{"as_of":"2026-08-10T08:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a7bdb7e7ea55322f9c401ffb66fd08c99a831d07088d986042eca2a3aa4bdf4a","coverage":[{"denominator":95,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":95,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T21:29:28.147348Z","state":"measured"},{"denominator":97,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":97,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T21:43:50.425136Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-30T21:45:05.589364Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"cited_work":{"arxiv_id":"2501.19089","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.19089","snapshot_observed_at":"2026-06-30T21:45:05.589364Z","title":"Wang, K., Yang, Y ., Saha, I., and Allen-Blanchette, C","venue":null,"work_id":"0ef9e6fd-7057-404e-ac86-7eed9a572d75","year":2025},"citing_paper":{"arxiv_id":"2605.13834","last_updated":"2026-05-29T19:42:16Z","snapshot_observed_at":"2026-07-06T23:25:21.032938Z","submitted_at":"2026-05-13T17:56:23Z","title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-14T19:05:31.289091Z"},"links":{"cited_paper":"/paper/2501.19089","citing_paper":"/paper/2605.13834"},"observation_digest":"sha256:89e346fc96d9c0616d559d740d2a3971da37b9e63b650ad8ed46d28173faf4f1","observation_id":"682825bd-26c9-4f5a-b5ca-03dcfc05532b","resolution":{"observed_at":"2026-05-14T19:07:51.537533Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"cited_work":{"arxiv_id":"2501.19089","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.19089","snapshot_observed_at":"2026-06-30T21:45:05.589364Z","title":"Wang, K., Yang, Y ., Saha, I., and Allen-Blanchette, C","venue":null,"work_id":"0ef9e6fd-7057-404e-ac86-7eed9a572d75","year":2025},"citing_paper":{"arxiv_id":"2605.13834","last_updated":"2026-05-29T19:42:16Z","snapshot_observed_at":"2026-07-06T23:25:21.032938Z","submitted_at":"2026-05-13T17:56:23Z","title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-06-30T21:43:50.425136Z"},"links":{"cited_paper":"/paper/2501.19089","citing_paper":"/paper/2605.13834"},"observation_digest":"sha256:4999bdd332742ca4c68f4fb222c68fa37a03b2ce53ff8e74e12e325a605475cf","observation_id":"8270ba44-4c04-4e19-a3c6-6d2a1b302b44","resolution":{"observed_at":"2026-06-30T21:45:05.590857Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.19089/citation-record","integrity":"/paper/2501.19089/integrity","json":"/paper/2501.19089/citation-record.json","paper":"/paper/2501.19089"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:27.684232Z","title":"Geometry-enhanced molecular representation learning for property prediction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.684232Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:a3aed56371931e4611b539beb880d72753190d55fb8e1f73401a53b78a000b10","observation_id":"bfc100ea-cfad-40a5-8a3a-7f50655f857b","resolution":{"observed_at":"2026-08-09T21:29:27.684232Z","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":"2026-08-09T21:29:27.718453Z","title":"Starling flock networks manage uncertainty in consensus at low cost","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.718453Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:5282de715ca70ef93f360abc65e3de759479f3b1ea97b9bbdbe35ed3394cdce8","observation_id":"2795cb7b-4586-4a6b-8df1-80edcf735e56","resolution":{"observed_at":"2026-08-09T21:29:27.718453Z","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":"2026-08-09T21:29:27.726148Z","title":"A latency-defined edge node placement scheme for opportunistic smart cities","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.726148Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:d16b95b65168764a6102060e58096a007243d8aee4511ff12315bea8d75f8365","observation_id":"e30ceb14-da89-4338-b80d-93481e78bbb0","resolution":{"observed_at":"2026-08-09T21:29:27.726148Z","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":"2026-08-09T21:29:27.730546Z","title":"Graph convolutional neural networks for web-scale recommender systems","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.730546Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:168eab5d95e0129efc4d9465085f9e0952f85670109a24e0afab45046cd4e034","observation_id":"a9b8c2eb-b214-4bc1-84e0-3ecbb78b8b72","resolution":{"observed_at":"2026-08-09T21:29:27.730546Z","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":"2026-08-09T21:29:27.734833Z","title":"Molecular contrastive learning of representations via graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.734833Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:6eefaa511db7cd28f8ac60b96daaa34fdb6c55e71099f3d7a08f3a5dbf0788cf","observation_id":"9c663ab4-2e69-4bde-b067-df1d49047ba0","resolution":{"observed_at":"2026-08-09T21:29:27.734833Z","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":"2026-08-09T21:29:27.739073Z","title":"Prediction of protein–protein interaction using graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.739073Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:04db48a1e914d74bdf17fe2ca3396dd277bfa29bddcf4ba651c67c1fc48caf89","observation_id":"74f57603-17db-4a0b-9e76-46c403ffc600","resolution":{"observed_at":"2026-08-09T21:29:27.739073Z","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":"2026-08-09T21:29:27.743880Z","title":"Deeprank-gnn: a graph neural network framework to learn patterns in protein–protein interfaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.743880Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:8da470bf58b16f7233101d27bd64305fd6b87a0c133ef586ea4dcb78f05e1657","observation_id":"4eaa404a-b251-4ee6-ae1b-26c5e97e776f","resolution":{"observed_at":"2026-08-09T21:29:27.743880Z","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":"2026-08-09T21:29:27.748323Z","title":"A graph placement methodology for fast chip design","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.748323Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:207d824a86d555f285dc6146db901c367d1235c1aeafac519c4cc266b340a7b3","observation_id":"02327d1b-fe8f-440f-a701-ba29eacee74a","resolution":{"observed_at":"2026-08-09T21:29:27.748323Z","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":"2026-08-09T21:29:27.752668Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.752668Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:b99ae0c670246737ca0f0a4a344d8a7a6cb117c2eef7aeb84aecc8b39dc217bd","observation_id":"c91d30e4-09ee-4697-a4ed-8275ab66a4c8","resolution":{"observed_at":"2026-08-09T21:29:27.752668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10947","last_updated":"2021-01-06T13:32:14Z","snapshot_observed_at":"2026-07-06T07:55:41.176211Z","submitted_at":"2019-05-27T02:59:06Z","title":"Graph Neural Networks Exponentially Lose Expressive Power for