{"as_of":"2026-08-11T22:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:51a61486df6cec228b69bbf419bc944dc0a30c83b95d21892b115c50d123035c","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:52:03.987849Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T11:23:28.294391Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00762","snapshot_observed_at":"2026-08-04T11:23:28.294391Z","title":"[CLPR25] Shi Chen, Zhengjiang Lin, Yury Polyanskiy, and Philippe Rigol- let","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.05554","last_updated":"2026-07-30T05:50:28Z","snapshot_observed_at":"2026-08-07T13:47:21.858527Z","submitted_at":"2025-10-07T03:51:57Z","title":"Critical attention scaling in long-context transformers","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T11:23:28.294391Z"},"links":{"cited_paper":"/paper/2501.00762","citing_paper":"/paper/2510.05554"},"observation_digest":"sha256:52a995f31aabe840299903bbda21f2218624ccaa79559fd6e1343c498b505e54","observation_id":"014ed71f-aa82-492f-8e19-0bdd56b9d305","resolution":{"observed_at":"2026-08-04T11:23:28.294391Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00762","snapshot_observed_at":"2026-08-01T15:05:01.548838Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18584","last_updated":"2026-07-20T23:43:26Z","snapshot_observed_at":"2026-08-08T04:20:11.525784Z","submitted_at":"2026-07-20T23:43:26Z","title":"On the Diverse Dynamical Behaviors Arising in Deep Linear Transformers","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T15:05:01.548838Z"},"links":{"cited_paper":"/paper/2501.00762","citing_paper":"/paper/2607.18584"},"observation_digest":"sha256:74d063c8391797f8dcc2f9121923f73580b5715bd45eea23e0b919b007adb5af","observation_id":"44471e30-fde5-43d4-bb4e-50badf061aaa","resolution":{"observed_at":"2026-08-01T15:05:01.548838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2501.00762/citation-record","integrity":"/paper/2501.00762/integrity","json":"/paper/2501.00762/citation-record.json","paper":"/paper/2501.00762"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:52:04.799198Z","title":"Random dynamical systems","venue":null,"work_id":"9320e2ff-e1fa-47c3-8eaa-77acea02e177","year":1998},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.734054Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:6c1208da1898bd66945fd42ed1ca1b9c117e26922395666051143a7674b795ab","observation_id":"867c905b-5411-4193-9c3f-fd6c2c93a871","resolution":{"observed_at":"2026-08-10T22:52:04.806738Z","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":"2026-08-10T22:52:04.775696Z","title":"Measuring and relieving the over-smoothing problem for graph neural networks from the topological view","venue":null,"work_id":"14b6c948-260b-4193-98c5-915434d1c7ea","year":2020},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.743894Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:39f355d9d07aca6821f7d9cac0a9364097c8dc19637a049e0a36e82355231b64","observation_id":"315a7d89-31fb-4c39-8487-3939a7085ab0","resolution":{"observed_at":"2026-08-10T22:52:04.781700Z","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":"1801.10247","last_updated":"2018-01-30T22:36:16Z","snapshot_observed_at":"2026-07-06T06:21:01.297755Z","submitted_at":"2018-01-30T22:36:16Z","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.10247","snapshot_observed_at":"2026-08-10T22:52:03.749534Z","title":"Fastgcn: fast learning with graph convolutional networks via importance sampling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.749534Z"},"links":{"cited_paper":"/paper/1801.10247","citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:8ad208f1af65c677df7bd876726e70fa62c6a666335703f6e4568b0698aecdae","observation_id":"8a301201-d39e-4f2c-a182-227e77a32bf0","resolution":{"observed_at":"2026-08-10T22:52:03.749534Z","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":"2026-08-10T22:52:04.755615Z","title":"Cohen and Charles