{"as_of":"2026-08-15T05:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c735a4e32f2341028d461f35f05885c37c2be338f1cc5b543233c8bbccb1ed07","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T14:25:55.903357Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.09596/citation-record","integrity":"/paper/2608.09596/integrity","json":"/paper/2608.09596/citation-record.json","paper":"/paper/2608.09596"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:25:56.474416Z","title":"Enhancing 5G radio planning with graph representations and deep learning,","venue":null,"work_id":"91e5d392-ad34-443a-93d7-8a3c122fe620","year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.733566Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:839069813fa8e0969b1be0104bf913a3181197f81fa966398925e76f862f9ea7","observation_id":"41ded3ec-59fb-4993-90d6-33f132ae1e0a","resolution":{"observed_at":"2026-08-11T14:25:56.479654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.458774Z","title":"Fault detection in telecom networks using bi- level federated graph neural networks,","venue":null,"work_id":"2ca3facf-193a-4824-8286-506fec7c71a9","year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.739028Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:365086638d5b092bcce50e197128743000a401edaf62f2fb95318df5c9a8303e","observation_id":"51caada9-05ed-486c-9c7c-dd8ca08ae882","resolution":{"observed_at":"2026-08-11T14:25:56.463615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-13T11:38:10.906031Z","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":"2026-08-11T14:25:55.744343Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.744343Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:18f7e4b738ece0d1055fadf6380c254986f2b0136cb12814630d8f6d6b71ffbc","observation_id":"8ab69480-9986-48ce-a372-b687ebe0c8d5","resolution":{"observed_at":"2026-08-11T14:25:55.744343Z","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":"2026-08-11T14:25:56.443658Z","title":"Graph neural networks in computer vision - architectures, datasets and common approaches,","venue":null,"work_id":"10e919aa-ac43-4d10-8402-f7cd80965e45","year":2022},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.750126Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:d5607824baf666dc873789154c147538ccf3dc9c1308e2699dc0411ae56f454d","observation_id":"8d8ba2a0-d873-4484-9a1f-48a46752be71","resolution":{"observed_at":"2026-08-11T14:25:56.448745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.428189Z","title":"Improving expressivity of GNNs with subgraph-specific factor embedded normalization,","venue":null,"work_id":"9e4d68fc-2804-4062-a9cc-6b601110e22b","year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.755363Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:e166d75c8a5b095968fb59d8e2c96bce55ecee122603fd10f917c6cc9e0b609f","observation_id":"6eb0257a-784e-4bc4-b94a-77fdbd3e9d79","resolution":{"observed_at":"2026-08-11T14:25:56.433544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10993","last_updated":"2023-03-20T10:21:29Z","snapshot_observed_at":"2026-08-13T12:20:52.753435Z","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":"2026-08-11T14:25:55.761377Z","title":"A survey on over- smoothing in graph neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.761377Z"},"links":{"cited_paper":"/paper/2303.10993","citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:7c34d61f9bb8ed221d364ba18e77607b04b12f20525853700cedcb28595a8087","observation_id":"91b371da-e5bc-4d1e-968f-bac1aad5fb31","resolution":{"observed_at":"2026-08-11T14:25:55.761377Z","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":"2026-08-11T14:25:56.412452Z","title":"Over-squashing in graph neural networks: A comprehen- sive survey,","venue":null,"work_id":"1cb00762-ebb7-4c88-99ea-7a5994ea8dab","year":2025},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.769115Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:17b79a8d563c199ae99563350f6481a504049184d48aca00c07229ba90e1d412","observation_id":"6eee5f3e-513e-47ed-bab4-583e91755436","resolution":{"observed_at":"2026-08-11T14:25:56.417511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.397490Z","title":"Simplifying graph convolutional networks,","venue":null,"work_id":"20d08bf3-93cb-4b22-8a40-4dbed20284a8","year":2019},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.778037Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:832b9d0b86f2289ebd03f9ad8d8aa3c79ab568122f6741926d3f89d7674dd216","observation_id":"1c215584-d8fa-4db2-8242-65d63ddae42c","resolution":{"observed_at":"2026-08-11T14:25:56.402618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10947","last_updated":"2021-01-06T13:32:14Z","snapshot_observed_at":"2026-08-14T22:01:14.568901Z","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":"2026-08-11T14:25:55.782602Z","title":"Graph