{"as_of":"2026-08-23T21:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a3309793abe551d20fcf0365f7718ecfcd5c80d5fa07805ebda05070eae19aa8","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T04:10:19.752352Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2505.02020/citation-record","integrity":"/paper/2505.02020/integrity","json":"/paper/2505.02020/citation-record.json","paper":"/paper/2505.02020"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:10:20.778888Z","title":"Stochastic training of graph convolutional networks with variance reduction","venue":null,"work_id":"b6916b3e-0211-4f99-8098-9042329818bd","year":2018},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.244307Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:4ffa049da1fad60b0635d4b0fe6c2ba53f57d4020e0795e2eb78938a3bc8e15c","observation_id":"9a5fe590-93db-4fbe-89bc-b3c1e8b4e96e","resolution":{"observed_at":"2026-08-16T04:10:20.783890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.758070Z","title":"Simple and deep graph convolutional networks","venue":null,"work_id":"1a80dfd0-0d25-4629-bee0-833d89946473","year":2020},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.249524Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:9d5fd3ad9331ca493172130113e276f989081c386a1ff893d116eca526e2025d","observation_id":"c28aa7bf-8d83-4560-811e-47e5e24ae569","resolution":{"observed_at":"2026-08-16T04:10:20.764480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03393","last_updated":"2024-01-16T16:12:14Z","snapshot_observed_at":"2026-08-16T15:18:03.796110Z","submitted_at":"2023-07-07T05:31:31Z","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03393","snapshot_observed_at":"2026-08-16T04:10:19.253502Z","title":"Exploring the potential of large language models (llms) in learning on graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.253502Z"},"links":{"cited_paper":"/paper/2307.03393","citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:b897e6bec9af8d6deeded5c6c2dfa25e9b855b1b334a7237f3fcc761006c72a2","observation_id":"fad858a9-1f2e-4db4-ae10-37aae8bc2329","resolution":{"observed_at":"2026-08-16T04:10:19.253502Z","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":"2026-08-16T04:10:20.737918Z","title":"Wide & deep learning for recommender systems","venue":null,"work_id":"3a08fdcb-6722-4934-bd87-c47488f24c3a","year":2016},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.261284Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:88c492a81509ff4ffd7889e1c534c45b4dc81f3595f58237a6a7b3c8a94a8978","observation_id":"1b49bd40-52d5-41a0-9d62-69cbb539deab","resolution":{"observed_at":"2026-08-16T04:10:20.744367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.708730Z","title":"Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks","venue":null,"work_id":"ca27499f-6639-49f5-b3fd-eb0c6e8c2a11","year":2019},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.271425Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:8a42a44a4de71d4f5f9182a33066632bed04764e9c10d60c257452bc5c77e728","observation_id":"03e68c63-ae12-48ac-a64d-0c7599c12dff","resolution":{"observed_at":"2026-08-16T04:10:20.721517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.681798Z","title":"Polynormer: Polynomial-expressive graph transformer in linear time","venue":null,"work_id":"ef35ca7c-c505-4193-9c08-42446862c86a","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.284810Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:37790c31d5e91215ff74ecdac6eff8fd11445062b43ab0adfb705a0bb741b90e","observation_id":"f54f3ea2-3bad-4a56-8160-0f32c079e178","resolution":{"observed_at":"2026-08-16T04:10:20.692920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.656061Z","title":"and Lenssen, J","venue":null,"work_id":"21fa540b-463a-47bc-9970-fc64b035cb2a","year":2019},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.291673Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:faadd248390137acdc0e30a0a9ba54e3ec93f4f6897e8b3a45d646bd2423bbc3","observation_id":"2ac8fc84-c238-4732-b6f2-2dec15e8ece4","resolution":{"observed_at":"2026-08-16T04:10:20.663218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.627761Z","title":"Predict then propagate: Graph neural networks meet personalized