Node Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.10947","snapshot_observed_at":"2026-08-09T21:29:27.757042Z","title":"Graph neural networks exponentially lose expressive power for node classification","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.757042Z"},"links":{"cited_paper":"/paper/1905.10947","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:7f94397c8a4be86d61d79083d9e9bb034142c56af67e8624c42ddb11be93db98","observation_id":"17c27ff3-07bf-430f-97ac-cbd49dc8b0c7","resolution":{"observed_at":"2026-08-09T21:29:27.757042Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.09550","last_updated":"2019-05-26T05:21:04Z","snapshot_observed_at":"2026-07-06T07:54:54.802338Z","submitted_at":"2019-05-23T09:27:21Z","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.09550","snapshot_observed_at":"2026-08-09T21:29:27.763204Z","title":"Revisiting graph neural networks: All we have is low-pass filters","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.763204Z"},"links":{"cited_paper":"/paper/1905.09550","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:85e7e3501220945c031ddcb5d809efe90691a5547da687de21ddebe11994ea18","observation_id":"f09bc8fb-60b9-4d3f-8f25-4cec48b2c8b5","resolution":{"observed_at":"2026-08-09T21:29:27.763204Z","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":"2026-08-09T21:29:27.767776Z","title":"Simple and deep graph convolutional networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.767776Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:c0f957bd543a7b7472f0d59663e0d2c7563b7c7d663a1fbc72a6b147f418c32f","observation_id":"a95139ff-9a79-4009-929a-39a43955f238","resolution":{"observed_at":"2026-08-09T21:29:27.767776Z","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":"2026-08-09T21:29:27.772092Z","title":"Towards deeper graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.772092Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:e39d1ca8912b268e501570f3a921f43a722b00362b3ced3c5cd5df9d10f5c7f9","observation_id":"7ad0537b-3047-4515-824d-72d8d43a85fd","resolution":{"observed_at":"2026-08-09T21:29:27.772092Z","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":"2026-08-09T21:29:27.776305Z","title":"InInternational conference on machine learning, pages 6878–6917","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.776305Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:dccb5af85cf5f004c20872db3ec3d348f09cc058b8e96657bd55e4038b79d2c6","observation_id":"647ee64d-db83-4af0-9ffc-cfd17f39bead","resolution":{"observed_at":"2026-08-09T21:29:27.776305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.12223","last_updated":"2020-02-13T02:27:25Z","snapshot_observed_at":"2026-07-31T22:27:00.310523Z","submitted_at":"2019-09-26T16:20:37Z","title":"PairNorm: Tackling Oversmoothing in GNNs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.12223","snapshot_observed_at":"2026-08-09T21:29:27.780517Z","title":"Pairnorm: Tackling oversmoothing in gnns","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.780517Z"},"links":{"cited_paper":"/paper/1909.12223","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:4f2fd4dc4d742c5de2ceef3c1dbda8d1fa649d4d110c1dec67866e1d75b9244e","observation_id":"6a4d0841-e34f-4910-a412-8d13256bb1c3","resolution":{"observed_at":"2026-08-09T21:29:27.780517Z","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":"2026-08-09T21:29:27.786136Z","title":"Towards deeper graph neural networks with differentiable group normalization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.786136Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:740f73b4f8101454cf68eaeb97c8a3156cc56f4cc51424853373f0b988e08df7","observation_id":"9b77112b-9252-4025-b061-6bc4a5cf1801","resolution":{"observed_at":"2026-08-09T21:29:27.786136Z","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":"2026-08-09T21:29:27.790454Z","title":"Understanding and resolving performance degradation in deep graph convolutional networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.790454Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:ffe94ab9c38cfe1cde657efff4e26fb49e8ffe90035b7967314c48fa05eae77e","observation_id":"bc25cebf-95ee-475f-8e31-a218b51d4f48","resolution":{"observed_at":"2026-08-09T21:29:27.790454Z","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":"2026-08-09T21:29:27.795603Z","title":"Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.795603Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:0fc61e9bd00789b11cefa57940323cad646ba496e9fc3f0b4f1debf73bd92a83","observation_id":"64b9f826-ce78-4f9c-abac-208753281850","resolution":{"observed_at":"2026-08-09T21:29:27.795603Z","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":"2026-08-09T21:29:29.476666Z","title":"Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","venue":null,"work_id":"4ab6e7de-3d3b-43ef-bd6a-611224742a60","year":2019},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.799906Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:29190a20298c9542a826867fa0a84945ad33a937b4895aea85ae6a24f34805cb","observation_id":"d7fb83a0-b749-485a-ab68-8493f039ca3c","resolution":{"observed_at":"2026-08-09T21:29:29.482632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.04931","last_updated":"2020-02-16T00:42:48Z","snapshot_observed_at":"2026-08-05T00:16:40.110456Z","submitted_at":"2019-07-10T21:11:13Z","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.04931","snapshot_observed_at":"2026-08-09T21:29:27.805046Z","title":"Graphsaint: Graph sampling based inductive learning method","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.805046Z"},"links":{"cited_paper":"/paper/1907.04931","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:8bc855cf4cf2c620cdbde030f20dc25c96b27e1e5efeb23a16769457a8c58c06","observation_id":"2bd85920-8f49-477a-8ff4-7c571f927aeb","resolution":{"observed_at":"2026-08-09T21:29:27.805046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07988","last_updated":"2021-10-26T20:07:59Z","snapshot_observed_at":"2026-08-09T23:19:48.421057Z","submitted_at":"2020-06-14T19:27:39Z","title":"Adaptive Universal Generalized PageRank Graph Neural Network","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07988","snapshot_observed_at":"2026-08-09T21:29:27.809778Z","title":"Adaptive universal generalized pagerank graph neural network","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.809778Z"},"links":{"cited_paper":"/paper/2006.07988","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:a292596343bf1af535e7e88b324a71c3fe92493bac679c9add35041d18b9c0bb","observation_id":"9edcc989-f84f-4741-bf4b-a8c2eed52a4d","resolution":{"observed_at":"2026-08-09T21:29:27.809778Z","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":"2026-08-09T21:29:29.460743Z","title":"Beltrami flow and neural diffusion on