{"as_of":"2026-08-11T14:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:538f48246137336f202aa7e40ec1ba4f65670cef14259ca15763251a43a55380","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:10:51.236364Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.06002/citation-record","integrity":"/paper/2501.06002/integrity","json":"/paper/2501.06002/citation-record.json","paper":"/paper/2501.06002"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:10:52.753877Z","title":"The graph neural network model,","venue":null,"work_id":"86d0b8cb-923f-43ce-b0bb-ce2fd2bcade9","year":2008},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.953085Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:d9c163a295ebc2dfd0758cd8c9a843c53ebae644c313df4968cbfa063ce5d5d5","observation_id":"01ca2a29-12f7-47b2-8f9c-f594fe09c860","resolution":{"observed_at":"2026-08-10T21:10:52.759228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","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":"2026-08-10T21:10:50.958726Z","title":"Semi-supervised classifica- tion with graph convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.958726Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:c091afc80036d128e35daf13adc28d53200e6d3776226f1d548e50b64fb5b377","observation_id":"e6970f09-9f0b-495b-861d-a80e44f55629","resolution":{"observed_at":"2026-08-10T21:10:50.958726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.00596","last_updated":"2019-12-04T01:43:00Z","snapshot_observed_at":"2026-08-07T13:22:06.360133Z","submitted_at":"2019-01-03T03:20:55Z","title":"A Comprehensive Survey on Graph Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.00596","snapshot_observed_at":"2026-08-10T21:10:50.964157Z","title":"A comprehensive survey on graph neural networks,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.964157Z"},"links":{"cited_paper":"/paper/1901.00596","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:b94634cc9e55717290030cab08589ed7fdc284b5b0e41c91f623dfedd08f42bb","observation_id":"75f8b84c-04c8-4ce4-8374-ff833d06000f","resolution":{"observed_at":"2026-08-10T21:10:50.964157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06667","last_updated":"2019-06-10T08:35:03Z","snapshot_observed_at":"2026-08-09T17:39:02.416243Z","submitted_at":"2019-02-13T09:58:44Z","title":"Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06667","snapshot_observed_at":"2026-08-10T21:10:50.970761Z","title":"Hierarchical graph convolutional networks for semi-supervised node classification,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.970761Z"},"links":{"cited_paper":"/paper/1902.06667","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:1147aa891b7d213e605373d0e2cee40e998d90aec406e84174f1a3fa9a9540eb","observation_id":"8121eb52-ac5a-4aa9-a852-de4c1a0f3c1c","resolution":{"observed_at":"2026-08-10T21:10:50.970761Z","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":"2026-08-10T21:10:52.736566Z","title":"Message passing neural networks,","venue":null,"work_id":"108b0f4a-870e-47b8-9835-46494dba235e","year":2020},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.976508Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:78e103cef7fbc670dea870bc4db069911bdc51bbc2a52b870f1aae5d686e247b","observation_id":"e5b42db6-adaa-4b73-becf-7646cc23a49b","resolution":{"observed_at":"2026-08-10T21:10:52.742498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.04638","last_updated":"2017-07-14T21:03:53Z","snapshot_observed_at":"2026-08-10T23:40:10.104282Z","submitted_at":"2017-07-14T21:03:53Z","title":"Predicting multicellular function through multi-layer tissue networks","version":1},"cited_work":{"arxiv_id":"1707.04638","doi":null,"metadata_source":"pith","pith_arxiv_id":"1707.04638","snapshot_observed_at":"2026-08-10T21:10:51.518815Z","title":"Predicting multicellular function through multi-layer tissue networks","venue":"cs.LG","work_id":"1f0b9495-39c5-4f0b-9527-05e3a8bdf02e","year":2017},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.982238Z"},"links":{"cited_paper":"/paper/1707.04638","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:ec9cb8f53f6d779a47dfe04cb5a1d6d11c09cc0dcae7195a70441957ddf76aa2","observation_id":"3db6212f-ff58-41f1-997b-61cb8d8a647f","resolution":{"observed_at":"2026-08-10T21:10:51.524887Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.718673Z","title":"Graph-based