pagerank","venue":null,"work_id":"5b07e3a5-d015-49a9-9f9d-4ae9c2729db0","year":2019},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.305675Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:7ec96a973c69ed8e9dc0e6daee6c1e94ae8feeda29e41145fc416eb1fc61ccde","observation_id":"d8778e9e-7a64-4653-b656-e2c20ec2b372","resolution":{"observed_at":"2026-08-16T04:10:20.641672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.309767Z","title":"S., Riley, P","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.309767Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:e1c8f791cba612b0b294b4634baa6e66431f934048da9a35f70684da0488838d","observation_id":"38023397-a9a1-4625-a0d5-bbbfef5fadc2","resolution":{"observed_at":"2026-08-16T04:10:19.309767Z","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":"2026-08-16T04:10:20.600438Z","title":"L., Ying, R., and Leskovec, J","venue":null,"work_id":"daa53bbb-dbb9-4e50-9892-012bf4e956c2","year":2017},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.314724Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:8f80c079fdcd33dafc7ca39a72544dd1896d0fb066d911f1da11e38acb549ea1","observation_id":"b2e69d3a-5449-4fb8-a2f6-74ffc023ca31","resolution":{"observed_at":"2026-08-16T04:10:20.605688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.319063Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.319063Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:ad90e12f01af44878574b507a87dc56ee616335dd39daa6f640634901f39daf0","observation_id":"d2b36570-c7f9-49e0-9e7b-1bde0179ca21","resolution":{"observed_at":"2026-08-16T04:10:19.319063Z","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":"2026-08-16T04:10:20.572771Z","title":"Harnessing explanations: Llm-to-lm interpreter for enhanced text-attributed graph representation learning","venue":null,"work_id":"edd47af3-82b7-4387-9838-216704916a39","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.326842Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:7014075bd9bdb55cf683cb82efaf063ab90257ed9025055f46c02a530f5dcf79","observation_id":"d6c68f71-153b-4d44-80d5-ed6d50afa66c","resolution":{"observed_at":"2026-08-16T04:10:20.578107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.335999Z","title":"and Szegedy, C","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.335999Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:7566f60775d5abd760d7695868359b729bff4f5afc4f17b98e017260119b1b81","observation_id":"22743fcf-67dd-4e64-9281-73f856056ae1","resolution":{"observed_at":"2026-08-16T04:10:19.335999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:10:19.341159Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.341159Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:562b3f185a2a7f1c9f29c00d4022ac5c2624a605dd38089927a13e0ad0195a89","observation_id":"8cc9f832-78da-4777-9992-334106f43187","resolution":{"observed_at":"2026-08-16T04:10:19.341159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:10:19.349557Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.349557Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:3d872cc37c90ed32c816fd7a5057673757580f91223f2c2e7f848499c7959d09","observation_id":"d410ee8d-c92d-4afc-a186-7b4a02f8b876","resolution":{"observed_at":"2026-08-16T04:10:19.349557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:10:19.355567Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.355567Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:2452aab7e50f2ed5e7be0438abee9cd838b42e764d48b83b09c6113b85c85f92","observation_id":"4735236f-a7a8-4906-94fc-ca29a0b31b72","resolution":{"observed_at":"2026-08-16T04:10:19.355567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:10:19.361711Z","title":"One for all: Towards training one graph model for all classification tasks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.361711Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:4906931973221b87da6c856d07f40a1f55991835d0c869614f290516988d387a","observation_id":"f38e2224-0c64-43b4-be70-5ddac2f2fd9f","resolution":{"observed_at":"2026-08-16T04:10:19.361711Z","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":"2026-08-16T04:10:20.491015Z","title":"Towards deeper graph neural networks","venue":null,"work_id":"714ea3ee-ae64-4ecc-87b2-495e50ecfab6","year":2020},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.367056Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:e8de3a4c0ee159f42cbda86b9b6cf908d5739558b1cb2f45d4e0350926890445","observation_id":"1c5b6732-172a-4df3-b9f7-3149b147f368","resolution":{"observed_at":"2026-08-16T04:10:20.496333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.470278Z","title":"Class-imbalanced graph learning without class rebalancing","venue":null,"work_id":"fead2160-3767-45d3-ba41-b257407aa2dc","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.371786Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:f6ff340cad73b1423fd97c91b2d9eeaa7af6f09b9a02561bf8ae5ca5f6a46d79","observation_id":"bb5d69e5-4ab8-48af-9d6f-7692248c51ef","resolution":{"observed_at":"2026-08-16T04:10:20.478936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.456298Z","title":"Revisiting