graphs","venue":null,"work_id":"24d19111-a55c-4ed7-a5b7-034deed29ea8","year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.814900Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:5167b584fdb486773c019b9cd1b272ac38efdc04931fbcaec5652de3366a0e36","observation_id":"0cfde880-d6b6-41f3-942c-1dd25d94ab2e","resolution":{"observed_at":"2026-08-09T21:29:29.465528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10011","last_updated":"2024-03-12T12:38:09Z","snapshot_observed_at":"2026-08-06T07:29:10.021130Z","submitted_at":"2024-02-15T15:18:53Z","title":"Clifford Group Equivariant Simplicial Message Passing Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10011","snapshot_observed_at":"2026-08-09T21:29:27.819245Z","title":"Clifford group equivariant simplicial message passing networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.819245Z"},"links":{"cited_paper":"/paper/2402.10011","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:a3362cb3fc717791bb68021b477675cf5f9a6558da34e3bc590daad191b9cf6f","observation_id":"5a5dae01-b17b-429d-b5ea-bc3dc0b36908","resolution":{"observed_at":"2026-08-09T21:29:27.819245Z","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":"2026-08-09T21:29:29.445190Z","title":"A generalized neural diffusion framework on graphs","venue":null,"work_id":"32751d87-fd57-4b59-8dd6-42e7d779e2bf","year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.824094Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:dc3bc4f9a0d2c636e94bc03c9189482672970d4c344a5d3b1aa922c82c1f9c8b","observation_id":"4023c853-53d9-44c2-a939-6988916899cd","resolution":{"observed_at":"2026-08-09T21:29:29.449768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07532","last_updated":"2021-06-22T07:40:01Z","snapshot_observed_at":"2026-08-08T07:19:01.554491Z","submitted_at":"2019-11-18T10:46:15Z","title":"Graph Neural Ordinary Differential Equations","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.07532","snapshot_observed_at":"2026-08-09T21:29:27.828090Z","title":"Graph neural ordinary differential equations","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.828090Z"},"links":{"cited_paper":"/paper/1911.07532","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:dc6c30ca2f4876899d1cfa10f8caef27d3454311adc48987fe8314a630472d7d","observation_id":"774bc073-ef7f-4995-884e-83e41acff324","resolution":{"observed_at":"2026-08-09T21:29:27.828090Z","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":"2026-08-09T21:29:29.429336Z","title":"Grand: Graph neural diffusion","venue":null,"work_id":"81ae7def-a919-469a-a8db-f6d32e7ea5eb","year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.832990Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:3e8dc0f52fada4ac477c3e14779191bacc71a89532aecbdf51915a219f659c48","observation_id":"eee75488-1f6a-4e06-bb1d-b442056edfc5","resolution":{"observed_at":"2026-08-09T21:29:29.433743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.414752Z","title":"Pde-gcn: Novel architectures for graph neural networks motivated by partial differential equations","venue":null,"work_id":"10fa0022-7eb0-458f-9cfb-94c51fce58c9","year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.837324Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:d9279435443b6f6f750ac0cb089852f6bb256deb4f2f8b2944bcf2066de9d5f3","observation_id":"931fc1a3-4f49-4f04-824f-c025a02db2fa","resolution":{"observed_at":"2026-08-09T21:29:29.419594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.400110Z","title":"Nonlinear dynamics and chaos","venue":null,"work_id":"bdc255f5-54f3-4c2b-a8f2-687af4539091","year":2002},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.841826Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:4023e063a3f8fa0990ca63b2432d0f30a963f2439b2954eacb6b3b6ed97a1c21","observation_id":"1ea44700-e0ca-4ba6-8666-98aa1baf8b12","resolution":{"observed_at":"2026-08-09T21:29:29.405211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:27.845875Z","title":"Discovering governing equations from data by sparse identification of nonlinear dynamical systems","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.845875Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:eb379e9921cfb96e87b52d5dcb9d965ae320a7ac97ee2a6183fddd285b6a2e1c","observation_id":"84196646-299b-43f7-b7f0-f1be2016c215","resolution":{"observed_at":"2026-08-09T21:29:27.845875Z","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":"2026-08-09T21:29:29.376335Z","title":"Output-only identification of self- excited systems using discrete-time lur’e models with application to a gas-turbine combustor","venue":null,"work_id":"9e85bbd8-1b29-4d2c-b126-4c67d5c763df","year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.851006Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:850586a251518f5ecfca4f12e1aec2fa0e2b081d8359b93643905a1792a75a9b","observation_id":"e55e311e-c313-43e3-86fc-64ca3eaefc74","resolution":{"observed_at":"2026-08-09T21:29:29.382027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.360897Z","title":"Output-only identi- fication of lur’e systems with hysteretic feedback nonlinearities","venue":null,"work_id":"458590a6-6284-4f01-92aa-3aef482b997b","year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.855211Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:47561def625732a32196d891c77d2bad64b7fde0fb0e6c3473b3efc6320e9d2a","observation_id":"c17201ee-98fd-49f6-8a23-c6865935e7a6","resolution":{"observed_at":"2026-08-09T21:29:29.365416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:27.860138Z","title":"Graph-coupled oscillator networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.860138Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:fa067349eccf9d714f09fd5f299fdf3917656801c4e6994a72c84bfc0452c880","observation_id":"d913c109-75c1-4b3e-896e-56af033ba171","resolution":{"observed_at":"2026-08-09T21:29:27.860138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.05437","last_updated":"2025-07-23T11:10:40Z","snapshot_observed_at":"2026-08-07T14:00:02.992461Z","submitted_at":"2022-06-11T06:26:12Z","title":"ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks","version":4},"cited_work":{"arxiv_id":"2206.05437","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.05437","snapshot_observed_at":"2026-08-09T21:29:28.614420Z","title":"ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks","venue":"cs.LG","work_id":"2f337f5b-5030-4c16-9701-982226af339b","year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.864241Z"},"links":{"cited_paper":"/paper/2206.05437","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:bec29c5727341bce15270f8e76272445f66fcc16d9c1338257c5b9f832c648b5","observation_id":"da7b4a58-f86f-4778-9771-1852c96ac188","resolution":{"observed_at":"2026-08-09T21:29:28.619619Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10121","last_updated":"2023-10-29T21:31:53Z","snapshot_observed_at":"2026-08-05T17:32:49.898075Z","submitted_at":"2023-10-16T06:57:24Z","title":"From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyond","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10121","snapshot_observed_at":"2026-08-09T21:29:27.869289Z","title":"From