{"as_of":"2026-08-07T20:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:703b42d0e28b9f84cdce5e513021d2da67f3a4da0cff41514270db92ff9c2795","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":"2026-08-07T10:44:01.831299Z","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":"2026-08-07T06:34:17.273281+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/2506.04653/citation-record","integrity":"/paper/2506.04653/integrity","json":"/paper/2506.04653/citation-record.json","paper":"/paper/2506.04653"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:44:09.242158Z","title":"ChainerMN: Scalable Distributed Deep Learning Framework","venue":null,"work_id":"e44692da-c621-4141-83d7-098e8c759f8f","year":2017},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.268246Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:ae7cdd361106a5cead3725f302aa097b478893788c13eb3068beb48d706862f6","observation_id":"76e092d7-594b-4394-b719-714b35f411fe","resolution":{"observed_at":"2026-08-07T10:44:09.285925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:43:56.391829Z","title":"On vanishing gradients, over- smoothing, and over-squashing in gnns: Bridging recurrent and graph learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.391829Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:a4887b3cbf787be14ad62871596d4ecdceb7777f09a1ca6ab4d02e0dce85e7a9","observation_id":"ca5ced3c-2e8a-49dc-9fd1-f028e8c29f0b","resolution":{"observed_at":"2026-08-07T10:43:56.391829Z","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":"2026-08-07T10:44:09.098598Z","title":"Beyond low-frequency information in graph convolutional networks","venue":null,"work_id":"33909302-2107-40e4-a399-c54e53082f1d","year":2021},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.503096Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:5b8f8704fd072cd7f5de08cbe6aaf091803503f1c723540e450084c1e389ae38","observation_id":"7ef74a88-4de5-4c16-bf14-3403268009d5","resolution":{"observed_at":"2026-08-07T10:44:09.167796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:08.930998Z","title":"A note on over-smoothing for graph neural networks","venue":null,"work_id":"49c0ceb9-27f4-4f8c-b8ce-76b4bb15cc78","year":2020},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.608227Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:c834f1e2c67d261e17b0eefe4184bc5d7d26c04e1b313dc525ff82f76a7b9c68","observation_id":"c1be2840-8428-45cd-8307-ccd9fc5b8bd1","resolution":{"observed_at":"2026-08-07T10:44:08.995239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:08.789063Z","title":"Grand: Graph neural diffusion","venue":null,"work_id":"65afdbac-5810-4d65-94e1-22818a53f942","year":2021},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.710648Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:58a30302b26ae5ee64e8dc9bb846aec6a3afc5f22f3f96661876c308863b51b3","observation_id":"574ec980-32cb-4605-b35e-6e5f3902db30","resolution":{"observed_at":"2026-08-07T10:44:08.876908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:08.632128Z","title":"Simple and deep graph convolutional networks","venue":null,"work_id":"c2d6f831-c635-4799-a494-b768223589da","year":2020},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.880864Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:d4a11cbfa9d64531cff9065f74ad95d3ddacd8f04adc40e87d42336fed1f4038","observation_id":"eaca6802-1917-4e25-a866-64ab37a6a736","resolution":{"observed_at":"2026-08-07T10:44:08.708868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:08.496159Z","title":"Long range graph benchmark","venue":null,"work_id":"9567e9b2-adfa-4830-b8e7-72bf4dcaf812","year":2022},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.966562Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:ff88e5c02118be25cf05a9dd417ac71a5d7e4190054d4769108a355649e7b546","observation_id":"ec155a1f-fe92-42a3-9165-893bc5cce7b6","resolution":{"observed_at":"2026-08-07T10:44:08.569355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:08.351762Z","title":"PDE-GCN: Novel architectures for graph neural networks motivated by partial differential