.980466Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:363ed2874f44e4efa81be4eb44314d6986edf5e0bd59399e88299d078ebb5807","observation_id":"b7777fbb-7792-4e85-bb5e-ef39914a7197","resolution":{"observed_at":"2026-08-15T21:04:09.007016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.928162Z","title":"Joshi, Anh Tuan Luu, Thomas Laurent, Yoshua Bengio, and Xavier Bresson","venue":null,"work_id":"32ab062f-01e9-42a7-8c46-a9cb9f7c292c","year":2023},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.004576Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:4962aafecb89abcb623052f19f07c3544874ad69fdc6b92a32cfb5c04714c96c","observation_id":"b4376f82-8f6d-4674-8a25-a137177bbc53","resolution":{"observed_at":"2026-08-15T21:04:08.934667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.16092","last_updated":"2023-12-20T07:43:53Z","snapshot_observed_at":"2026-08-18T14:04:39.324221Z","submitted_at":"2023-07-29T23:31:18Z","title":"Feature Transportation Improves Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.16092","snapshot_observed_at":"2026-08-15T21:04:08.011950Z","title":"ADR-GNN: advection-diffusion-reaction graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.011950Z"},"links":{"cited_paper":"/paper/2307.16092","citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:6f5b8afa91494405696bd69f656baae05a9c3c9dd7255e3ba7bff98b61c83912","observation_id":"18148faf-fd0f-4f7a-814b-06bf6b1a1786","resolution":{"observed_at":"2026-08-15T21:04:08.011950Z","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":"2026-08-15T21:04:08.910993Z","title":"On random graphs i","venue":null,"work_id":"77a3a681-fa31-4bd3-bde0-fdc94d6535c6","year":1959},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.018581Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:b353dc2c4ba8b339393e35c29ded75a5fa742691c7c1f4ae5dbaa55f12492e4a","observation_id":"af811dc0-4cb8-45b7-bd8d-3a5924a43f32","resolution":{"observed_at":"2026-08-15T21:04:08.916726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.839435Z","title":"OGB- LSC: A large-scale challenge for machine learning on graphs","venue":null,"work_id":"54dede78-2109-4823-ba48-284be45b040a","year":2021},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.051089Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:d43ac03a3f95816cdd0b8b7a4171a80b276d7e156932dd3e51b2cb745cfa6dcd","observation_id":"cdebd697-f6c4-49ee-b2f7-04a3572a3790","resolution":{"observed_at":"2026-08-15T21:04:08.845051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.823073Z","title":"Aggarwal, and Jiliang Tang","venue":null,"work_id":"49b9af9c-5752-4c3b-a5f7-a40a58d0bbb8","year":2022},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.056776Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:03a3ebc4cc204a692e47dcfafad8b4b05bd4dba4808111f87da06cc7c523b109","observation_id":"5d1c185d-3183-4c04-8a7c-6278fa637e9d","resolution":{"observed_at":"2026-08-15T21:04:08.828410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.807683Z","title":"Kipf and Max Welling","venue":null,"work_id":"8f82c504-d793-4f24-8b01-4aa2c503a0ac","year":2017},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.061868Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:4ed38f6f61db578ec2565babcbb42f08781ce5cc4b906ea94e9324556e30825c","observation_id":"d0d7eea0-f73c-467b-bf89-3f15f044db93","resolution":{"observed_at":"2026-08-15T21:04:08.812651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.758692Z","title":"A reduction of a graph to a canonical form and an algebra arising during this reduction","venue":null,"work_id":"6cacc1ce-d420-42e4-a9cf-e02bb2214139","year":1968},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.077977Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:4c0874e0dfc49943c114be93b86d833cc29f5bbc17b44a3bbab967c592690cd0","observation_id":"4d1c7a72-4e31-47cf-956f-d1784dd1facb","resolution":{"observed_at":"2026-08-15T21:04:08.763986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.691007Z","title":"Graph neural networks exponentially lose expressive power for node classification","venue":null,"work_id":"a95a099e-c91e-45c4-a888-4918763f9f8b","year":2020},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.099152Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:d03154bfc9a169b167831832deb96894294a38bc8fad1ef8d65b27a946192d91","observation_id":"268df92c-8f7a-465a-be77-e2ed99f8a5fe","resolution":{"observed_at":"2026-08-15T21:04:08.696042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.673572Z","title":"Convolution operators and L(p,q ) spaces","venue":null,"work_id":"c9c4b4b4-d159-4a0f-81f4-75430f08fb4d","year":1963},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.104345Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:2621cdd35e77fe8eb4268a286428ef73134902ca04dcb651dd1512dafded32ff","observation_id":"3b4931ae-258e-46b3-904a-db3a35a574a2","resolution":{"observed_at":"2026-08-15T21:04:08.679433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.642611Z","title":"Recipe for a general, pow- erful, scalable graph transformer","venue":null,"work_id":"fdedeb1f-6239-44d1-a9cc-3188a53e2a35","year":2022},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.114434Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:a1acddfed4970c4753b52b5b611992864f4afc120a45d7bc9fb6c3fc4a4b1c4e","observation_id":"8b36a260-8b5b-46b4-b5da-64f921ca2655","resolution":{"observed_at":"2026-08-15T21:04:08.647488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.627223Z","title":"Transforming pagerank into an infinite-depth graph neural network","venue":null,"work_id":"9d4baa4d-5db1-44d9-9c8e-4fc4c5e18b56","year":2022},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.118919Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:dc8b83344f0b9ac47fa23af4c0417595527c58b080de724f0757462c1e8ccb25","observation_id":"4c5ea199-06fe-43b8-8c9a-582db1c8b64c","resolution":{"observed_at":"2026-08-15T21:04:08.632198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.610702Z","title":"Rank collapse causes over-smoothing and over-correlation in graph neural networks","venue":null,"work_id":"1ac3a498-6f52-41e2-8331-bcecd564449a","year":2023},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.123610Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:2107868dab7678bb47abc43d7174212295acf09834157086de384ded5b986abc","observation_id":"94fd7fcc-b925-4622-ab6f-211e5753406a","resolution":{"observed_at":"2026-08-15T21:04:08.615623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11504","last_updated":"2024-12-09T14:03:33Z","snapshot_observed_at":"2026-08-16T13:17:42.742901Z","submitted_at":"2024-09-17T19:16:03Z","title":"Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11504","snapshot_observed_at":"2026-08-15T21:04:08.127821Z","title":"Preventing representational rank collapse in mpnns by splitting the computational graph","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.127821Z"},"links":{"cited_paper":"/paper/2409.11504","citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:67b2c8f96b8db769970a5c2163a426fe1f9a95cfc230acbb9404ca9e0084e439","observation_id":"747b7770-496d-4ca4-89a5-1238aef30cc7","resolution":{"observed_at":"2026-08-15T21:04:08.127821Z","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":"2026-08-15T21:04:08.594231Z","title":"Konstantin Rusch, Benjamin Paul Chamberlain, Michael W","venue":null,"work_id":"4570d202-b124-4a48-b9de-d6effb65faae","year":2023},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.137560Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:a6a24967f49a08a278a36e36dcb4a978ea330aee08060a0303a6804ce3ff697d","observation_id":"0e30b65a-abee-4544-af6c-5ed0d2f716d8","resolution":{"observed_at":"2026-08-15T21:04:08.599105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.577639Z","title":"Discrete signal processing on graphs","venue":null,"work_id":"1b4f9d9a-5425-42f7-9849-6956ea228c73","year":2013},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.143373Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:d371effce6c132eff9b543e1a681b0a90f8013a4d8da6a45af1e12f3e9ac61be","observation_id":"bbd48874-0332-4ab1-bba6-9e42190373e1","resolution":{"observed_at":"2026-08-15T21:04:08.583316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.562832Z","title":null,"venue":null,"work_id":"35f103b2-84d4-4115-b3b5-c38b11de3773","year":2015},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.153666Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:272e0739d58cf62e913ae32d26709540bf1e2294e270c11ffe42deee5808887a","observation_id":"fb5388bd-8ef1-4232-be69-2d5d6e012cfc","resolution":{"observed_at":"2026-08-15T21:04:08.567514Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.528627Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":"39074208-11d7-40bc-b77b-fdeeedc5faa5","year":2017},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.163261Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:accc4f95a1fd4e428f3616a26d31e45511442b98d4fdf18296ffdfee0b934cf3","observation_id":"9872d478-c6a3-482f-86e0-19b684a03ac1","resolution":{"observed_at":"2026-08-15T21:04:08.535165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.512837Z","title":"Graph attention