neural networks exponentially lose expressive power for node classification,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.782602Z"},"links":{"cited_paper":"/paper/1905.10947","citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:807a0fa0181aa901a800540c8f617b3ff12287dcc09add5396c29829605ba633","observation_id":"920877d1-b75a-4839-9a5a-8b69bbc67627","resolution":{"observed_at":"2026-08-11T14:25:55.782602Z","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":"2026-08-11T14:25:56.381702Z","title":"Bag of tricks for training deeper graph neural networks: A comprehensive benchmark study,","venue":null,"work_id":"d7f8eed2-e661-4809-9530-07c4d1ae5229","year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.787792Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:59e1896ab6e99605a854c1babdf64244fc609d13fc79be902471a0d21c81a838","observation_id":"e68326cb-fd47-42e5-9ac2-6f57357f6fcd","resolution":{"observed_at":"2026-08-11T14:25:56.386750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.366257Z","title":"Gradient rewiring for editable graph neural network training,","venue":null,"work_id":"224c5878-ca42-47cf-9dd8-4a92836c6f52","year":2024},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.792345Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:fccb543cb9035f1ab4eb94e52aa0795dfd672497160a5a217efa87f2800f8309","observation_id":"51607ce5-7f52-4344-9b7f-2c72de9a4c0a","resolution":{"observed_at":"2026-08-11T14:25:56.371102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.350488Z","title":"Dirichlet energy constrained learning for deep graph neural networks,","venue":null,"work_id":"cf29791b-6465-41a4-a8b6-18870f9d3802","year":2021},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.796973Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:cd953847ed358fa7f7a09ad5efd4fead30bf1f579d3da4829eb8f85b4f5cb7e6","observation_id":"32ca3eda-df76-43b4-a4d3-6eade5fe2ac3","resolution":{"observed_at":"2026-08-11T14:25:56.355471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.334327Z","title":"Rewiring techniques to mitigate oversquashing and oversmoothing in GNNs: A survey,","venue":null,"work_id":"c2b6f30b-5dd6-401a-befc-8267b2477c95","year":2024},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.801455Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:e7e019557180a27d4140f6fa4aa8d83f9b9c98e5d9b99e3be90ba15c4126ad0c","observation_id":"391a7e70-4132-47ea-bd6b-ec5af85a8e70","resolution":{"observed_at":"2026-08-11T14:25:56.339352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.318844Z","title":"Reverse graph learning for graph neural network,","venue":null,"work_id":"72c942c9-a277-44d5-85ab-8386d62756a7","year":2024},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.806071Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:f093de59d1c514d07bf21d4b3239565ed97ccb5e1586940889437f02fe8c4ecc","observation_id":"44e191eb-0b6f-4947-8442-4fe7c51bb13d","resolution":{"observed_at":"2026-08-11T14:25:56.324042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.302476Z","title":"Self-supervised node representation learning via node-to-neighbourhood alignment,","venue":null,"work_id":"3d02a6dc-9425-4cfb-a931-1f70a2f3187e","year":2024},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.810698Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:b6b31f43b0469e425095e9994682d558dbbd71c8d41616f71d4226ddde5b8432","observation_id":"fa1d2b4e-02b7-41fb-a3d4-4c1b11062bf7","resolution":{"observed_at":"2026-08-11T14:25:56.307848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.288029Z","title":"Rewiring with positional en- codings for graph neural networks,","venue":null,"work_id":"639c3d8c-a7c6-4763-ac5f-0ff0b608fe98","year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.815265Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:89c835471f1c6e16c028224ac0e4f380cfa5bfef4f4a8fe5970132ccdd1a0df2","observation_id":"c63a74c3-d399-475b-b8cf-ad00c2cb7f9f","resolution":{"observed_at":"2026-08-11T14:25:56.292687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.273742Z","title":"Tudataset: A collection of benchmark datasets for learning with graphs,","venue":null,"work_id":"5f9f0d24-e0b7-4fe1-839f-47f9922c73f8","year":2020},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.820259Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:e99ab6a01f14f97d48e68c3e9887185d8ccd5a89dc8a8cf9dd0f6367bb61070c","observation_id":"d3bcd510-8e2b-4cd1-ae95-2e4c3309ad46","resolution":{"observed_at":"2026-08-11T14:25:56.278456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.258426Z","title":"Graph attention