M","venue":null,"work_id":"bcdec7d9-0b50-4ee6-8eb7-d5b3bf403713","year":1984},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.758277Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:fe0bfad7d8147de53888091d7273c6cfb9df7d06c44fe879ddfc26e9f435e576","observation_id":"a396ab2f-d80a-4fb4-a1c3-f576e23a5fcd","resolution":{"observed_at":"2026-08-10T22:52:04.762355Z","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":"2006.13318","last_updated":"2020-06-23T20:36:56Z","snapshot_observed_at":"2026-07-06T09:32:05.177891Z","submitted_at":"2020-06-23T20:36:56Z","title":"A Note on Over-Smoothing for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.13318","snapshot_observed_at":"2026-08-10T22:52:03.771559Z","title":"A note on over-smoothing for graph neural networks","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.771559Z"},"links":{"cited_paper":"/paper/2006.13318","citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:d64e79c0edf343c84d4eb559956d9e104bde59ada275d32cf96580743d4a5a12","observation_id":"781dfe6c-f189-4d5d-8e2f-2b4cf2617937","resolution":{"observed_at":"2026-08-10T22:52:03.771559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11668","last_updated":"2023-06-20T16:40:41Z","snapshot_observed_at":"2026-08-11T12:32:29.189914Z","submitted_at":"2023-06-20T16:40:41Z","title":"Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations","version":1},"cited_work":{"arxiv_id":"2306.11668","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.11668","snapshot_observed_at":"2026-08-10T22:52:04.171535Z","title":"Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations","venue":"stat.ML","work_id":"95419bc7-a54b-477b-aee7-a8eaf7d773e3","year":2023},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.779111Z"},"links":{"cited_paper":"/paper/2306.11668","citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:94744520524e9f2497c7dfad4e9add5e1d5135d87458d1f3231b2e35b57cfe1a","observation_id":"9f4f37ea-958c-422f-94f9-21a321271e89","resolution":{"observed_at":"2026-08-10T22:52:04.181485Z","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":"2026-08-10T22:52:04.734300Z","title":null,"venue":null,"work_id":"7e4ae7d8-10cb-41fd-b643-85ae2efaf0f3","year":2019},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.787148Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:35ef25c202bd07362eaa90c152cfb68a4c03a192daaa6e5874c13fe37b8008c3","observation_id":"f0f1ce97-6bed-4dca-91a3-f02a5b666a08","resolution":{"observed_at":"2026-08-10T22:52:04.740034Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-10T22:52:04.712070Z","title":"Understanding the difficulty of training deep feedforward neural networks","venue":null,"work_id":"35e87c43-f7db-4150-8181-95cbf147930b","year":2010},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.792937Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:300dbd4b9cb63b67dcf69cf13351138e7a764447e4943e1db60918da84e7ee81","observation_id":"9708a534-7b1e-4908-bc77-315d4b12c9d7","resolution":{"observed_at":"2026-08-10T22:52:04.718346Z","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":"2026-08-10T22:52:04.687513Z","title":"Exact combinatorial optimization with graph convolutional neural networks","venue":null,"work_id":"630b3410-d150-47da-9577-8d4998e3b495","year":2019},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.797950Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:f6e5bd56e4e0de4d5a6cd231423c7961b18c111bf6ee010a79082ec49ff04270","observation_id":"c09e8efa-0931-420b-bc75-e3fee0ead939","resolution":{"observed_at":"2026-08-10T22:52:04.695628Z","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":"2026-08-10T22:52:04.669041Z","title":"Neural message passing for quantum chemistry","venue":null,"work_id":"9d6f041c-b879-48d2-85c0-b5908d961c93","year":2017},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.805257Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:2cf38ab88afaba169ed9488f61a8dd8143479349ff98a1003fcd6c655c60512e","observation_id":"4f6e8803-4c52-4eb8-acf9-e443c47d4744","resolution":{"observed_at":"2026-08-10T22:52:04.674603Z","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":"2026-08-10T22:52:04.643525Z","title":"An overview on the application of graph neural networks in wireless