continuous dynamics to graph neural networks: Neural diffusion and beyond","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.869289Z"},"links":{"cited_paper":"/paper/2310.10121","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:9c731894e6a181128dad8d369fc461ab6e5fc1083225c03087497238727254e5","observation_id":"be891aba-55da-4395-b96c-cb9a700d41d0","resolution":{"observed_at":"2026-08-09T21:29:27.869289Z","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":"2026-08-09T21:29:29.336304Z","title":"Fast and flexible multiagent decision-making","venue":null,"work_id":"95f51dd8-8445-4861-a771-5d669528b854","year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.874273Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:28dd8ac96b76716c36778e1fc1a58dc366ca04c8918952520cf25724f5714eda","observation_id":"9fb6f361-1539-4146-96df-e8f924a3586e","resolution":{"observed_at":"2026-08-09T21:29:29.341661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.321315Z","title":"Nonlinear opinion dynamics with tunable sensitivity","venue":null,"work_id":"ddb8483b-43c9-44e9-ac70-6cc1ad45b9df","year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.878899Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:90ef798d094a9b3859f3e6de3cb43a7eab5fa671574f34da01a8573a3a1e5bf9","observation_id":"ceb41b83-67d5-4867-ad38-8d5e1644568c","resolution":{"observed_at":"2026-08-09T21:29:29.326410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.306361Z","title":"On the number of linear regions of deep neural networks","venue":null,"work_id":"17b4be10-d2d4-448d-b858-1dbaa6c67c12","year":2014},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.882928Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:be50e9ed9fc1ee3637b3eb0c592fa157fa6a6b71d16ab8f34489e445d342b7e0","observation_id":"9ad1a85b-0591-4b73-b274-9fae72767c6b","resolution":{"observed_at":"2026-08-09T21:29:29.311327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:27.887699Z","title":"Deep learning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.887699Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:af3048e60f1e71f22d7ee6947857ca30848973759fee9820a6df828894d20312","observation_id":"c8ed424b-98fe-480f-857a-19420ebbc218","resolution":{"observed_at":"2026-08-09T21:29:27.887699Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10701","last_updated":"2023-03-01T04:22:54Z","snapshot_observed_at":"2026-07-06T14:33:16.914984Z","submitted_at":"2022-12-21T00:33:59Z","title":"A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.10701","snapshot_observed_at":"2026-08-09T21:29:27.891714Z","title":"A non-asymptotic analysis of oversmoothing in graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.891714Z"},"links":{"cited_paper":"/paper/2212.10701","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:c40c8f49e220d2c088072aed3e38e62b96033a85a852701a8a3e834cb9048144","observation_id":"b9818c97-630e-45f3-b6df-d5b95666e21b","resolution":{"observed_at":"2026-08-09T21:29:27.891714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-09T21:29:27.896756Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.896756Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:af199997c7e1f19b60fbff836924bb94f3b6df1fb9930cab149e9989be072a2a","observation_id":"5d097e60-1330-47d0-933f-68aefe0ce044","resolution":{"observed_at":"2026-08-09T21:29:27.896756Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.13663","last_updated":"2020-06-17T21:45:09Z","snapshot_observed_at":"2026-08-09T14:54:23.652621Z","submitted_at":"2020-03-30T17:48:04Z","title":"Revisiting Over-smoothing in Deep GCNs","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.13663","snapshot_observed_at":"2026-08-09T21:29:27.901311Z","title":"Revisiting over-smoothing in deep gcns","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.901311Z"},"links":{"cited_paper":"/paper/2003.13663","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:6835d6ceaf651da4da1456082f843fde3f7b51e4157ad1f99ae23993fa204a87","observation_id":"482f5cb3-2d38-471f-a23a-73a18bad5838","resolution":{"observed_at":"2026-08-09T21:29:27.901311Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-09T21:29:27.906257Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.906257Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:97f3c03841a5540a58aacb6576377c53f6ddfab46941dc7b10099a12e5c858fc","observation_id":"74c8de23-b7b6-40c2-8aeb-71939af6f9ec","resolution":{"observed_at":"2026-08-09T21:29:27.906257Z","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":"2026-08-09T21:29:29.282316Z","title":"Demystifying oversmoothing in attention-based graph neural networks","venue":null,"work_id":"c1b96b98-0f44-44c0-b627-ff822404c1f9","year":2023},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.911053Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:4d4a4d6dedff5407263bce06b603ea6a0155a30b6c6e84ab024cc66c38c1da10","observation_id":"4b5dacfd-8362-42b0-9bd4-195d03c09299","resolution":{"observed_at":"2026-08-09T21:29:29.287741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10991","last_updated":"2023-09-06T06:58:11Z","snapshot_observed_at":"2026-08-10T06:11:19.584898Z","submitted_at":"2022-06-22T11:45:36Z","title":"Understanding convolution on graphs via energies","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10991","snapshot_observed_at":"2026-08-09T21:29:27.915677Z","title":"Understanding convolution on graphs via energies","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.915677Z"},"links":{"cited_paper":"/paper/2206.10991","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:562a39f51a6fd4796c3c367d12fef229ec0f67b4512e2a8c0748cc0241d5380d","observation_id":"6cf2c913-eb5d-42d7-8e7e-fc7513a46210","resolution":{"observed_at":"2026-08-09T21:29:27.915677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11504","last_updated":"2024-12-09T14:03:33Z","snapshot_observed_at":"2026-08-07T09:45:04.201426Z","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":"2409.11504","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.11504","snapshot_observed_at":"2026-08-09T21:29:28.503510Z","title":"Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph","venue":"cs.LG","work_id":"ddfce09b-54a6-44e1-bdb8-0bf87d21f0c5","year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.920112Z"},"links":{"cited_paper":"/paper/2409.11504","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:5b38d053fdaca32e56702452f2cf413bafa4c4db227c922d1d1a4d1235a3d66b","observation_id":"bd28229d-bfcd-48cc-8c18-b767cbe808d1","resolution":{"observed_at":"2026-08-09T21:29:28.508889Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.268110Z","title":"Not