heterophily for graph neural networks","venue":null,"work_id":"a138608a-ce88-48a3-a1ff-44f42281646d","year":2022},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.378433Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:19f645141422104dc9826566e09f6dd3bdcb5b06fc16d3c3bfff423309821e33","observation_id":"73f34db9-c18c-49ec-bcd3-ba5e6dd33870","resolution":{"observed_at":"2026-08-16T04:10:20.460386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.440351Z","title":"Fast graph sharpness-aware minimization for enhancing and accelerating few-shot node classification","venue":null,"work_id":"400370a1-5067-496a-a3a3-61a060845ee0","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.382889Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:4d69ef45e43ac015271bae863fd42a7291b0b69ec56859ccb3fa18a345913dcc","observation_id":"4ed4e116-55e0-424e-94f5-e2ca09aba9be","resolution":{"observed_at":"2026-08-16T04:10:20.445742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.417773Z","title":"Classic gnns are strong baselines: Reassessing gnns for node classification","venue":null,"work_id":"1f7af750-8014-4e91-b922-f0dba4e6b046","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.387968Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:4f09c25f87a8a91321e2a1ac9deae78723100848a2aecadb1629f26913c2845f","observation_id":"d6272d07-7895-49ab-9d2b-825154a362d9","resolution":{"observed_at":"2026-08-16T04:10:20.422762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.393887Z","title":"Is homophily a necessity for graph neural networks? In ICLR, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.393887Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:9723e7355464dcb9356013e4d27d2759dbbe623fe66173cd871ab6ea58fe659c","observation_id":"ef7953d9-d300-49f7-a729-5b65841fc1f9","resolution":{"observed_at":"2026-08-16T04:10:19.393887Z","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":"2026-08-16T04:10:20.382656Z","title":"The pagerank citation ranking: Bringing order to the web","venue":null,"work_id":"ea67616a-82a4-466a-a9f1-5e316c77170a","year":1999},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.400354Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:8cce41b8cbd509c647df4a3d9378d9045b09c9ebca4c1d99cb053505066ebd98","observation_id":"436c5f2b-7d5e-4609-bf95-525134e3eed4","resolution":{"observed_at":"2026-08-16T04:10:20.394379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.362137Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":"06104c58-eaa6-4f4c-8140-c8fe469409a8","year":2019},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.406357Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:c4a7561b16b67d0718a56b5614079559150c43049d46bae0bb43d54bd22074db","observation_id":"7bbf06d1-874d-4972-a09b-640a2f579fd3","resolution":{"observed_at":"2026-08-16T04:10:20.369545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.347077Z","title":"C.-C., Lei, Y., and Yang, B","venue":null,"work_id":"2dcae1bf-d2ed-4f94-992c-34c624452f10","year":2020},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.412320Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:0eea27be802c4f22f6a684139ec7f5e53b7e9f72ab7bcfca5d1ce4322f572efd","observation_id":"563e4d9a-cea9-42bd-9c21-13be0332a626","resolution":{"observed_at":"2026-08-16T04:10:20.352102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.330714Z","title":"Multi-track message passing: Tackling oversmoothing and oversquashing in graph learning via preventing heterophily mixing","venue":null,"work_id":"352518a0-efb2-45b5-b827-36a82722bfc0","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.419230Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:4449262a6d49e0c1c38e8654f02c9f37c40c77eae5670ba0c3a5bdcd0cb05037","observation_id":"b63abb02-63ff-4189-b2a3-919abe2f778e","resolution":{"observed_at":"2026-08-16T04:10:20.335170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.313438Z","title":"A critical look at the evaluation of gnns under heterophily: Are we really making progress? In ICLR, 2023","venue":null,"work_id":"4723f7c6-9172-4f4c-b9f5-a0cd71e7130b","year":2023},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.425629Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:2c9ea4764f87cbfd0eeabcc4913fa4ecf80be8944ac7774d790a191f4144a969","observation_id":"579831dc-2f25-4783-9b87-15834efc67fd","resolution":{"observed_at":"2026-08-16T04:10:20.319128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.295705Z","title":"P., Luu, A","venue":null,"work_id":"821718f9-521a-45cf-9f2a-e408865a27bb","year":2022},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.432061Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:7db590ca7ca6be9bdfffef5db57bc14319ef82772bcd0d639eadc6d1d357cb44","observation_id":"fdce7b7a-c075-4a25-bc63-8be160cb429a","resolution":{"observed_at":"2026-08-16T04:10:20.302493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.277935Z","title":"Dropedge: Towards deep graph convolutional networks on node classification","venue":null,"work_id":"852338e6-4d78-4011-bf9f-a4f82fe87065","year":2020},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.438307Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:ee2a7038a9bbff028c1988436b336ed54231cbe6718a5da84f18a2f3b8133230","observation_id":"d6f6da63-e2b7-4933-abe7-71ea8a138055","resolution":{"observed_at":"2026-08-16T04:10:20.285699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.263139Z","title":"Multi-scale attributed node embedding","venue":null,"work_id":"ad65112f-5f38-41b8-8ceb-01c889426577","year":2021},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.443736Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:65aa6acb1c9c945333013929d7952569c746ec40ccccfed7f8e44bdc21b59518","observation_id":"076541e8-13dd-4209-9b80-5723f01b25a2","resolution":{"observed_at":"2026-08-16T04:10:20.267506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.247972Z","title":"E., Hinton, G","venue":null,"work_id":"3b1bfe02-d998-49a2-8aa3-2b5690ef8a33","year":1986},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.447961Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:266d9bbc764abc568424879e9ca8cb633b2068e6d369f8a7cb8a03e95e2de69d","observation_id":"7019b0eb-8b1c-4f11-82cc-caa1d5eff507","resolution":{"observed_at":"2026-08-16T04:10:20.254388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.223208Z","title":"Collective classification in network data","venue":null,"work_id":"77adad25-7cfb-4f0e-944b-1a466085a21c","year":2008},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.451867Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:d7744cdd8adb94e2756269e364e3941a381bde72679d9a458d8c17dd33bb7826","observation_id":"f16a1155-6f97-4265-989c-2e52c9947112","resolution":{"observed_at":"2026-08-16T04:10:20.229688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.203044Z","title":"Ordered gnn: Ordering message passing to deal with heterophily and over-smoothing","venue":null,"work_id":"1764d77a-57fa-4bfe-9d0c-bdf375dee4f5","year":2023},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.455228Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:31478eba521cac96a1be4455fff4eb08fdf1515067872591046e890203f0aa54","observation_id":"33f919aa-4266-4b8b-8a50-f91a3160c548","resolution":{"observed_at":"2026-08-16T04:10:20.210548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.177334Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":"792cafa2-288d-48a6-8f82-0efe593efb3f","year":1929},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.459050Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:fe9f44ccc646a1143a5da0efc58045a1e0372f7a01f5f4d439abf27e1c8bb5d2","observation_id":"96a5184e-9cd1-44d5-aa5a-7742a8c42a43","resolution":{"observed_at":"2026-08-16T04:10:20.188292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.149614Z","title":"N., Kaiser, L., and Polosukhin, I","venue":null,"work_id":"f2298165-bd48-4046-807f-02c3fce29bbd","year":2017},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.633846Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:b78a04721a216efa0bcb59820b65c471613d7142ed2dc24075df1afb86b0fd77","observation_id":"82fa8bdf-5dba-456e-994b-50ecc4233bd9","resolution":{"observed_at":"2026-08-16T04:10:20.155487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.131527Z","title":"Graph attention networks","venue":null,"work_id":"379ce9fe-6647-4542-a36e-718be87ed133","year":2018},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.640015Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:c913ee61ffee5ad2b3aed398fc62a7a6a5de1a1c58b5d7bec95d67474e42991a","observation_id":"3ccb4d2b-6ad2-4391-9371-6f570446f4f2","resolution":{"observed_at":"2026-08-16T04:10:20.137815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.01315","last_updated":"2020-08-25T15:46:13Z","snapshot_observed_at":"2026-08-18T10:54:34.717319Z","submitted_at":"2019-09-03T17:10:28Z","title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.01315","snapshot_observed_at":"2026-08-16T04:10:19.645712Z","title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.645712Z"},"links":{"cited_paper":"/paper/1909.01315","citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:a0229caa28ddca7b3b8a6ee732f5db10ecad8d7037d5d811902e26b95e41a90d","observation_id":"8f4c674b-5aad-4880-9302-28366bb3bd34","resolution":{"observed_at":"2026-08-16T04:10:19.645712Z","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":"2026-08-16T04:10:20.112623Z","title":"H., Fifty, C., Yu, T., and