networks","venue":null,"work_id":"8e33382f-87d3-4e8b-bcb4-e252ce05e760","year":2021},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.811364Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:362822a69db697624972520f1579aef7287bd37fdb35c5e8f5b7aa99c17c0b10","observation_id":"1933447d-7d60-491a-bd43-f758c92a904d","resolution":{"observed_at":"2026-08-10T22:52:04.650229Z","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":"2026-08-10T22:52:03.818010Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.818010Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:4ed782699b62e4eae9bdc3469aeedd929f2d7e32389f753bbd52d8ab2267e579","observation_id":"1a71b996-82a8-46b2-a2cc-545191339528","resolution":{"observed_at":"2026-08-10T22:52:03.818010Z","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":"2026-08-10T22:52:04.608990Z","title":"Not too little, not too much: a theoretical analysis of graph (over) smoothing","venue":null,"work_id":"05253824-d48c-4ec7-a1ea-387bf4070e44","year":2022},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.826849Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:9fd105bd4ecf2eefea007956a1c54dd46831c8e9746eb09bace1f99a96ac0fb7","observation_id":"15696b80-0dcc-464d-90d6-d4393c9e0e03","resolution":{"observed_at":"2026-08-10T22:52:04.614286Z","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":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-10T22:52:03.834144Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.834144Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:ff30dd8c40e3f55b6ef8f3ce4eb2c0f3ea7eba8f6e2cb0373d9abe4e91e129a6","observation_id":"60b7afe9-ea9e-48e2-81c6-f27f545fe985","resolution":{"observed_at":"2026-08-10T22:52:03.834144Z","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":"2026-08-10T22:52:04.592116Z","title":"Kipf and Max Welling","venue":null,"work_id":"98621be2-ad7a-4d53-aba9-72a9b89308d8","year":2017},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.840656Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:5f1ded3a8556a3adc85c5f853f42b923ad88ea3a9c534a724f08602a684a8691","observation_id":"7de468ea-d72a-487f-9ee0-2499b246eecb","resolution":{"observed_at":"2026-08-10T22:52:04.597437Z","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":"2026-08-10T22:52:04.573184Z","title":"A review of graph neural networks and their applications in power systems","venue":null,"work_id":"c23a5886-5e5d-4c4f-9d1e-4eaeb4055ede","year":2021},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.847683Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:5feccd78849091d397ef976a82f97dcc5726dcbcbe90a3965681d6efd1a3171b","observation_id":"a4d343a1-14bc-4ef2-af59-c8e72d4f49b9","resolution":{"observed_at":"2026-08-10T22:52:04.578806Z","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":"2026-08-10T22:52:04.555447Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":"f00c8961-239d-434e-94c3-bd514ab06810","year":2018},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.867242Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:ca4e84e1938539cd7e2436c04055cbd737feea70c6ef9c579e6001f33a198c61","observation_id":"18950c49-747b-4e4b-ae9d-083862e11253","resolution":{"observed_at":"2026-08-10T22:52:04.560818Z","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":"2026-08-10T22:52:04.536825Z","title":"Graph neural networks meet wireless communications: Motivation, applications, and future directions","venue":null,"work_id":"24701937-5577-4038-841d-8e1aac4511b1","year":2022},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.873551Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:3b4fddeff4495c63d9f346aa34353c9fb0939cf19077304c30c9864acedd25d4","observation_id":"8ede011c-4196-40da-aa4f-d74270bbf1fe","resolution":{"observed_at":"2026-08-10T22:52:04.543190Z","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":"2026-08-10T22:52:04.520309Z","title":"Markov chains","venue":null,"work_id":"1d510003-aac1-42c3-ac38-e16acdef756d","year":1998},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.880432Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:a3e3c798f983836ba9d00bc9723f05c2a64ce95d056f108c0ed23436c9843f35","observation_id":"e6673c75-e290-4839-9197-f2d52ace16c0","resolution":{"observed_at":"2026-08-10T22:52:04.525686Z","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":"2026-08-10T22:52:04.502424Z","title":"Graph