deep learning for medical diagnosis and analysis: Past, present and future,","venue":null,"work_id":"cdc0915b-ba7f-4242-854b-ad39f6ee8dfe","year":2021},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.988710Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:1c090aaac847d042eb209e8d04f195e58c4c56b1d67c14314e29c06dbe732801","observation_id":"cbc2ed21-f550-439d-b2dc-160d9383a79a","resolution":{"observed_at":"2026-08-10T21:10:52.724517Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.690941Z","title":"Graph neural networks in network neuroscience,","venue":null,"work_id":"0241748e-68fe-4245-83c5-5c9fe534ca3c","year":2015},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.993565Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:cdd20b842e24eb491cdde64589341c5ecb7a28b46d418dd325b674291aff0fd6","observation_id":"2bc66791-d132-420e-9ea3-3b84d5f4bedb","resolution":{"observed_at":"2026-08-10T21:10:52.699373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.622038Z","title":"Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classifica- tion,","venue":null,"work_id":"5c27d4bd-5fc8-4786-bc38-f99d3c875cdc","year":2023},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:50.998369Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:a1db5899c40112a3e7e542e7dba00911d510c6711d4593e8d021c6e40c2b9027","observation_id":"3da781f3-674a-4228-86a7-916932b2eb47","resolution":{"observed_at":"2026-08-10T21:10:52.646076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.594306Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning,","venue":null,"work_id":"59a12f8b-c530-46b7-8afa-59f048ee498d","year":2018},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.003033Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:cbdaa32e6c5c71471779d43e7cff82661c427f6b3be79938c141347477eb5562","observation_id":"e1089a3a-f00d-4cb5-b9f9-ee2e3836aae2","resolution":{"observed_at":"2026-08-10T21:10:52.601100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05205","last_updated":"2021-03-09T11:53:06Z","snapshot_observed_at":"2026-08-06T10:13:00.684351Z","submitted_at":"2020-06-09T12:04:50Z","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05205","snapshot_observed_at":"2026-08-10T21:10:51.008702Z","title":"On the bottleneck of graph neural networks and its practical implications,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.008702Z"},"links":{"cited_paper":"/paper/2006.05205","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:7534192258c0344ea1384378ca8f6fa55c651470881aa6fa1aae21c049707d20","observation_id":"26a2328f-57ca-4f6f-8baa-a2ba7ad81ade","resolution":{"observed_at":"2026-08-10T21:10:51.008702Z","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":"2026-08-10T21:10:52.569232Z","title":"Representing long-range context for graph neural networks with global attention,","venue":null,"work_id":"fb73e415-e73a-4760-b1f5-a6e0e75b989f","year":2021},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.014638Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:e526facc444afec1d4e6987ff6cafd457fcb8031642b725f5af1f0462226d705","observation_id":"7e35c88e-f18f-411a-b9be-5793d8b89c13","resolution":{"observed_at":"2026-08-10T21:10:52.575915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.534058Z","title":"A gnn architecture with local and global-attention fea- ture for image classification,","venue":null,"work_id":"584387e4-4432-465b-b084-e1539b6111d3","year":2023},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.021270Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:6a1781c570aba8719f2d306df6a2b686215b58d58f4cf70eed77742155485c7c","observation_id":"e2c73c8e-309b-454e-b540-c372c109bb0d","resolution":{"observed_at":"2026-08-10T21:10:52.540476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.450477Z","title":"Revisiting over-smoothing and over- squashing using ollivier-ricci