Weinberger, K","venue":null,"work_id":"aab12d66-fb0e-4984-9e94-c0bf844c9e4a","year":2019},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.650754Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:793a8df40febeb578f35526e5b208fdd054451b0060359c593cb55d5524ff4a0","observation_id":"17ecb678-6d5c-44e6-a989-c5364bef45c9","resolution":{"observed_at":"2026-08-16T04:10:20.119291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.095664Z","title":"Nodeformer: A scalable graph structure learning transformer for node classification","venue":null,"work_id":"ec800ab4-eed0-4f76-815f-066a76de54f7","year":2022},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.654881Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:622abac6fc9b352420d6b68244bca8011a04c372bb80d0eba1d2a58df6df6258","observation_id":"2f3ade38-7ed3-4e5d-82ee-ab638794dbcf","resolution":{"observed_at":"2026-08-16T04:10:20.100806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.079023Z","title":"Sgformer: Simplifying and empowering transformers for large-graph representations","venue":null,"work_id":"6b731ed5-3334-4ce3-8d56-15b41bf2489a","year":2023},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.661045Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:89a7274bc5fc9966918cb7bcd6db2745aa86e59277ebd6df8150418cb0bbbced","observation_id":"94d49b2c-658e-4ff1-b32f-b3da434568cb","resolution":{"observed_at":"2026-08-16T04:10:20.083617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.061592Z","title":"Less is more: on the over-globalizing problem in graph transformers","venue":null,"work_id":"dc80d1fd-e925-46f3-98dd-7ab85cf1f96b","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.668838Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:eac9b1ad7ce0fd0bc4108a786eae1a24239cae110724ad4d917e32a9ca132c9d","observation_id":"83321f99-45db-482f-a7c1-7abba17e2840","resolution":{"observed_at":"2026-08-16T04:10:20.067499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:20.045821Z","title":"Representation learning on graphs with jumping knowledge networks","venue":null,"work_id":"501d10bd-78dc-4fc5-b750-df636bc95789","year":2018},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.673842Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:106dc842570c28a7ecc39cba00d6730bff441cddb7503f7fcd014a95c73e597e","observation_id":"c076decc-049a-4428-8abe-32df2c661de7","resolution":{"observed_at":"2026-08-16T04:10:20.051187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.679010Z","title":"How powerful are graph neural networks? In ICLR, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.679010Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:5fffcb48ca1718e509209dd285db0edbbd46a4d890afc16082513bfeabb36006","observation_id":"eb8afc3e-b33e-449a-9187-a3ac14e09464","resolution":{"observed_at":"2026-08-16T04:10:19.679010Z","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":"2026-08-16T04:10:20.018982Z","title":"S., ichi Kawarabayashi, K., and Jegelka, S","venue":null,"work_id":"5a9df021-10a6-4860-8ed1-1f57009392a6","year":2021},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.684325Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:59b91869e5045f4c94736941913f2c6d8402c7d92ea174decc3f0a7eccc05b45","observation_id":"363607a7-8247-46d0-8826-01008fd3b46a","resolution":{"observed_at":"2026-08-16T04:10:20.023861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.998871Z","title":"Graph neural networks are inherently good generalizers: Insights by bridging gnns and mlps","venue":null,"work_id":"bf854e6e-404a-4267-8480-a095461d446f","year":2023},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.691753Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:f89e422184d032bd26846fc70392a54bd584211857a12b50c1de85314fe05aa9","observation_id":"6df331b2-825d-4538-a7e7-96fbad023ef5","resolution":{"observed_at":"2026-08-16T04:10:20.007653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.701327Z","title":"W., and Salakhutdinov, R","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.701327Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:2e8733eafdf8fbd6572f77aa37c68d2cb4477fbcb9a13eec9ffb570e55f5609f","observation_id":"c0e03c30-dae8-4406-88cc-a7de5637582a","resolution":{"observed_at":"2026-08-16T04:10:19.701327Z","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":"2026-08-16T04:10:19.965823Z","title":"Do