too little, not too much: a theoretical analysis of graph (over) smoothing","venue":null,"work_id":"493b5b26-960f-4641-9416-457d961da7d2","year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.925045Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:b0d209053c46b325c09b407949bae959898a968836f7354ab9b2b85574b9cb78","observation_id":"dfba2b76-076d-4f72-9634-4eac05036e8e","resolution":{"observed_at":"2026-08-09T21:29:29.272747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:27.929615Z","title":"Neural ordinary differential equations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.929615Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:df0ac536c0443faf8434d08dfe26dc64e3cb2ae32ce98a55e72a9a94f570e387","observation_id":"4542c6e9-3ebb-4262-b33b-e393adad54ba","resolution":{"observed_at":"2026-08-09T21:29:27.929615Z","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":"2026-08-09T21:29:29.244637Z","title":"Grand++: Graph neural diffusion with a source term","venue":null,"work_id":"d41e747c-0f1a-42e9-b3bb-85db40c4d87f","year":2022},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.934524Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:9c0336adfefb0f3d293bf99ddd338d8629124d795ec2bbb5a29b2368488bc2bd","observation_id":"5b2d5ca9-24c7-442f-9a2d-eb8d8b864710","resolution":{"observed_at":"2026-08-09T21:29:29.249613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.231087Z","title":"Gread: Graph neural reaction-diffusion networks","venue":null,"work_id":"a347d743-e849-4a95-a1ce-20df7046e08b","year":null},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.938574Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:da60a0ed3bc1d1a2cb78e27b0bed1dcc81f4f6bf70606f455ca909db4c23be81","observation_id":"4b1dc8eb-824c-4fae-99b3-20779ba9b68c","resolution":{"observed_at":"2026-08-09T21:29:29.235556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.216388Z","title":"From coupled oscillators to graph neural networks: Reducing over-smoothing via a kuramoto model-based approach","venue":null,"work_id":"66f07ca4-7722-447d-ad1f-0ca4b812693f","year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.943397Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:c98f349a986428a16c51f10c490f2d61e3a6dc64a971c5208f54347428140593","observation_id":"5c717ec6-1d45-4e53-a077-91f265df992e","resolution":{"observed_at":"2026-08-09T21:29:29.221048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.202712Z","title":"Graph neural ricci flow: Evolving feature from a curvature perspective","venue":null,"work_id":"8e572f4f-8c90-4168-ac5a-d5ba2b5ee97a","year":2025},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.947716Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:5ba939b00d94381d51d31290a96eb1948dd1dfe95ff99df64d6a05bae66e6625","observation_id":"19c3c4fa-7c07-48d8-a9c8-fac9ed1fc7a8","resolution":{"observed_at":"2026-08-09T21:29:29.207185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.188040Z","title":"Lectures on network systems, volume 1","venue":null,"work_id":"dc56b9d5-e755-40d7-b7fb-b2ed5dcf3182","year":2018},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.952349Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:3f474c4da3f3d1dd0be004db88e6fd7007a7017a13601a9e7efebd868454d009","observation_id":"72bf67ac-f88a-49d0-b36a-138f40a2f178","resolution":{"observed_at":"2026-08-09T21:29:29.192782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.173663Z","title":"Natural frames and interacting particles in three dimensions","venue":null,"work_id":"76961f4d-0667-44f9-8439-bd68b7e45ea4","year":2005},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.956488Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:9a8da75f27c9d91581eddede4f4d379421dd3165d9280a7d6b497c308a9f9e7f","observation_id":"f33221a8-c737-4387-b72d-87bb35b64688","resolution":{"observed_at":"2026-08-09T21:29:29.178330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.158537Z","title":"Coordinated control of an underwater glider fleet in an adaptive ocean sampling field experiment in monterey bay","venue":null,"work_id":"cd9f7f80-7566-4f13-9d2e-23654a1764d1","year":2010},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.961569Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:8586cab981025223eefb5c381d44dd3e63c6f93a3f9ffa3dfef55ff765e563b0","observation_id":"5fd8261c-7140-4a66-895a-337286111403","resolution":{"observed_at":"2026-08-09T21:29:29.163679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.143558Z","title":"Collective motion, sensor networks, and ocean sampling","venue":null,"work_id":"fb68e840-c891-41e0-bbed-1f3b54bb03b2","year":2007},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.965773Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:21a4a9c33e670556d6e94ddb6f3e404a8f887b8986b41163905861dc10387b8e","observation_id":"0b1b42f9-5181-4139-8c67-8e42e5470d9b","resolution":{"observed_at":"2026-08-09T21:29:29.148006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.128593Z","title":"Interaction ruling animal collective behavior depends on topological rather than metric distance: Evidence from a field study","venue":null,"work_id":"d3461898-38a4-4fa2-a545-a2bbc2441bae","year":2008},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.970617Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:8eee7857f46783dddfdc29b97277e9cc23352ea3dacf070db844dff54c0b47b9","observation_id":"b3d93279-6721-4c11-8347-a0e29ea75a40","resolution":{"observed_at":"2026-08-09T21:29:29.133363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.113384Z","title":"Odnet: Opinion dynamics-inspired neural message passing for graphs and hypergraphs.Transactions on Machine Learning Research, 2024","venue":null,"work_id":"452d6f7b-e2a8-48a0-bb8e-ceb2f8eed629","year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.974823Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:21213ce31603a4f92d1abd661b238772ba074c3e2e1cfd87360854fdc28b0e98","observation_id":"5b2c751b-77a2-42ab-9462-c83b31ea0bf1","resolution":{"observed_at":"2026-08-09T21:29:29.118970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.099682Z","title":"Consensus problems on networks with antagonistic interactions","venue":null,"work_id":"a4b8c224-84bf-427c-8ce4-75feb1b0e32d","year":2012},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.978842Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:f98f907e287dbee5af3f189cf79b30635463c0b80ade6d36fa15e0c05730d07e","observation_id":"079ca40c-0343-43aa-9c82-df7634333f38","resolution":{"observed_at":"2026-08-09T21:29:29.104075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.085138Z","title":"Biased assimilation, homophily, and the dynamics of