networks,","venue":null,"work_id":"4b2f2124-f9fe-41ab-9c18-42b2af21d579","year":2018},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.824745Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:32e0ec592f6e2d1ddb41550f0adaa4e81b540a7bd159ac363660f49aed64e28e","observation_id":"2f4c52d4-179f-4456-9780-d6da300580d3","resolution":{"observed_at":"2026-08-11T14:25:56.263285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.243061Z","title":"measuring and relieving the over-smoothing problem for graph neural networks from the topological view,","venue":null,"work_id":"725df861-ff75-4cd6-8475-ca0f30aedf4c","year":2020},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.829037Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:95640124a2440ee01f8b74821e7818fd782af7eb8a6edcc27b05bc2571816d01","observation_id":"0e360cb7-d6e7-48a1-80b7-d8b94e3c063e","resolution":{"observed_at":"2026-08-11T14:25:56.248021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.227758Z","title":"On the trade- off between over-smoothing and over-squashing in deep graph neural networks,","venue":null,"work_id":"cbebc8ca-784f-4de4-8d40-5e7321908eb3","year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.833514Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:574065091c3927322331c66ed6b8911fae1139c2bd7b7b65315624ec09d2f7e5","observation_id":"bbde6e8c-6900-478e-b7bf-1d541bdc0cba","resolution":{"observed_at":"2026-08-11T14:25:56.232825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.210787Z","title":"un- derstanding virtual nodes: oversquashing and node heterogeneity,","venue":null,"work_id":"7d6d517c-d9f5-46f0-b192-6353bb3a5c3d","year":2025},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.838368Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:6b211143419d598c0e8b472f6aab407d0acb7e8fa8e835d877daac08b58cde4f","observation_id":"ecb0cd7c-b64a-4069-98b0-fb36f780724c","resolution":{"observed_at":"2026-08-11T14:25:56.216332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.194910Z","title":"On the connection between MPNN and graph transformer,","venue":null,"work_id":"23a8394c-3a09-4efe-8a82-77feaaf4c01a","year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.843334Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:f597ce15e484ef2f886e3072d7a5d18b0eca20e4b38d8225d89fe47cedbc5fcd","observation_id":"903db435-33b4-4f22-9b24-6626cb8c59a3","resolution":{"observed_at":"2026-08-11T14:25:56.199982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.179127Z","title":"Fast and distributed equivariant graph neural networks by virtual node learning,","venue":null,"work_id":"85381e3c-22e0-43da-aed7-ceb388559141","year":2026},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.848095Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:fcda08bf89474d589ed383356600c0de17f5b85530893a1b247994631a6455dd","observation_id":"4b8dd9a1-5d58-49ef-a5c5-c520c6d79e08","resolution":{"observed_at":"2026-08-11T14:25:56.184122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.163088Z","title":"Mitigating over-smoothing and over- squashing using augmentations of forman-ricci curvature,","venue":null,"work_id":"24197e9b-c4a2-43d3-89f8-8ea2efd30d69","year":2024},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.852680Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:c23d22d1b6eea9c6de4981884a7082ee421d92bfc8137443ee0f08b68c2bfb23","observation_id":"a03d6c4e-6f16-4323-88af-181689b995f5","resolution":{"observed_at":"2026-08-11T14:25:56.167941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.14522","last_updated":"2022-11-12T16:11:19Z","snapshot_observed_at":"2026-08-14T07:38:21.479705Z","submitted_at":"2021-11-29T13:27:56Z","title":"Understanding over-squashing and bottlenecks on graphs via curvature","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.14522","snapshot_observed_at":"2026-08-11T14:25:55.857074Z","title":"Un- derstanding over-squashing and bottlenecks on graphs via curvature,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.857074Z"},"links":{"cited_paper":"/paper/2111.14522","citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:bc67a1e661e2c8a5e2c5ff908d293aede7b2d54ceed91733cd8ce9abcdc584f9","observation_id":"bf02c42b-7a19-4b31-8efb-be3492d7a07e","resolution":{"observed_at":"2026-08-11T14:25:55.857074Z","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":"2026-08-11T14:25:56.147842Z","title":"Cayley graph propagation,","venue":null,"work_id":"7adec1c1-a770-41ab-a803-1be794bce051","year":2025},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.861606Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:d220dac01703ea1940e3ea494ef0e49ab0f72ed540d4aad0abe4ba3cb0ac4312","observation_id":"4b0c6f72-c879-4d8f-b095-f388055e32b6","resolution":{"observed_at":"2026-08-11T14:25:56.152412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.131950Z","title":"Virtual node tuning for few-shot node