equations","venue":null,"work_id":"633549da-783e-4aa7-8fe9-326472e0068a","year":2021},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:57.104377Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:c32b8d308335c6adba6029684578a9e14b160f57cf44ca1e51496a4649337741","observation_id":"265eddcd-3320-4a96-af11-f1e7d55adbc9","resolution":{"observed_at":"2026-08-07T10:44:08.425498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:43:57.243977Z","title":"Dropmes- sage: Unifying random dropping for graph neural networks.Proceedings of the AAAI Conference on Artificial Intelligence, 37(4):4267–4275, Jun","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:57.243977Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:99f14c922259d60094292859e3301c10f818eee94659a39897191e3fff003e45","observation_id":"2c255ff3-b2f4-48c3-a771-344983d1917d","resolution":{"observed_at":"2026-08-07T10:43:57.243977Z","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":"2026-08-07T10:44:08.195288Z","title":null,"venue":null,"work_id":"f2f5f9f1-8e68-48d3-9b82-c6cd27187108","year":2019},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:57.354816Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:34b398261edcf02577594e5a12122694a6d273bc37840c5520317d1fb06cef99","observation_id":"495269bf-ab66-418f-98ff-dede56ecdfd3","resolution":{"observed_at":"2026-08-07T10:44:08.281236Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:08.058483Z","title":"Understanding the difficulty of training deep feedforward neural networks","venue":null,"work_id":"7a2eeb76-ca83-40b0-917e-e265092ee3ea","year":2010},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:57.499562Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:846f94fb6a32467ceb20efb2fddfc52c878472aeb0105d449c19d416b7ae8bc6","observation_id":"e7149c11-faf0-44f1-86f1-16d1ba1b203d","resolution":{"observed_at":"2026-08-07T10:44:08.126897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:07.926578Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":"af27e576-5754-4b43-a59d-8dd9c7df41cd","year":2017},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:57.625844Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:396117b6b366a17d45a100b96d1c81704c935560ebc92d0e64ca06fee33638b9","observation_id":"43e1bcca-f525-4710-8b70-332f80b992db","resolution":{"observed_at":"2026-08-07T10:44:08.001010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:07.781616Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":"3c3a27eb-9523-4ea9-84f5-dc19b46c1144","year":2015},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:57.780591Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:0d441cc7dc4ee580db98e67ae22c739db6c28fb2ca8fd49a7798f86c96218085","observation_id":"db46330f-cdc6-44b2-9314-589d9776ab4a","resolution":{"observed_at":"2026-08-07T10:44:07.858102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:07.635478Z","title":"Bernnet: Learning arbitrary graph spectral filters via bernstein approximation","venue":null,"work_id":"6dd1dbc6-8f82-4fa8-829e-892ce0818ad4","year":2021},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:57.887860Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:28ce0a94b22a31cf31469ca79a8b1832e1788dc9df44b28ab90c98df2ecb63d7","observation_id":"c422c020-5df9-4ec1-ab2b-f91966e51f62","resolution":{"observed_at":"2026-08-07T10:44:07.698741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00687","last_updated":"2021-02-25T02:06:27Z","snapshot_observed_at":"2026-08-06T19:12:42.155813Z","submitted_at":"2020-05-02T03:09:50Z","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00687","snapshot_observed_at":"2026-08-07T10:43:58.034479Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.034479Z"},"links":{"cited_paper":"/paper/2005.00687","citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:3af8aa7d0ddc5f8d872a05888811529f243e6895ea19d09ef5c4ffece089c9f0","observation_id":"e5b61d6e-a1d7-4568-910c-10c06414de59","resolution":{"observed_at":"2026-08-07T10:43:58.034479Z","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":"2026-08-07T10:44:07.513875Z","title":"Not too little, not too much: a theoretical analysis of graph (over)smoothing","venue":null,"work_id":"8373c2d0-08e0-47e0-a06d-81eb276d51e7","year":2022},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.126159Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:6021d253c6b599007ccd7a55c47e8245ed1c5feeb4c4a5c8e029325f7fa4bd02","observation_id":"5b629470-89fc-4941-94ad-c3eb8d9caa3d","resolution":{"observed_at":"2026-08-07T10:44:07.568988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:07.357225Z","title":"Kipf