polarization","venue":null,"work_id":"df6861a2-d9f5-4ee4-b1d7-c7044562c5c8","year":2013},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.983872Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:d9221a272b92ac952ab8bc978c3386e05c1c09aa961c697a5de103bc5e9e0150","observation_id":"f0ac6e61-c44c-4590-a891-961baa778760","resolution":{"observed_at":"2026-08-09T21:29:29.089830Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:27.988098Z","title":"Springer Science & Business Media, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.988098Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:ce2225b87d770fed454c7b41048ebfc27fab528052858c904134d3c9ef6b5252","observation_id":"0cc1551e-d991-4c6e-a694-73129edc428b","resolution":{"observed_at":"2026-08-09T21:29:27.988098Z","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":"2026-08-09T21:29:29.061876Z","title":"The nonlinear feedback dynamics of asymmetric political polarization","venue":null,"work_id":"0cbc4f60-8d67-4e90-ab01-f0a6b3135c07","year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.992173Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:1b0d8610a565ac657d1e35308254f0236804043be26ccfe3cc87a140baf5bdb6","observation_id":"b95fec96-3a7e-4ddc-9caa-f1d87f31602b","resolution":{"observed_at":"2026-08-09T21:29:29.066504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:29.047475Z","title":"Active risk aversion in sis epidemics on networks","venue":null,"work_id":"e8be4fff-a6d8-4776-8d62-bbf6464996b9","year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:27.997142Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:ee02b7d68ba1bc7245b23fd590f5c1231c0c3a03568a24484497e1d1525f5bfd","observation_id":"1eb5fa15-1abc-419d-8c7a-46784788479e","resolution":{"observed_at":"2026-08-09T21:29:29.051853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12993","last_updated":"2025-03-18T20:06:24Z","snapshot_observed_at":"2026-08-09T23:15:28.002642Z","submitted_at":"2024-10-16T19:39:28Z","title":"Opinion-driven risk perception and reaction in SIS epidemics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12993","snapshot_observed_at":"2026-08-09T21:29:28.001349Z","title":"Opinion-driven risk perception and reaction in sis epidemics","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.001349Z"},"links":{"cited_paper":"/paper/2410.12993","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:e31f1aa96c473b2759a3137acbbe4148857eb66e7ebfefc2f0dc7294675f59aa","observation_id":"466c9eaf-e7c6-4821-b909-3dfe23c039d3","resolution":{"observed_at":"2026-08-09T21:29:28.001349Z","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":"2026-08-09T21:29:29.033467Z","title":"Opinion dynamics for decentralized decision-making in a robot swarm","venue":null,"work_id":"a697d9a6-fc0a-4003-9524-14787057bcdd","year":2010},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.006636Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:eedeaff34adb6621a7abbeeebae0a24ac418b03705326ea6a99726da27aa09d0","observation_id":"af1716a5-9163-4606-ac88-262490ca1afc","resolution":{"observed_at":"2026-08-09T21:29:29.037966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14746","last_updated":"2025-03-11T05:00:19Z","snapshot_observed_at":"2026-07-31T08:41:27.589791Z","submitted_at":"2024-06-20T21:36:54Z","title":"Behavior-Inspired Neural Networks for Relational Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14746","snapshot_observed_at":"2026-08-09T21:29:28.010734Z","title":"Behavior-inspired neural networks for relational inference","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.010734Z"},"links":{"cited_paper":"/paper/2406.14746","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:79f3d10ba667887a0d45e7055b4a1611bb7bfd67f20849db578aad530a9ec240","observation_id":"6b7f280d-4277-44fa-9acf-e68de7546f3f","resolution":{"observed_at":"2026-08-09T21:29:28.010734Z","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":"2026-08-09T21:29:28.015812Z","title":"Neural message passing for quantum chemistry","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.015812Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:eda332926511a6780e16e65058369d5ae4ccec65d42b98c4175fc835d3b6374e","observation_id":"4f41e553-3104-467d-8911-9f347b3586e5","resolution":{"observed_at":"2026-08-09T21:29:28.015812Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10993","last_updated":"2023-03-20T10:21:29Z","snapshot_observed_at":"2026-08-10T02:14:11.377359Z","submitted_at":"2023-03-20T10:21:29Z","title":"A Survey on Oversmoothing in Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10993","snapshot_observed_at":"2026-08-09T21:29:28.020175Z","title":"A survey on oversmoothing in graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.020175Z"},"links":{"cited_paper":"/paper/2303.10993","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:653869de96769d23587edf8b26cf8d26339e99be7091935a69ffdec342b26918","observation_id":"118c5610-37cf-4c97-a86c-74b054c6dba1","resolution":{"observed_at":"2026-08-09T21:29:28.020175Z","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":"2026-08-09T21:29:29.011075Z","title":"Continuous graph neural networks","venue":null,"work_id":"42b6567d-167b-4dfe-80fa-f0e0174a84ed","year":2020},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.024907Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:9fa0d4228558e3d6077cea548805a864430265c1045020f8831126dfb05d70c9","observation_id":"282fb88e-e8cc-431c-9f79-4e3a6e6af4e8","resolution":{"observed_at":"2026-08-09T21:29:29.015599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.13318","last_updated":"2020-06-23T20:36:56Z","snapshot_observed_at":"2026-07-06T09:32:05.177891Z","submitted_at":"2020-06-23T20:36:56Z","title":"A Note on Over-Smoothing for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.13318","snapshot_observed_at":"2026-08-09T21:29:28.029182Z","title":"A note on over-smoothing for graph neural networks","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.029182Z"},"links":{"cited_paper":"/paper/2006.13318","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:f65c857c46d1f4b199668baa2a39bb3cea5f9ce94393a3dfdac89228f368ad65","observation_id":"7c1dd11d-f251-450a-be81-7e53bbfc13bf","resolution":{"observed_at":"2026-08-09T21:29:28.029182Z","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":"2026-08-09T21:29:28.034300Z","title":"Reaching a consensus","venue":null,"work_id":null,"year":1974},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.034300Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:29b0879b8595ddde423a9ac1abda1379896954638ce5af0bd81d7d5ed270eef6","observation_id":"37be1723-af6a-46a1-a646-e1d07d378194","resolution":{"observed_at":"2026-08-09T21:29:28.034300Z","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":"2026-08-09T21:29:28.987576Z","title":null,"venue":null,"work_id":"1212f587-baab-4dd5-a2d9-ed4a0a48afc7","year":2005},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.038412Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:f2a312031b6fc331ab0cadd0cd0a78c8fc40bb911ece769ef9e2efb01c3a2c6f","observation_id":"90f43340-cc6b-415f-a53b-a12b081fb941","resolution":{"observed_at":"2026-08-09T21:29:28.991673Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.973124Z","title":"On