curvature,","venue":null,"work_id":"24fa3b43-ec11-405a-85ac-8cbd155ea7aa","year":2023},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.026354Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:edc1f551cf9a7d1fd8764387f90a4ba8591b1410990dfc5b9c981663b03c4752","observation_id":"01614fb6-1fe0-45dc-808a-ef304abda57a","resolution":{"observed_at":"2026-08-10T21:10:52.474754Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01668","last_updated":"2024-05-04T14:53:28Z","snapshot_observed_at":"2026-08-10T07:39:17.907754Z","submitted_at":"2023-10-02T21:59:44Z","title":"Locality-Aware Graph-Rewiring in GNNs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01668","snapshot_observed_at":"2026-08-10T21:10:51.031293Z","title":"Locality-aware graph-rewiring in gnns,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.031293Z"},"links":{"cited_paper":"/paper/2310.01668","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:c97c7f007bf32b906ad3c66da514d8a4ac131d247ebe2086167b72627de1cb8f","observation_id":"b81786cd-cedd-4d5f-9753-22e64675a482","resolution":{"observed_at":"2026-08-10T21:10:51.031293Z","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":"2026-08-10T21:10:51.037036Z","title":"A sur- vey on oversmoothing in graph neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.037036Z"},"links":{"cited_paper":"/paper/2303.10993","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:2adab3c1a60d2c4107c48569a0b3a6b0607976dda476b23783ba2aa6ee03be50","observation_id":"85b237b1-1f71-42ac-aaf4-caa326bb891d","resolution":{"observed_at":"2026-08-10T21:10:51.037036Z","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":"2026-08-10T21:10:52.370639Z","title":"Measuring and relieving the over-smoothing problem for graph neural networks from the topological view,","venue":null,"work_id":"f6528cea-cb25-4d76-88c5-7ec13c613568","year":2020},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.052656Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:c356264927540b9a10a4b469c3365d72171af5fae22afd74bb91f78701ca2a45","observation_id":"1c5fee7b-5327-493f-bccb-c1a57be26152","resolution":{"observed_at":"2026-08-10T21:10:52.392269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.274766Z","title":"On over-squashing in message passing neural networks: The impact of width, depth, and topology,","venue":null,"work_id":"40db03f6-03a0-421c-8faf-c0a8614c1e1f","year":2023},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.064749Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:ea867a82afcd1b92819682de874f640b0e1bb22363ac53270b979a6413b4ef2c","observation_id":"624332bd-c87f-44fd-b8cf-7f58d6d4be85","resolution":{"observed_at":"2026-08-10T21:10:52.294789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.174778Z","title":"Ricci curvature of markov chains on metric spaces,","venue":null,"work_id":"0aaeffd7-5040-4e3d-87e0-d835ab1543e8","year":2009},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.070482Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:b5f26ebc37dd49ba94907d7a9839e89e2d7587f9f2871bd08762ed5d7abedc40","observation_id":"c72ab6c7-70c6-4955-9cab-67d509681953","resolution":{"observed_at":"2026-08-10T21:10:52.217153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:52.024300Z","title":"Ollivier-ricci curvature-based method to community detection in com- plex networks,","venue":null,"work_id":"945368b9-9e76-4701-b82d-40679800ddfe","year":2019},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.075578Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:bcfb849c56c136ebce412225d037cf01ccc562e552283c30c3d02ce8feb96cb2","observation_id":"ea955239-06bd-4c99-bf6d-79e5c1c977fb","resolution":{"observed_at":"2026-08-10T21:10:52.044823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.968736Z","title":"Note on a method for calculating cor- rected sums of squares and products,","venue":null,"work_id":"7ca85b48-8d28-4ca3-96a9-53b2ffdfe4c6","year":1962},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.085581Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:815419e082a3f05764afa44cba23e47fe600243d86aabc6197c8b522279f58be","observation_id":"e3346a81-0a4e-47ba-997c-d885b7a00c0c","resolution":{"observed_at":"2026-08-10T21:10:51.979347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.943346Z","title":"Graph