networks","venue":null,"work_id":"e43c2bee-7cb2-41a6-be4d-8d6dd5064caf","year":2018},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.168494Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:c5ed879be15d58c812f953a4e5d6cc5ad9709d30da217cc7c95f387cec6f8da4","observation_id":"93631824-ddae-4077-81ec-553488e54aaa","resolution":{"observed_at":"2026-08-15T21:04:08.518341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08586","last_updated":"2023-10-17T00:12:20Z","snapshot_observed_at":"2026-08-16T15:00:19.684100Z","submitted_at":"2023-09-15T17:43:40Z","title":"Replacing softmax with ReLU in Vision Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08586","snapshot_observed_at":"2026-08-15T21:04:08.172998Z","title":"Replacing softmax with relu in vision transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.172998Z"},"links":{"cited_paper":"/paper/2309.08586","citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:1ec5c891885f202ab244d75f2753faa98068077ef17f77ed0e0049532719f012","observation_id":"07732558-01d9-496c-8bc2-5377410a2495","resolution":{"observed_at":"2026-08-15T21:04:08.172998Z","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":"2026-08-15T21:04:08.496150Z","title":"Representation learning on graphs with jump- ing knowledge networks","venue":null,"work_id":"57020a5c-4e0f-4eec-b28b-4461e1c5c506","year":2018},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.178515Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:0f1a157192624be79bb854e164602691f06c796481cd3b634fa39ccc82c55aae","observation_id":"82a4f8a2-9d9d-4ee7-97a6-b23b77aa236e","resolution":{"observed_at":"2026-08-15T21:04:08.501401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.477628Z","title":"How powerful are graph neural net- works? In 7th International Conference on Learning Rep- resentations, New Orleans, LA, USA, May 6-9,","venue":null,"work_id":"84c8aa79-b0ff-4504-a18d-2db9297cb970","year":2019},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.183700Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:b0e30f6cc81f626bf551e24ef8faa0152101e2264917bdde9a49e7ab3042a57e","observation_id":"448f3c75-2252-4352-8720-412251131c2b","resolution":{"observed_at":"2026-08-15T21:04:08.484274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.460979Z","title":"Two sides of the same coin: Heterophily and oversmoothing in graph con- volutional neural networks","venue":null,"work_id":"45787791-6e3d-455f-ac04-a86f4f450029","year":2022},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.188419Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:3f19daf46d328353edba9706b192ff4fa0182dfff98e33013683c331b20a1b61","observation_id":"16cd298b-c115-4c97-ba97-910ddb670272","resolution":{"observed_at":"2026-08-15T21:04:08.466079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.445104Z","title":"Multi-channel graph neural networks","venue":null,"work_id":"99f52d09-e211-4ae3-90bd-43b85585a579","year":2020},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.193358Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:20ccca5f8d30a29681b93ae318b24cadd7ab88836c173cff235cb63f80e94f45","observation_id":"bd6012d9-5650-4cb3-bf92-39e1d4509607","resolution":{"observed_at":"2026-08-15T21:04:08.450328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.424864Z","title":"We use the vectorized signal ˆx = vec(X) ∈ Rn·c by stacking its columns","venue":null,"work_id":"1c6a6ccd-528d-4795-89fe-e7a4185a2ccb","year":2009},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.198242Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:90431bdefcf3be30311bab4f9da01068af9c2796005815337a313ff99ffdf634","observation_id":"e48b7c24-bedf-4603-b082-3f93065b4046","resolution":{"observed_at":"2026-08-15T21:04:08.433293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.406379Z","title":null,"venue":null,"work_id":"62550ac9-f8db-4e28-84c5-6d1556b5f771","year":null},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.203440Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:b66b945eda208cb6c6ea27637fb0105d69ace4309559824433f0300ad8d7675f","observation_id":"857332fb-0788-40e9-a681-2d8f15ebe37c","resolution":{"observed_at":"2026-08-15T21:04:08.412222Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.889768Z","title":"Marques, Alejandro Ribeiro, and Geert Leus","venue":null,"work_id":"828399ff-2604-4ced-8c74-0b6c0746280d","year":2018},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":1959,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.023732Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:9414a3b6634a890cf255aed2a0d800d02282a39d365fd366394a9bff334945ea","observation_id":"5c0ba3f4-fbc8-4a98-a4bc-ed7cb9cbb77b","resolution":{"observed_at":"2026-08-15T21:04:08.895608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.657931Z","title":"Geom-gcn: Geo- metric graph convolutional networks","venue":null,"work_id":"bd5b1557-fde8-4091-b5e3-5d619797c777","year":2020},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":1963,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.109289Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:57a96da6ee4384d8a8cb9217020e911374ab0478e31a404c2b94ec2dba665d81","observation_id":"3de57ead-590d-448a-9876-b37fcc8dc97b","resolution":{"observed_at":"2026-08-15T21:04:08.663355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.742631Z","title":"Bronstein","venue":null,"work_id":"90196563-5084-4cfa-a653-88f6e03ada9f","year":2019},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":1968,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.083496Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:fa85fa7b41abab3d788cbdbfb6396a69533c6d6d6c492283c8bd669aa28682e0","observation_id":"57c50634-ebe0-4dfc-a673-0c87b4fb63d4","resolution":{"observed_at":"2026-08-15T21:04:08.747966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.774935Z","title":"Hamilton, Vincent L´etourneau, and Prudencio Tossou","venue":null,"work_id":"0cb1f859-11d2-4552-9e4d-b613baae8a9c","year":2021},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.073072Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:3a987012ad37262a64e09d2774081ff1dd9e23a9be56aeb2300d9d743c14a27e","observation_id":"916e1bf0-fb4a-440b-9d5d-91912c0a1eae","resolution":{"observed_at":"2026-08-15T21:04:08.780310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.06333","last_updated":"2020-12-08T01:19:48Z","snapshot_observed_at":"2026-08-19T06:30:19.084601Z","submitted_at":"2020-12-08T01:19:48Z","title":"Sheaf Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.06333","snapshot_observed_at":"2026-08-15T21:04:08.034748Z","title":"Sheaf neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.034748Z"},"links":{"cited_paper":"/paper/2012.06333","citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:b0c1d0f452d499ca2fddd774424bf705abcbac5e3f747deb9bb4fa574619a8e2","observation_id":"bd2f2607-b62e-4b84-9241-aedcf3d0b16d","resolution":{"observed_at":"2026-08-15T21:04:08.034748Z","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":"2026-08-15T21:04:08.148201Z","title":"Rethinking softmax: Self-attention with polynomial acti- vations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.148201Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:230860d00ba9fe0f40e2781d2f9191f1d4276c961a4d1ad307cec5e95054175e","observation_id":"134e10a1-3cf3-4553-8fee-2d50a3df9c04","resolution":{"observed_at":"2026-08-15T21:04:08.148201Z","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":"2026-08-15T21:04:08.985371Z","title":"Convolutional learning on multigraphs","venue":null,"work_id":"3e111c0b-3022-4628-b531-763eff4c60a7","year":2023},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:07.986499Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:9ca902dfdbc57da276bd5d3f9458f105045fe7821487d7e6a892220974cff8a6","observation_id":"1599d9db-da10-4365-bd1d-9410b50f2465","resolution":{"observed_at":"2026-08-15T21:04:08.990317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.546246Z","title":"Where did the gap go? re- assessing the long-range graph benchmark","venue":null,"work_id":"2504da92-5299-4e9e-b7bf-428da13e9dc7","year":2024},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.158345Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:27559ae3774a38086966db116e5777a5ddd27487f337ee0fa494db271a6dde58","observation_id":"f15c0c40-e98e-4b41-b6c0-ae73c33e72bb","resolution":{"observed_at":"2026-08-15T21:04:08.551405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.949953Z","title":"Long range graph benchmark","venue":null,"work_id":"56569afd-f481-486c-8b71-d5d68acbd93e","year":2022},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:07.999093Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:a178acf89c258d688a7e3a04948768795391a43ae58877e3607c9a1c2c5b9689","observation_id":"aed620b9-0bec-43e6-a495-6ada96a88b53","resolution":{"observed_at":"2026-08-15T21:04:08.955977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.791012Z","title":"Kolda and Brett W","venue":null,"work_id":"4a23282f-6ce9-4622-8156-23f72a2d0312","year":2009},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.066933Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:65f038d6e0d3983a913ad4dbb2fe69c0ca7219f06e57c979ba11bab321508d2f","observation_id":"93be8abe-2d01-4db3-9c42-bd4941a5b93c","resolution":{"observed_at":"2026-08-15T21:04:08.796529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.872146Z","title":"Wavelets on graphs via spectral graph