convergence rate of weighted-averaging dynamics for consensus problems","venue":null,"work_id":"2bc5310e-4a99-4d5f-b05b-cad048df937b","year":2017},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.042595Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:3961187286a220c9a8f6882f0425dbc3b8e3c07f8ec36228eacf6e591277dda9","observation_id":"9bee0713-195d-442f-bde4-683ded0b1520","resolution":{"observed_at":"2026-08-09T21:29:28.977691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.958952Z","title":"Information flow and cooperative control of vehicle formations","venue":null,"work_id":"21f6534b-8eaa-444f-b9e7-1514df5008c7","year":2004},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.046573Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:e13097be16e536299f5b6ff9591737cb4d9c1b710d558c47f011a4b0d950c15c","observation_id":"eb61b131-b08e-4428-92e6-0f6b8c747884","resolution":{"observed_at":"2026-08-09T21:29:28.963433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.944303Z","title":"Convergence in multiagent coordination, consensus, and flocking","venue":null,"work_id":"10f3103f-4e11-4992-b36c-dbe3e3d485f7","year":2005},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.050623Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:24266541c510e9a87e4be902a2c1f9d8a6e376a7671e41f12adb002401959c68","observation_id":"5d0cf567-9e4b-41c2-aba6-07d406d485c3","resolution":{"observed_at":"2026-08-09T21:29:28.948959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.929028Z","title":"Proactive opinion- driven robot navigation around human movers","venue":null,"work_id":"4de0a2d8-3bde-4288-8756-c1f5fae2f2fc","year":2023},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.054921Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:477da4beb85adc6102406f8d8785e447b6eb965798ca6de3ff655af77e5903aa","observation_id":"288e1128-2fa4-42a0-bb2a-f8782a53b66b","resolution":{"observed_at":"2026-08-09T21:29:28.933612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.059664Z","title":"Simplifying graph convolutional networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.059664Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:17e78b8cd3c3046455f066caf5126ca85241f6f037bf964de17aae4f64163d4b","observation_id":"d4b087d7-c175-41ab-8e1b-2f283a2fdc1c","resolution":{"observed_at":"2026-08-09T21:29:28.059664Z","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":"2026-08-09T21:29:28.904961Z","title":"Dissecting the diffusion process in linear graph convolutional networks","venue":null,"work_id":"2983bae3-a82d-404f-a4d2-1aed2ee90336","year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.064014Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:ab2052ccd21af9b577229ca0b07532c3dff32b4ffd139d61048fe91d6702bcd7","observation_id":"d04bf323-9c9e-48cb-9666-f2f95e98621b","resolution":{"observed_at":"2026-08-09T21:29:28.910037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16780","last_updated":"2023-05-30T12:25:39Z","snapshot_observed_at":"2026-07-06T15:33:49.583359Z","submitted_at":"2023-05-26T09:47:03Z","title":"Graph Neural Convection-Diffusion with Heterophily","version":2},"cited_work":{"arxiv_id":"2305.16780","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.16780","snapshot_observed_at":"2026-08-09T21:29:28.420505Z","title":"Graph Neural Convection-Diffusion with Heterophily","venue":"cs.LG","work_id":"a0ceca7d-8ff1-4873-8ccb-81ba67bfa12d","year":2023},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.068809Z"},"links":{"cited_paper":"/paper/2305.16780","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:237a4df2003cded0f39c931c6caec290351a0865ad575ea8f42cde6fa8a297b1","observation_id":"7be01041-2889-464a-ba2a-6b5cb4296860","resolution":{"observed_at":"2026-08-09T21:29:28.427794Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.16092","last_updated":"2023-12-20T07:43:53Z","snapshot_observed_at":"2026-08-06T12:11:22.080883Z","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":"2026-08-09T21:29:28.073260Z","title":"Adr-gnn: advection-diffusion-reaction graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.073260Z"},"links":{"cited_paper":"/paper/2307.16092","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:53bcaf8d8e4d4ce19ed9a5808cee2f86b2de100666881ac1afb25616eb2954b9","observation_id":"29f7ea65-85c3-48fd-a2ae-3930ba45f87c","resolution":{"observed_at":"2026-08-09T21:29:28.073260Z","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":"2026-08-09T21:29:28.078400Z","title":"On the difficulty of training recurrent neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.078400Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:d62bf25140013c147b39ca1e8fdec459838fac04e23376d05352c3ac256bbed1","observation_id":"089cbd12-284e-45a9-8d6c-611c92da7706","resolution":{"observed_at":"2026-08-09T21:29:28.078400Z","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":"2026-08-09T21:29:28.880991Z","title":"A convergence analysis of gradient descent on graph neural networks","venue":null,"work_id":"336311e3-900d-4d43-b353-2d2f3610dd2d","year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.083360Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:a8bed65e51691b75588f68e17cefd118f3093d24e6f5690124706848db9b0450","observation_id":"d6b286c3-ddba-4491-8275-dbf932c3964f","resolution":{"observed_at":"2026-08-09T21:29:28.885614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.088211Z","title":"On vanishing gradients, over- smoothing, and over-squashing in gnns: Bridging recurrent and graph learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.088211Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:e2c0ac558757ea2086e0531d9cb7d10f44d61272b33f570df2a554b0df79d102","observation_id":"f67d3d3e-6ce5-4ce5-bb6e-7885642f4a76","resolution":{"observed_at":"2026-08-09T21:29:28.088211Z","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":"2026-08-09T21:29:28.865880Z","title":"Beyond low-frequency information in graph convolutional networks","venue":null,"work_id":"f5218729-7a9f-4b10-a317-536f46ce428c","year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.092458Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:1842849ca1c9c146571f495d3d262eefadb2022d84988b8040068e3533ce6f8b","observation_id":"822887e8-d40b-43c5-885a-cfbeca37f151","resolution":{"observed_at":"2026-08-09T21:29:28.871190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.850493Z","title":"Analyzing the expressive power of graph neural networks