transformer networks,","venue":null,"work_id":"1e706a72-c1fa-4f37-a65b-bc20c7546269","year":2019},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.098293Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:ff572fbc03e69280e0b8347338c65691eb125e0e6ce34343ef560b97fa0c1b43","observation_id":"3aaf1f84-684d-44e5-b27a-89f64746ab9e","resolution":{"observed_at":"2026-08-10T21:10:51.948413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.09699","last_updated":"2021-01-24T09:38:54Z","snapshot_observed_at":"2026-08-05T19:35:00.334774Z","submitted_at":"2020-12-17T16:11:47Z","title":"A Generalization of Transformer Networks to Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.09699","snapshot_observed_at":"2026-08-10T21:10:51.103008Z","title":"A generalization of transformer networks to graphs,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.103008Z"},"links":{"cited_paper":"/paper/2012.09699","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:685dbd1773843fb5c17b00896de9a0b61d659978bbca72ae8dfad89af5222dcb","observation_id":"42b292f9-0c04-479f-aea0-3bf0d4f2f737","resolution":{"observed_at":"2026-08-10T21:10:51.103008Z","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":"2026-08-10T21:10:51.914747Z","title":"Under- standing oversquashing in gnns through the lens of effec- tive resistance,","venue":null,"work_id":"f2f3cdda-8493-464d-85d5-010d07e83cea","year":2023},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.107712Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:a76f266bec0998cbeec0b0f2d1efe287b43745fbb60c7acb0f67491c3082ddcb","observation_id":"8758fbfd-36b5-4817-8cec-58099d8f360b","resolution":{"observed_at":"2026-08-10T21:10:51.930168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.07369","last_updated":"2022-11-30T19:11:11Z","snapshot_observed_at":"2026-08-09T02:19:27.431872Z","submitted_at":"2022-06-15T08:22:07Z","title":"DiffWire: Inductive Graph Rewiring via the Lov\\'asz Bound","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.07369","snapshot_observed_at":"2026-08-10T21:10:51.112871Z","title":"Diffwire: Inductive graph rewiring via the lov\\’asz bound,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.112871Z"},"links":{"cited_paper":"/paper/2206.07369","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:656a5348182af8c2edda3951953322f1c192c448fcff25f4b2556de7ce7525ad","observation_id":"03b0a4d0-56e7-4255-8fb1-64f35e6906fd","resolution":{"observed_at":"2026-08-10T21:10:51.112871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.11790","last_updated":"2023-02-16T03:22:54Z","snapshot_observed_at":"2026-07-06T14:08:34.026927Z","submitted_at":"2022-10-21T07:58:03Z","title":"FoSR: First-order spectral rewiring for addressing oversquashing in GNNs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.11790","snapshot_observed_at":"2026-08-10T21:10:51.118025Z","title":"Fosr: First-order spectral rewiring for addressing oversquash- ing in gnns,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.118025Z"},"links":{"cited_paper":"/paper/2210.11790","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:9ae13cb7fb4163e905c5a66530ced07fa5b76a680d87d68ea305e6af7510b2a9","observation_id":"bc3a7c14-e726-4682-9649-3e6f94d0ef8f","resolution":{"observed_at":"2026-08-10T21:10:51.118025Z","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":"2026-08-10T21:10:51.887082Z","title":"Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks,","venue":null,"work_id":"181de9b0-c8e9-4283-84d3-a5911e33e501","year":2022},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.123246Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:e291f482e0aac2f809f0daa9f2aeea374232f15e1d8dafeec246cfa114dc242c","observation_id":"8b027429-a191-42d2-a924-486693d6936e","resolution":{"observed_at":"2026-08-10T21:10:51.892031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.851286Z","title":"Ueber den begriff der vollst¨andigen differentialgeometrischen fl ¨ache,","venue":null,"work_id":"8a9e0af4-a22d-4448-8ea5-c26a9955dcd9","year":1931},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.128047Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:eb871fafd1c7e1456d306e213511d6829a56b4efa267af13c95da44525f740c1","observation_id":"115cbbce-6e70-4a1b-b804-e21dc61be1c0","resolution":{"observed_at":"2026-08-10T21:10:51.864978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.817059Z","title":"Bolzano and uniform continuity,","venue":null,"work_id":"31c10d8b-08cd-49ad-9c45-e945accaf418","year":2005},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.134507Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:297b02cbae368706b0e720187d038a0b38654406952863b675c1f454d49c1a7c","observation_id":"6e774521-9452-4829-9e16-cbc477bb1901","resolution":{"observed_at":"2026-08-10T21:10:51.830364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19616","last_updated":"2024-11-03T09:23:33Z","snapshot_observed_at":"2026-07-06T19:24:03.133851Z","submitted_at":"2024-09-29T09:01:22Z","title":"DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-Decoupling","version":2},"cited_work":{"arxiv_id":"2409.19616","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.19616","snapshot_observed_at":"2026-08-10T21:10:51.376777Z","title":"DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-Decoupling","venue":"cs.LG","work_id":"2ad3246f-6023-4cf7-928a-1c4dc354d698","year":2024},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.139394Z"},"links":{"cited_paper":"/paper/2409.19616","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:f59b027175bca5da6b38eff600ccc492a09c54dda92fdf1fd76b75b839be5ae2","observation_id":"59e1509a-a6b6-45e1-a3e5-8ab632aa6a43","resolution":{"observed_at":"2026-08-10T21:10:51.384678Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.785834Z","title":"Representation learning on graphs with jumping knowledge networks,","venue":null,"work_id":"57ad9ed4-5160-43e1-8c3f-cecc55997dea","year":2018},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.144268Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:03b2323df256cf22f23b94e281f3ed2f9f0ea4be69d10acb02154aa61ea40520","observation_id":"baeabcbe-6271-42a1-802e-408875c39ff6","resolution":{"observed_at":"2026-08-10T21:10:51.794446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00826","last_updated":"2019-02-22T19:15:54Z","snapshot_observed_at":"2026-07-06T07:05:24.565760Z","submitted_at":"2018-10-01T17:11:31Z","title":"How Powerful are Graph Neural Networks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00826","snapshot_observed_at":"2026-08-10T21:10:51.149192Z","title":"How powerful are graph neural networks?","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.149192Z"},"links":{"cited_paper":"/paper/1810.00826","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:8aecd17dbeda07b6ac6fb29e59ce73cfe4f0b19ffe904dec0ee6af5a9cf7f40c","observation_id":"fcbbf9ee-43d2-4ebe-9b47-a87ad55ea4bd","resolution":{"observed_at":"2026-08-10T21:10:51.149192Z","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":"2026-08-10T21:10:51.765180Z","title":"Graph attention networks,","venue":null,"work_id":"7afcbd01-dbd6-4af6-b661-ffc58b6314dc","year":2017},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.153790Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:74d2dd44676426e2994d30d366054c7a8bc9195da323dbfe0d1cfc9f820b0dff","observation_id":"72c46d76-ef96-4a9a-bab1-c1421f4e4922","resolution":{"observed_at":"2026-08-10T21:10:51.770904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.14522","last_updated":"2022-11-12T16:11:19Z","snapshot_observed_at":"2026-08-10T10:56:00.667216Z","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":"2026-08-10T21:10:51.158207Z","title":"Understanding over-squashing and bottlenecks on graphs via