neural networks exponentially lose expressive power for node classification","venue":null,"work_id":"66526c8c-38f7-4880-bf22-e5c70309f479","year":2020},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.887163Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:070980175a5c5d251107750bf21629f069f4cab1188b0678cf55e9493acc36ef","observation_id":"8c375bec-b1ca-494d-90ca-1930f8262fd3","resolution":{"observed_at":"2026-08-10T22:52:04.507940Z","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":"2026-08-10T22:52:04.482374Z","title":"A multiplicative ergodic theorem","venue":null,"work_id":"4c4d1263-2bc5-4e4b-8319-6cf1c28327eb","year":1968},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.893036Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:b12380d7dedacd68c51af13e13f5053edf524954a57d81f109dd0d21781ef16a","observation_id":"c047bc25-054d-4ce5-9a03-88dc3f126ee3","resolution":{"observed_at":"2026-08-10T22:52:04.488566Z","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":"2026-08-10T22:52:04.462411Z","title":"A survey on oversmoothing in graph neural networks","venue":null,"work_id":"8fe9027b-d1b8-41d4-9d14-8f79bbe394c9","year":2023},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.898638Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:06255b6554b017edd61489509df524abec6038265ae888344b8d1f6c7035f69e","observation_id":"24a6a041-25b4-46df-a8c3-ff540e625fad","resolution":{"observed_at":"2026-08-10T22:52:04.468474Z","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":"2026-08-10T22:52:04.441348Z","title":"Graph neural networks in particle physics","venue":null,"work_id":"f3658079-dd5c-4da6-92ce-0f74441a6466","year":2020},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.903974Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:40f924e17c3dde4ffeb7b233eb7f14450e557c29aec6b3a4d7a4cdf1a1429fba","observation_id":"c6233368-ebb7-4b32-b447-90956627bc4e","resolution":{"observed_at":"2026-08-10T22:52:04.447773Z","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":"2026-08-10T22:52:04.423057Z","title":"The graph neural network model","venue":null,"work_id":"057fa62b-9976-4ad1-901f-aee448bd76b3","year":2008},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.910644Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:c1e19b8ad020924d3031b87a7e745b1cb47aa10ce37f167398c75ffc930d2cff","observation_id":"875c8949-b98d-4d21-84aa-b46b7b1fc1e2","resolution":{"observed_at":"2026-08-10T22:52:04.429295Z","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":"2026-08-10T22:52:03.916506Z","title":"Residual connections and normalization can provably prevent oversmoothing in gnns","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.916506Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:dff6b213cef2095edbbc7cb3c4796958a3bcc9f45db3993883931c6e549bf3b2","observation_id":"71b030a6-0758-4da7-a612-c597371a0a35","resolution":{"observed_at":"2026-08-10T22:52:03.916506Z","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":"2026-08-10T22:52:04.400731Z","title":"Graph attention networks","venue":null,"work_id":"30f19d1d-5c36-4fd7-9970-c5979d5a4bfb","year":2018},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.924953Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:26814e05bf38d8ebbaef11a3540d9c5479f66b03d4b04b89d5f67172a74f8c65","observation_id":"65bc648a-ab8a-48bb-bebd-d882fc0b8888","resolution":{"observed_at":"2026-08-10T22:52:04.407828Z","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":"2026-08-10T22:52:04.379360Z","title":"Demystifying oversmoothing in attention-based graph neural networks","venue":null,"work_id":"6e384b6e-f92c-4b88-995e-e25faf2e145b","year":2023},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.932338Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:6d990d1d13e1e7ec7a7ba819abbcef24a11f6607dd3a255c73fb852974e0e6b8","observation_id":"3670a408-17a1-42c4-bc1b-4a2b873eb0fd","resolution":{"observed_at":"2026-08-10T22:52:04.386202Z","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":"2026-08-10T22:52:04.362532Z","title":"A