in a spectral perspective","venue":null,"work_id":"01f5ad64-55eb-4e88-abf5-108824046c39","year":2021},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.097141Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:f3b362d4c69d8083698e0969654d8bff7834155207979649d9b217297248746d","observation_id":"606131b2-2f0c-459f-be5c-9a5436149ec4","resolution":{"observed_at":"2026-08-09T21:29:28.855513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.101216Z","title":"Automating the construction of internet portals with machine learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.101216Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:c5a4b9ab7d02ed5aef1d531dd3318710610c996e29fb689b2603b50fc0b8902a","observation_id":"0698c5e3-464f-44e7-a632-5efa632b275f","resolution":{"observed_at":"2026-08-09T21:29:28.101216Z","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":"2026-08-09T21:29:28.106020Z","title":"Collective classification in network data","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.106020Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:3145548915e067c3b02adbc0f2a7832fd8f73bffb21c887699868ef2859b9397","observation_id":"05118520-343d-41f6-a985-964db3dc6a91","resolution":{"observed_at":"2026-08-09T21:29:28.106020Z","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":"2026-08-09T21:29:28.817381Z","title":"Query-driven active surveying for collective classification","venue":null,"work_id":"16062bb5-3435-4e98-b3f4-799e3dbd64f4","year":2012},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.110271Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:3cd84d8d68294f8457198dd6b585091b9353a7fd159a4156eede12b6db9c0da7","observation_id":"8aa65370-8800-4c2c-af04-50dc3a2fa23b","resolution":{"observed_at":"2026-08-09T21:29:28.822499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05868","last_updated":"2019-06-18T13:15:39Z","snapshot_observed_at":"2026-07-06T07:14:41.761512Z","submitted_at":"2018-11-14T15:53:19Z","title":"Pitfalls of Graph Neural Network Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.05868","snapshot_observed_at":"2026-08-09T21:29:28.115138Z","title":"Pitfalls of graph neural network evaluation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.115138Z"},"links":{"cited_paper":"/paper/1811.05868","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:f4172a2a156ef957a41754a0f06d07d689980f37d60a1f9c066664317d359a99","observation_id":"02c662f4-2587-421f-add5-6843c8e9753a","resolution":{"observed_at":"2026-08-09T21:29:28.115138Z","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":"2026-08-09T21:29:28.803334Z","title":"Learning to extract symbolic knowledge from the world wide web.AAAI/IAAI, 3(3.6):2, 1998","venue":null,"work_id":"b14b402f-854b-42ec-aff3-2eec8c21bd1d","year":1998},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.119576Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:9e576ddba1d002c04e029fa036b43df627a4832170fd4c451f093d37b8a2440d","observation_id":"fc13a07c-e88a-4276-890c-73df866e3dce","resolution":{"observed_at":"2026-08-09T21:29:28.807892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.124424Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.124424Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:f100308eef5e72be7d160cff8c07a2ce3a4ad7e3d57ff68d13558f72ce232eca","observation_id":"8020a674-b598-4423-969a-dfdb435430ad","resolution":{"observed_at":"2026-08-09T21:29:28.124424Z","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":"2026-08-09T21:29:28.778096Z","title":"Matrix differential calculus with applications in statistics and econometrics","venue":null,"work_id":"a8c282b7-7482-44b6-9227-eac6dcf77bf4","year":2019},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.128804Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:414a720fcfa7455c3a9af8ce590612d92b0a79f38d08bf5ab943a422df5dffbc","observation_id":"cedf3e25-f1c9-4ebe-8839-260c508a2deb","resolution":{"observed_at":"2026-08-09T21:29:28.783601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.760912Z","title":"Systems of differential equations that are competitive or cooperative ii: Convergence almost everywhere","venue":null,"work_id":"c01f2fdd-c4f2-4c15-a86e-2478ed45d2dd","year":1985},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.133621Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:f813ce0d1957098e8451ddc6375c9b325ae67094f16815cb0e0985c959a251f2","observation_id":"4c33e68c-bea4-4f7a-8719-d52d01b831f6","resolution":{"observed_at":"2026-08-09T21:29:28.767276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T21:29:28.137939Z","title":"Image-based recommendations on styles and substitutes","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.137939Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:959e298e1c2f81ef0c2d38547b1c36bd4fb6576f2018dd3777a86e7833a1c4e5","observation_id":"6ec29272-e4c2-4f88-b227-0ea824e59a7c","resolution":{"observed_at":"2026-08-09T21:29:28.137939Z","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":"2026-08-09T21:29:28.737118Z","title":"Diffusion-convolutional neural networks","venue":null,"work_id":"0d0c1ca6-4ef7-4588-975a-373ec638334e","year":2016},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.142982Z"},"links":{"citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:8903ee783cb594939a5a26b6c4360eddcf393c25f6c6233cb6c6b1f93fbf382f","observation_id":"39e45667-0539-4cb0-af99-8d7fcb6defa7","resolution":{"observed_at":"2026-08-09T21:29:28.742623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.05118","last_updated":"2018-07-13T15:00:17Z","snapshot_observed_at":"2026-07-06T06:50:03.471843Z","submitted_at":"2018-07-13T15:00:17Z","title":"Tune: A Research Platform for Distributed Model Selection and Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.05118","snapshot_observed_at":"2026-08-09T21:29:28.147348Z","title":"Tune: A research platform for distributed model selection and training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-09T21:29:28.147348Z"},"links":{"cited_paper":"/paper/1807.05118","citing_paper":"/paper/2501.19089"},"observation_digest":"sha256:f1f034754cd0738fc4d8a0888d55249098695c870ca16a64ffb869ffeb77fa49","observation_id":"c3782279-124e-4144-8e52-45cf2f0fc219","resolution":{"observed_at":"2026-08-09T21:29:28.147348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.19089","last_updated":"2025-05-16T21:51:27Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T06:37:19.673594Z","submitted_at":"2025-01-31T12:34:09Z","title":"Resolving Oversmoothing with Opinion Dissensus"},"reference_resolution":{"displayed":95,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":50,"verified_exact":3,"verified_fuzzy":42},"total_outbound_references":95},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 2 inbound Pith citation observations for arXiv:2501.19089."}