curvature,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.158207Z"},"links":{"cited_paper":"/paper/2111.14522","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:ff9c0703ea36dcb85bcc41fd03444d801e8bb6ba3737ecbd056d851962b50316","observation_id":"61b3e8bb-7bae-4920-916c-ccb441ff4b50","resolution":{"observed_at":"2026-08-10T21:10:51.158207Z","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":"2026-08-10T21:10:51.747951Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs,","venue":null,"work_id":"71ec9de3-d14b-4e2f-ad70-ad43240dc5cd","year":2020},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.163493Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:1e1d3bb477be817dd1d48eec1c11c4ad317bbc90f9fc8480bfa5b0c914a32fa5","observation_id":"8f0a80c6-4550-4694-acde-5e53ca50c4d1","resolution":{"observed_at":"2026-08-10T21:10:51.753317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05287","last_updated":"2020-02-14T01:47:35Z","snapshot_observed_at":"2026-08-10T23:39:48.575656Z","submitted_at":"2020-02-13T00:03:09Z","title":"Geom-GCN: Geometric Graph Convolutional Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05287","snapshot_observed_at":"2026-08-10T21:10:51.168363Z","title":"Geom-gcn: Geometric graph convolutional networks,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.168363Z"},"links":{"cited_paper":"/paper/2002.05287","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:75c3356898cdd5a23af284f5461c3fdda8a29fdec453a59e91164ce786a40f69","observation_id":"5dd553c2-a362-484b-a9d7-222478d2fa80","resolution":{"observed_at":"2026-08-10T21:10:51.168363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03509","last_updated":"2021-05-10T02:23:20Z","snapshot_observed_at":"2026-07-06T09:53:43.248602Z","submitted_at":"2020-09-08T04:04:04Z","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.03509","snapshot_observed_at":"2026-08-10T21:10:51.173815Z","title":"Masked label prediction: Unified message passing model for semi-supervised classification,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.173815Z"},"links":{"cited_paper":"/paper/2009.03509","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:4c1b47d4dcd17ac429f5d0261c15def070348a847804c700949ab856bd126d16","observation_id":"7a9c1af0-1347-4473-8d5e-f7b698531421","resolution":{"observed_at":"2026-08-10T21:10:51.173815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04910","last_updated":"2023-02-27T11:39:09Z","snapshot_observed_at":"2026-07-06T13:19:23.070974Z","submitted_at":"2022-06-10T07:23:51Z","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04910","snapshot_observed_at":"2026-08-10T21:10:51.188088Z","title":"Nagphormer: A tokenized graph transformer for node classification in large graphs,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.188088Z"},"links":{"cited_paper":"/paper/2206.04910","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:22892ad5b063ce115aace5d991ee3df211182de909ff64bd731e45b6b5ec4a5b","observation_id":"bf2c420b-c417-48c5-8519-9c5ce3df00b1","resolution":{"observed_at":"2026-08-10T21:10:51.188088Z","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":"2026-08-10T21:10:51.730370Z","title":"Automating the construction of internet portals with machine learning,","venue":null,"work_id":"75b05eb1-6961-4164-9f00-bd7855af6077","year":2000},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.192875Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:3e6858b360746a7bd57df3fb5d1c4a51196d6c1b628090c37f1534bb054ffbf0","observation_id":"97feb409-bb29-4816-937d-94b75ff32189","resolution":{"observed_at":"2026-08-10T21:10:51.736312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.709695Z","title":"Revisiting semi-supervised learning with graph embeddings,","venue":null,"work_id":"4b05a068-9937-4edb-838a-0b7052801ad9","year":2016},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.197340Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:280b0378cc18e99b6e249be6638c1600df3cb03767a520240898afe09177ed1a","observation_id":"722d8fc9-8d15-48f3-891d-e9098355064d","resolution":{"observed_at":"2026-08-10T21:10:51.715439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.688987Z","title":"Affordable graph neural net- work framework using topological graph contraction,","venue":null,"work_id":"d1d5a827-d5fc-4a38-95aa-ca38411384da","year":2023},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.202018Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:9d0f91e14dd5730fc353a94c4dbeaaf99bf82bd35a80fb4f2c0b373c351eaa5f","observation_id":"d4325afd-4c0b-46ed-a318-454880a1e2ce","resolution":{"observed_at":"2026-08-10T21:10:51.694569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.671913Z","title":"Falcon: Feature-label constrained graph net col- lapse for memory-efficient gnns,","venue":null,"work_id":"2a58577a-1947-4ef8-b40c-31bd00522764","year":2024},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.206554Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:dd22514646324428554137aad2ef551db07ce5a8649b87fa79b21239c4e66f99","observation_id":"8b9efa39-336a-486f-9ac5-797605065238","resolution":{"observed_at":"2026-08-10T21:10:51.677342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.211671Z","title":"Deep learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.211671Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:88ac126b825794ba5d3c0806f6180089962a9876973a146eb2cd4b08d11388ac","observation_id":"4bc811e2-1738-48ad-9bd5-9edb3b2d9630","resolution":{"observed_at":"2026-08-10T21:10:51.211671Z","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":"2026-08-10T21:10:51.643112Z","title":"Welford’s algorithm for weighted statistics,","venue":null,"work_id":"e574aaa8-089d-4bdf-952b-3fad8d2f1e37","year":2021},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.216904Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:117aa2cebf12a76a0757a92543745f7fb19fdc41ffeef9bf953d3c33be629c1a","observation_id":"2752f66e-bfb7-4140-b439-e59ca1baea4c","resolution":{"observed_at":"2026-08-10T21:10:51.648627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.624757Z","title":"Complex network metrics: Can deep learning keep up with tailor-made reference algorithms?","venue":null,"work_id":"215912c5-51eb-42cf-9f9f-333df3fba36d","year":2020},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.221885Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:7d4a08a956b0b6a05b2f208ce7ac5619708e3e89c643f5b12b2d1c7d1b943ede","observation_id":"1fbfd909-58b6-47b1-8895-3069520bbd1f","resolution":{"observed_at":"2026-08-10T21:10:51.630388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.604366Z","title":"Demystifying structural disparity in graph neural networks: Can one size fit all?","venue":null,"work_id":"050dda44-8993-44c2-93db-9308f0929ece","year":2024},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.226652Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:30d1d3bdf572262095c10a730bda7aae2e43bd1281b5dc746d0503521631e8aa","observation_id":"52e7ffdb-ba43-4a58-8305-53cfc81b76ee","resolution":{"observed_at":"2026-08-10T21:10:51.609523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:10:51.231654Z","title":"Automatic differentiation in pytorch,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.231654Z"},"links":{"citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:c61438cd9afcac68770fc2c9398228129660738eaf6a440dcae3b68b6dfed2a8","observation_id":"e618d0c7-7679-45c9-a64d-aacada64ba72","resolution":{"observed_at":"2026-08-10T21:10:51.231654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.02428","last_updated":"2019-04-25T10:06:09Z","snapshot_observed_at":"2026-08-02T18:54:43.326912Z","submitted_at":"2019-03-06T14:50:02Z","title":"Fast Graph Representation Learning with PyTorch Geometric","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.02428","snapshot_observed_at":"2026-08-10T21:10:51.236364Z","title":"Fast graph representa- tion learning with pytorch geometric,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T21:10:51.236364Z"},"links":{"cited_paper":"/paper/1903.02428","citing_paper":"/paper/2501.06002"},"observation_digest":"sha256:216e2cabd16094cdf6bc1a973dfbc32b31de3c307d2b82bfb196b3a8045d557f","observation_id":"1f90dc70-67f1-487b-beae-d1dddcfc528b","resolution":{"observed_at":"2026-08-10T21:10:51.236364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.06002","last_updated":"2025-01-10T14:34:20Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T07:39:09.030631Z","submitted_at":"2025-01-10T14:34:20Z","title":"DeltaGNN: Graph Neural Network with Information Flow Control"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":2,"verified_fuzzy":28},"total_outbound_references":48},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2501.06002."}