non-asymptotic analysis of oversmoothing in graph neural networks","venue":null,"work_id":"a044a1b3-0b9e-4ddc-8324-78b14ae1ef8b","year":2023},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.938911Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:d8ca67a453b1ca572d326d3c5e0bba106d7e01ee296d25e3536fee3f7563140c","observation_id":"f6606020-5569-4c48-89d0-ccacaee51239","resolution":{"observed_at":"2026-08-10T22:52:04.368193Z","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":"2026-08-10T22:52:03.950288Z","title":"A comprehensive survey on graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.950288Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:1afbcce10d3a496ff185bfbcfb4cc6303dacb2cafde387e6bb7426701d6717d8","observation_id":"636e60b8-d948-425b-a056-6ebb7a36c2fa","resolution":{"observed_at":"2026-08-10T22:52:03.950288Z","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":"2026-08-10T22:52:04.328839Z","title":"A review on graph neural network methods in financial applications","venue":null,"work_id":"c64f43a2-8fe5-4b84-8046-a1569e6db4ef","year":2022},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.957319Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:acf7d919ddc72cf95c2a70d6824ee34d8da76ffee41bedb19d1c22dac5f8efcc","observation_id":"d1be6ee9-f6a4-481c-9a65-ae6a9bfe6e84","resolution":{"observed_at":"2026-08-10T22:52:04.335049Z","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":"2026-08-10T22:52:04.311381Z","title":"Revisiting semi-supervised learning with graph embeddings","venue":null,"work_id":"b995a636-670c-4f10-9a0f-0a406ca7ac7f","year":2016},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.964018Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:0740548b1b5285c7bc4446a217b14d5d70dc5b5c8a0517c681066278cf104484","observation_id":"1306f931-9602-4fe4-8281-18c21a2baed1","resolution":{"observed_at":"2026-08-10T22:52:04.316918Z","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":"2026-08-10T22:52:04.292127Z","title":"Graph neural networks: A review of methods and applications","venue":null,"work_id":"0087ed87-8431-4d3f-8739-3cf353f0c3c8","year":2020},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.970321Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:d2ed0137bc1f9b4bd1dc7bac0bb4238fa965cdaa738d4901944ad15a1a197d0a","observation_id":"b6ab79bc-ffae-4800-9087-0c5ea8f73e92","resolution":{"observed_at":"2026-08-10T22:52:04.299425Z","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":"2026-08-10T22:52:04.271311Z","title":"Graph neural networks and their current applications in bioinformatics","venue":null,"work_id":"113b3d00-a817-48ff-9b65-bfca62e820a7","year":2021},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.977655Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:12203195f41afa81f4b85960003bfa90a0243965a84718b282c422fb0bfd02f8","observation_id":"c1ea89ed-579f-477d-b496-92149a7eaa11","resolution":{"observed_at":"2026-08-10T22:52:04.277594Z","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":"2026-08-10T22:52:04.249722Z","title":"A comprehensive review of the oversmoothing in graph neural networks","venue":null,"work_id":"6c76e547-e0ce-49da-b7ee-931a108e9c1b","year":2023},"citing_paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T22:52:03.987849Z"},"links":{"citing_paper":"/paper/2501.00762"},"observation_digest":"sha256:7e12621af7e8abcfa4f5bb0a31f794fff128a37ab650d566868b8b6395b32387","observation_id":"42004854-4883-402e-b242-20d199616ea1","resolution":{"observed_at":"2026-08-10T22:52:04.256269Z","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"}}],"paper":{"arxiv_id":"2501.00762","last_updated":"2025-01-04T03:14:11Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T01:57:03.338571Z","submitted_at":"2025-01-01T07:35:36Z","title":"Residual connections provably mitigate oversmoothing in graph neural networks"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":1,"verified_fuzzy":26},"total_outbound_references":34},"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 34 of 34 outbound references and 2 inbound Pith citation observations for arXiv:2501.00762."}