transformers really perform bad for graph representation? In NeurIPS, 2021","venue":null,"work_id":"d55c30f6-57a0-4053-93ef-a9880d050cdb","year":2021},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.709393Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:c03139f59c13219184513ec61e66a83440e2a05bfd3befbb7660302beeca13ce","observation_id":"70e50698-1552-4085-92ce-6090fd777ce0","resolution":{"observed_at":"2026-08-16T04:10:19.972084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.944816Z","title":"A complete expressiveness hierarchy for subgraph gnns via subgraph weisfeiler-lehman tests","venue":null,"work_id":"39d8be80-27bd-43e7-9dfe-035342896148","year":2023},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.716342Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:cf9ee37c786f27477259e80388c45e1024cd58d1d4ac5782ec34cee4f14f2776","observation_id":"0024199c-f419-45ee-8324-bf6bd633b97d","resolution":{"observed_at":"2026-08-16T04:10:19.951694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.923330Z","title":"Rethinking the expressive power of gnns via graph biconnectivity","venue":null,"work_id":"b3f95edb-f41c-4e69-9691-ae65ade4bbb8","year":2023},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.722507Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:070fb074d106739250b7661534ecc76bc4eabb82c188e4557552dc9cf54d3d49","observation_id":"53c0e16d-696a-4a4f-825d-85f378bacce5","resolution":{"observed_at":"2026-08-16T04:10:19.932348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.00955","last_updated":"2021-08-02T14:55:10Z","snapshot_observed_at":"2026-08-19T14:15:43.742272Z","submitted_at":"2021-08-02T14:55:10Z","title":"Evaluating Deep Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.00955","snapshot_observed_at":"2026-08-16T04:10:19.728502Z","title":"Evaluating deep graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.728502Z"},"links":{"cited_paper":"/paper/2108.00955","citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:81ba4a59fe63fd782158724863059e1b0c18e7540ef46183b27a55f8c6983a60","observation_id":"37c983f8-d0ef-4d82-80b3-e0e222884fdc","resolution":{"observed_at":"2026-08-16T04:10:19.728502Z","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":"2026-08-16T04:10:19.899736Z","title":"Online gnn evaluation under test-time graph distribution shifts","venue":null,"work_id":"899d29b5-6c73-4ab8-94db-ff15d33fe4f1","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.734225Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:49939134b28e9a2a89b8ffa823babaab2582cc0494afdf44b1e3130da8ad5eaf","observation_id":"80c8820d-172c-48ea-8ce2-a318268fdc43","resolution":{"observed_at":"2026-08-16T04:10:19.905656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.882461Z","title":"What is missing in homophily? disentangling graph homophily for graph neural networks","venue":null,"work_id":"cfd6c8bb-8040-454d-91d1-90a5d76ccc21","year":2024},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.739649Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:ff72b10feeaa849c9623a6fea4e068b9180e0566261341f855e8060a6bbabcd3","observation_id":"5dbf6c64-99f8-4dd9-8231-ee0f77680cb2","resolution":{"observed_at":"2026-08-16T04:10:19.887066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.861618Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","venue":null,"work_id":"afc7f800-c796-4c7d-9085-927214e1651c","year":2020},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.747538Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:a82122d4726d3423fbf00f1cee82dafe32d49a9224cbd7cab519f38201402806","observation_id":"583234e8-548e-4684-b626-be1741e23d26","resolution":{"observed_at":"2026-08-16T04:10:19.870197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-16T04:10:19.752352Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-16T04:10:19.752352Z"},"links":{"citing_paper":"/paper/2505.02020"},"observation_digest":"sha256:6d9e4db03bb69933718da21540700a512caa3cb9725f113e7b641c469791e420","observation_id":"0be06b8b-24f1-4d3b-819f-8afffd103539","resolution":{"observed_at":"2026-08-16T04:10:19.752352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.02020","last_updated":"2025-05-04T07:53:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T04:01:24.990630Z","submitted_at":"2025-05-04T07:53:16Z","title":"Wide & Deep Learning for Node Classification"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":41},"total_outbound_references":55},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2505.02020."}