classification,","venue":null,"work_id":"ffbd990f-6f08-49d1-a507-206be568f4af","year":2023},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.866070Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:46c195c562aac26ed39f6eb139db7189afb432abbe6228d8561395a017e2f5b6","observation_id":"09a8985a-dc5c-4fcd-b55a-282ddc7d5c62","resolution":{"observed_at":"2026-08-11T14:25:56.137077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.116712Z","title":"Topological data analysis in graph neural networks: Surveys and perspectives,","venue":null,"work_id":"49e13a32-5a5d-4776-965d-ee32829982ea","year":2025},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.870459Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:a5ba3ecb368ba1af9e33ea8b8f7b7345b77e54c41a2b3ee6954412a25ec0f59c","observation_id":"e77466fd-95c2-459f-acb0-b6998e4c7e89","resolution":{"observed_at":"2026-08-11T14:25:56.121399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.100338Z","title":"Local virtual nodes for alleviating over-squashing in graph neural networks,","venue":null,"work_id":"c36c5be8-19d8-4a68-95aa-a1b441b26c65","year":2025},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.875180Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:20daa4d6f9d4986fe4768b82463ac3edd2607afb377658810610121e1d76b87f","observation_id":"afd67095-0861-40e5-87b8-ae147f6fa26f","resolution":{"observed_at":"2026-08-11T14:25:56.105750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.083431Z","title":"PANDA: Expanded width-aware message passing beyond rewiring,","venue":null,"work_id":"14d9f39e-9f08-46f2-be2f-22dbea203544","year":2024},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.880269Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:8c58da8cbc10af9d99b219051f528bdde75f4bbdd76d7c8e00696ef5cc7f13ef","observation_id":"f4ef483f-33ef-40f8-9bc0-29889c84a3f0","resolution":{"observed_at":"2026-08-11T14:25:56.088626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.067236Z","title":"Understanding oversmoothing in diffusion-based GNNs from the perspective of operator semigroup theory,","venue":null,"work_id":"07ce7ec6-f4eb-4c2b-92b5-3c0484cc9b56","year":2025},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.884778Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:c691e086755c5ba620809ccf2bd9819590661be032a99316b550489a45d3ae9e","observation_id":"e09808e8-672e-4d5b-aee4-86864e35c997","resolution":{"observed_at":"2026-08-11T14:25:56.071886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.051906Z","title":"Enhanced subgraph learning in 2-FWL GNNs via local connectivity, spectral, and distance encodings,","venue":null,"work_id":"041d1e7d-d72b-4664-9677-684505407a07","year":2025},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.889226Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:e06b3b9125b4e65b86eda64487b3c8dc721a7d192027eac5d707c2ed03a19dda","observation_id":"7d43c732-53ce-4438-bc37-597410e32c9b","resolution":{"observed_at":"2026-08-11T14:25:56.057194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.035263Z","title":"Demystifying higher-order graph neural networks,","venue":null,"work_id":"d2c30db2-fbba-4d80-b8e2-51575831b1ac","year":2026},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.893749Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:1fc545798203672db0bf28de4e1575b72124382de087f54f1d4aad734cf325d0","observation_id":"aa7b0c80-eef5-45b8-99c4-05dd280853fc","resolution":{"observed_at":"2026-08-11T14:25:56.040972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.019433Z","title":"Simple spectral graph convolution,","venue":null,"work_id":"a5c6c6e0-7486-4fbe-8f6f-9b227b9d87ce","year":2021},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.898379Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:abfadc2316c2aaa40622607290cc6f8cf148b2b683c34a59b5aca828aa691726","observation_id":"ef0cc86a-bb57-4682-9a42-11edb7ec2b9f","resolution":{"observed_at":"2026-08-11T14:25:56.024635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T14:25:56.000648Z","title":"The effectiveness of curvature- based rewiring and the role of hyperparameters in GNNs revisited,","venue":null,"work_id":"4874a948-49c0-46f2-bcab-455b747c2504","year":2025},"citing_paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T14:25:55.903357Z"},"links":{"citing_paper":"/paper/2608.09596"},"observation_digest":"sha256:ef9221ee568991eb3243814a4f2835e1b7e52cda80a8ee2c9f1111077120ca61","observation_id":"546b7d05-292e-4398-8479-9ce1ca742ccc","resolution":{"observed_at":"2026-08-11T14:25:56.008028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.09596","last_updated":"2026-08-10T13:30:46Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T22:01:33.623668Z","submitted_at":"2026-08-10T13:30:46Z","title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":31},"total_outbound_references":35},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2608.09596."}