and Max Welling","venue":null,"work_id":"46dd4484-506a-404e-9c81-29c80ab80b95","year":2017},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.208574Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:90e78d2e513c7d97aad4e4dadb0ecee8a3259b86bc0749e54da2088b0af99e53","observation_id":"9d3c4e4b-6f64-4fa4-85aa-2a8f21e4c7f3","resolution":{"observed_at":"2026-08-07T10:44:07.442707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:07.197891Z","title":"Deepgcns: Can gcns go as deep as cnns? In Proceedings of the IEEE/CVF international conference on computer vision, pages 9267–9276, 2019","venue":null,"work_id":"49c3984e-92c5-4b33-b2d2-65e8aa937ee6","year":2019},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.324385Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:1dde921241caf54f07fa8e9a6995a52212357eee6c1a991b0f703d81e1408c70","observation_id":"ff015c8c-625c-45d9-b4b8-2de1f7ce5e75","resolution":{"observed_at":"2026-08-07T10:44:07.283811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:07.061817Z","title":"Training graph neural networks with 1000 layers","venue":null,"work_id":"656dde48-9e23-4e39-acf1-41855f77c655","year":2021},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.444172Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:5d85f37dfda048d6c5af2ec486b65529706e7a63d50b4ad1c908771cc9a024d7","observation_id":"0a885a96-5942-4d61-a674-9455c2f5b1a4","resolution":{"observed_at":"2026-08-07T10:44:07.113805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:06.909605Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":"0c75ead6-b519-428d-990d-a72fff5fbf93","year":2018},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.571350Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:1912325d8250ccf50bf0ce1942aab6727e8d870bde1552c4ba6592de9d40f83c","observation_id":"157b438b-48ad-4c30-af97-b894971a3e79","resolution":{"observed_at":"2026-08-07T10:44:06.988674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:43:58.716051Z","title":"Skipnode: On alleviating performance degradation for deep graph convolutional networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.716051Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:914305df4122359eaf2a1fbac70577e506235c2bdfe46d46619a9357fb82250e","observation_id":"417efef6-14a2-4a52-af94-2cde04913880","resolution":{"observed_at":"2026-08-07T10:43:58.716051Z","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":"2026-08-07T10:44:06.755048Z","title":"Classic GNNs are strong baselines: Reassessing GNNs for node classification","venue":null,"work_id":"a6118df6-898f-44a5-9e0b-0dbfb64f7d59","year":2024},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.810087Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:a91e3dfe27daba8ba3516db8196c61090a4381998e39f1f134e0d157c008de65","observation_id":"01ab829d-1518-4329-9659-7cda1f636242","resolution":{"observed_at":"2026-08-07T10:44:06.829511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:06.637040Z","title":"Image-based recommendations on styles and substitutes","venue":null,"work_id":"7ee9fcb6-dc46-4a70-892b-09b1cf588df1","year":2015},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:58.973961Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:72fde0dbc2956773819fffbc248e5e6df8d937e5f2d5eb3f6d05306bc7becf0c","observation_id":"d485f88f-91bf-4fc8-b5ba-84e2d393a6cb","resolution":{"observed_at":"2026-08-07T10:44:06.689078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:06.524502Z","title":"Graph neural networks exponentially lose expressive power for node classification","venue":null,"work_id":"1d822836-53a5-42ea-b2ce-5dbba4be2082","year":2020},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:59.128246Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:14cad1656731b0ef47de4b73cafb83931f5ae3c0c898357c5d17fed5450c6a15","observation_id":"353298e3-a129-47bb-aac2-f387ef10ab90","resolution":{"observed_at":"2026-08-07T10:44:06.573439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:06.416920Z","title":"Mitigating oversmoothing through