theory","venue":null,"work_id":"fd5e72ff-b215-421d-8024-d945882ddff9","year":2011},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.029532Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:c4995cf2ec11b22a1b1795ca369a8f9b47321b5b8133f0c5a10ba4ee0172bc08","observation_id":"45551539-5fda-4b63-9067-3466210d3dc5","resolution":{"observed_at":"2026-08-15T21:04:08.878215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.726503Z","title":"Gpnet: Simpli- fying graph neural networks via multi-channel geometric polynomials","venue":null,"work_id":"1b74748c-d39b-40de-b5f3-45ea51db6674","year":2025},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.089000Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:4cbbc637f4756e35472f3ea627d955052b7a519716c667e1b60ec89ae35a8c2e","observation_id":"e020ce8b-12d5-4ccf-b4cb-c4a5c502bf61","resolution":{"observed_at":"2026-08-15T21:04:08.731629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.856897Z","title":"Deep residual learning for image recog- nition","venue":null,"work_id":"79a5989d-c127-4748-b3ea-32b0751c4547","year":2016},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.045927Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:bbc61956f802471b53cbe741ed231c033f8dd6893660c057aff42abc5c393452","observation_id":"a8e70092-af58-40eb-bed5-a9c8bbc15928","resolution":{"observed_at":"2026-08-15T21:04:08.861909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:09.035125Z","title":"Bronstein","venue":null,"work_id":"3502ab4a-4c4c-4d62-8142-7fdada2fe6a4","year":2022},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:07.969320Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:5ce02d8463d0911f7445a183f8d90c349af4c30c82089691ff7a3382c5b6c2ce","observation_id":"9a4ab36b-d669-498b-9881-751ef7359ba9","resolution":{"observed_at":"2026-08-15T21:04:09.040668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:09.018120Z","title":"How attentive are graph attention networks? In The Tenth International Conference on Learning Representa- tions, Virtual Event, April 25-29,","venue":null,"work_id":"8301d543-51cc-4116-9bd0-c6cdd72d22f5","year":2022},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:07.974569Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:907ead8b7597b7aceae7f75475604f7ff788c0d38e1d73e04cfc258d54fc9b23","observation_id":"2e2f55f5-4f89-47b5-9d86-44f4bdd029bd","resolution":{"observed_at":"2026-08-15T21:04:09.023535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T21:04:08.968538Z","title":"Convolutional neural networks on graphs with fast localized spectral filtering","venue":null,"work_id":"fabaf31d-7e11-4a01-b632-db660e6d1739","year":2016},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:07.993417Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:dc8eb100253733fb087f61ec3b6cf77a3ae493212bfce501aee2b0422ec1b8a4","observation_id":"3ffc760f-63b6-416a-9a03-5daae847e3c8","resolution":{"observed_at":"2026-08-15T21:04:08.973770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.11876","last_updated":"2024-09-02T09:49:49Z","snapshot_observed_at":"2026-08-16T13:33:41.976314Z","submitted_at":"2024-07-16T16:00:42Z","title":"Simplifying the Theory on Over-Smoothing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.11876","snapshot_observed_at":"2026-08-15T21:04:08.132753Z","title":"Simplifying the theory on over- smoothing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.132753Z"},"links":{"cited_paper":"/paper/2407.11876","citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:4766d3223bfb6b7190b4fb7525b2abb66ff7b6158af3b1cdb09e41955d572b18","observation_id":"5eb57617-2398-43f1-be36-2c033bc4bd08","resolution":{"observed_at":"2026-08-15T21:04:08.132753Z","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":"2026-08-15T21:04:08.708758Z","title":"Revisiting heterophily for graph neural networks","venue":null,"work_id":"808c24b2-5646-4437-860f-5e2984a1a835","year":2022},"citing_paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T21:04:08.093924Z"},"links":{"citing_paper":"/paper/2505.11346"},"observation_digest":"sha256:9b788322b4327e9c4f031c3e5ed108b6e8ed47f952b423b0792e9fc45bfba3cf","observation_id":"131da6d1-b59a-4162-ad56-01ea9e9d7f85","resolution":{"observed_at":"2026-08-15T21:04:08.714677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.11346","last_updated":"2025-05-16T15:13:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T14:04:11.023103Z","submitted_at":"2025-05-16T15:13:09Z","title":"What Can We Learn From MIMO Graph Convolutions?"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":37},"total_outbound_references":45},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2505.11346."}