reverse process of GNNs for heterophilic graphs","venue":null,"work_id":"a3416615-7cde-4c6c-9ce6-be2777b2824b","year":2024},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:59.247083Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:5d90fdfa5b4d7015b1fc205f7b76e028d32932a95978040e4e3acdb5c019eb33","observation_id":"536f79f5-3785-4615-90bd-9922aa870453","resolution":{"observed_at":"2026-08-07T10:44:06.468027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05287","last_updated":"2020-02-14T01:47:35Z","snapshot_observed_at":"2026-08-07T18:28:55.768202Z","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":"2026-08-07T10:43:59.384379Z","title":"Geom-gcn: Geometric graph convolutional networks","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:59.384379Z"},"links":{"cited_paper":"/paper/2002.05287","citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:7c632258f7efc31bd183e530d7c8d3db970a9164843f26313ed7eda1c42f61ba","observation_id":"de28c197-f021-497d-b087-939cfd17db6f","resolution":{"observed_at":"2026-08-07T10:43:59.384379Z","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":"2026-08-07T10:44:06.253299Z","title":"Multi-track message passing: Tackling oversmoothing and oversquashing in graph learning via preventing heterophily mixing","venue":null,"work_id":"27b7c8eb-d5d1-4de3-9670-d1f00083711b","year":2024},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:59.523909Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:693c34e28c6c4b1bd1902d328146329227d07bff68ea8d8319801ed903560df6","observation_id":"5ce9b88d-aa05-4bcc-9f33-7b634ff122b6","resolution":{"observed_at":"2026-08-07T10:44:06.337966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:06.084971Z","title":"A critical look at evaluation of gnns under heterophily: Are we really making progress? In The Eleventh International Conference on Learning Representations, 2023","venue":null,"work_id":"869f47c1-06f5-4776-9713-f3ebc4754f09","year":2023},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:59.644207Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:1186769f1b52f72687d3b521d900e40385b4dc5d00ea781889022cf2788ac2c1","observation_id":"0f1399d2-afc1-449c-a9d9-aa5610123130","resolution":{"observed_at":"2026-08-07T10:44:06.148950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:05.887822Z","title":"Dropedge: Towards deep graph convolutional networks on node classification","venue":null,"work_id":"bb2dfcc6-1b23-49e5-ba1e-f4ac7b38af5a","year":2020},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:59.797177Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:2fbfc8d87fad12415b13c09b5c56d77b0129aa64cf5dbac3249004d2fdedcc2b","observation_id":"abebb8a6-90d3-4516-a917-9dd313c5b1b3","resolution":{"observed_at":"2026-08-07T10:44:05.998010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:05.745105Z","title":"Multi-scale attributed node embedding","venue":null,"work_id":"568684bf-21d2-47a4-a78b-88b0d8feab7c","year":2021},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:59.913361Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:db7edf8d91770800a22aa7317d1759a8e39c1ba48a8c0f21ad0934e11efa959b","observation_id":"3c8769b7-1ced-4223-a606-f19e98f4e47b","resolution":{"observed_at":"2026-08-07T10:44:05.810906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:05.577663Z","title":"Graph-coupled oscillator networks","venue":null,"work_id":"322c1367-700a-4ad9-bb41-061235aa55dd","year":2022},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:00.034745Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:1b643bc4cfe3d9239416c362a48e712242d47835fe2f96b729c49790d4499336","observation_id":"cde7b7e4-c531-4417-9cf5-9ae56c8779b3","resolution":{"observed_at":"2026-08-07T10:44:05.651788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10993","last_updated":"2023-03-20T10:21:29Z","snapshot_observed_at":"2026-07-06T15:05:38.707313Z","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":"2026-08-07T10:44:00.183707Z","title":"A survey on oversmoothing in graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:00.183707Z"},"links":{"cited_paper":"/paper/2303.10993","citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:c6713f501f9bd10cc8472a5756db3ba32bbbf12b78e6475019df9e82e4adefaa","observation_id":"c956adcf-dcfe-4168-be24-b64834c92f96","resolution":{"observed_at":"2026-08-07T10:44:00.183707Z","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":"2026-08-07T10:44:05.446602Z","title":"Konstantin Rusch, Benjamin Paul Chamberlain, Michael W","venue":null,"work_id":"da826758-588a-4fb7-b7d6-fdcecc0d6c5f","year":2023},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:00.302351Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:d0735f66b6553089e9a1b9ab106727f899b874f4bff7a267c278d4c4c820828a","observation_id":"08c555cf-381a-42e1-8502-dbbe9e1d2b6f","resolution":{"observed_at":"2026-08-07T10:44:05.512774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:05.287047Z","title":"Collective classification in network data","venue":null,"work_id":"ae0a9526-abee-460c-8849-5904785e24a9","year":2008},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:00.459713Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:e785e24aa67c7dc22418f74b9e9c9cd8e7e79b83e9b0cfc783afdb25a0490401","observation_id":"5cc76cb2-684c-4f98-9388-ec1b8c27d957","resolution":{"observed_at":"2026-08-07T10:44:05.363120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:04.995900Z","title":"Ordered GNN: Ordering message passing to deal with heterophily and over-smoothing","venue":null,"work_id":"df8b2690-3d33-4012-8529-7a24adf9caf1","year":2023},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:00.532737Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:4ba6f15bb751c0196feed91c67f00d64afe3e1fd11bfecaec5e2ea7170863607","observation_id":"e999fddd-15ac-4272-bf0e-03bb06f45e90","resolution":{"observed_at":"2026-08-07T10:44:05.199579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2024.11164","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:44:02.023471Z","title":"Simple and deep graph attention networks","venue":null,"work_id":"dc994640-043f-4f8c-b8cf-b6dcf3f9cc97","year":2024},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:00.646879Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:be43ccbdcc2c834ce74b2cb68bf13af0aa5814af780f7e8b840f5cab3e8b95c2","observation_id":"7eb58683-fb10-4644-b19c-7c12dc00fbec","resolution":{"observed_at":"2026-08-07T10:44:02.070540Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:04.687382Z","title":"Grand++: Graph neural diffusion with a source term","venue":null,"work_id":"73c16c62-4736-4ae0-93ed-cb518c1439ba","year":2022},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:00.880307Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:aabdd255497cfb441e00dddcb55cdc4fbbc136f842b5597dd48d369a34b95c88","observation_id":"abf190f5-d45e-4ad0-a7fa-cbd23dbd7780","resolution":{"observed_at":"2026-08-07T10:44:04.835892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:04.323955Z","title":"Chainer: a next-generation open source framework for deep learning","venue":null,"work_id":"69439c2d-25bc-4dd2-9019-1a73c124a404","year":2015},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.041160Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:96f6661f51b585386bc04e1e1226306ae7b15ac1aaea035a5f7e2a167c6b8086","observation_id":"7bd76422-b1d4-402c-a5f4-368d599f003f","resolution":{"observed_at":"2026-08-07T10:44:04.504627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:03.981414Z","title":"Chainer: A deep learning framework for accelerating the research cycle","venue":null,"work_id":"93b741e3-88bd-4788-bde9-4c202a38fa96","year":2002},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.200457Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:38f20856de6769eee7eaf6869cd91def7c6cac5bfe86984b8a57a023cf77220e","observation_id":"bdd18227-f681-47fd-b546-d3fc8d4fca96","resolution":{"observed_at":"2026-08-07T10:44:04.119530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:03.770066Z","title":"Visualizing data using t-sne","venue":null,"work_id":"2754087d-472e-4dee-8651-79f71c827f99","year":2008},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.320792Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:86e421a0a898befdf6fcd2689b6f24120b1e7d5bc2a3af95dfbe97005923cdf1","observation_id":"049efefa-e7cc-494b-b3d6-fa0f96e5dfe6","resolution":{"observed_at":"2026-08-07T10:44:03.905437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:01.399771Z","title":"Graph attention networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.399771Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:c182b49a02cd53b29e2c32dd3227e54ae5a10d5ac953a8482e2602b9b5c881bd","observation_id":"ea4ab1b4-c6df-4f4f-b463-9ae43f8916ac","resolution":{"observed_at":"2026-08-07T10:44:01.399771Z","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":"2026-08-07T10:44:03.386629Z","title":"Simplifying graph convolutional networks","venue":null,"work_id":"e4789f42-52b5-4a6f-b317-c6bc5f3b6177","year":2019},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.473433Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:9faa3c4e14783edf17790778ee03bd86b41738c2c8d1c2b2f901df57c2b91640","observation_id":"44b830da-a5a9-4877-bbc3-4b7cd48042e9","resolution":{"observed_at":"2026-08-07T10:44:03.600318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:03.117831Z","title":"Demystifying oversmoothing in attention-based graph neural networks","venue":null,"work_id":"74117e60-df74-481a-8db2-fdcd86b4f042","year":2023},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.528415Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:238ab9688da937d19f8d12f997177f7654abb938241a6ab13cd6a20f3d959f39","observation_id":"c2628bef-b24a-4b6f-a18f-14294c8a6a2f","resolution":{"observed_at":"2026-08-07T10:44:03.250597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:02.956270Z","title":"A non-asymptotic analysis of oversmoothing in graph neural networks","venue":null,"work_id":"e1fda61c-0d29-4390-a6be-6fe8ceea9bb3","year":2023},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.582213Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:376e633d716b4b81a8b94d402c444449f737aa32cc2d8e81c962bee825aae73c","observation_id":"0415241c-0cba-4a07-bed2-efc213e3b9be","resolution":{"observed_at":"2026-08-07T10:44:03.024509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:02.789302Z","title":"Model degradation hinders deep graph neural networks","venue":null,"work_id":"85c743c4-63f0-4832-ba57-7802b7df9d97","year":2022},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.645139Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:6e392aa3bbfe0a2e393889b17c988da354b733b67a988b966824b82bb9c075a1","observation_id":"9692189c-6d21-47c0-9e5b-ab756eaac9a5","resolution":{"observed_at":"2026-08-07T10:44:02.870133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:02.654191Z","title":"Pairnorm: Tackling oversmoothing in gnns","venue":null,"work_id":"8f3b02bc-287d-4cef-aacc-dde4a098665d","year":2020},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.700119Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:a4ba6f5f804fae9c4e9f8c83bc82544e1e76959c1623ed00e1ba66ab965a4438","observation_id":"9b9ea8d6-1ff5-4ed6-9b96-841b69ead489","resolution":{"observed_at":"2026-08-07T10:44:02.715681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:02.523971Z","title":"Dirichlet energy constrained learning for deep graph neural networks","venue":null,"work_id":"a9a73b07-b051-4837-a600-6f6b105fdd4e","year":2021},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.751430Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:37fee63f945e0b1157cca344aaf5076dca2d87486cf9c48524789de4891ec187","observation_id":"743a66b3-5747-4d3d-b3b1-b9765d824cb1","resolution":{"observed_at":"2026-08-07T10:44:02.578468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:44:02.363482Z","title":"Understanding and resolving performance degradation in deep graph convolutional networks","venue":null,"work_id":"042287fb-0799-4c1e-8357-79d3094edc77","year":2021},"citing_paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T10:44:01.831299Z"},"links":{"citing_paper":"/paper/2506.04653"},"observation_digest":"sha256:f457dbccedae0c5575d3feae94ef39150a30bcc21b7b167b016bcf70ecfd3b7a","observation_id":"8f6d37b7-ac41-421c-93f2-85915f22c349","resolution":{"observed_at":"2026-08-07T10:44:02.427359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.04653","last_updated":"2025-06-05T05:49:12Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T10:34:14.373427Z","submitted_at":"2025-06-05T05:49:12Z","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":39},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2506.04653."}