{"as_of":"2026-08-17T16:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee409e278bcad5057abbd85eb2094389d66a5d38b80166561941fd020cabd2ff","coverage":[{"denominator":62,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":62,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:43:49.216345Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-14T19:31:41.045648Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-14T19:32:52.027685Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"cited_work":{"arxiv_id":"2505.15842","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.15842","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ah-ugc: Adap- tive and heterogeneous-universal graph coarsening.arXiv preprint arXiv:2505.15842, 2025a","venue":null,"work_id":"b104fb15-a550-4435-95cd-36ba6487bbad","year":null},"citing_paper":{"arxiv_id":"2605.13021","last_updated":"2026-05-13T05:24:35Z","snapshot_observed_at":"2026-08-12T15:13:18.107542Z","submitted_at":"2026-05-13T05:24:35Z","title":"Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-14T19:31:41.045648Z"},"links":{"cited_paper":"/paper/2505.15842","citing_paper":"/paper/2605.13021"},"observation_digest":"sha256:43a9868f86671fac5e2381c366a36d952efa6c093f200512f66035ff5d7d7440","observation_id":"63488708-4052-4222-aae4-92313a535e49","resolution":{"observed_at":"2026-05-14T19:32:52.030841Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.15842/citation-record","integrity":"/paper/2505.15842/integrity","json":"/paper/2505.15842/citation-record.json","paper":"/paper/2505.15842"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:43:51.197123Z","title":"A novel coarsened graph learning method for scalable single-cell data analysis,","venue":null,"work_id":"39a13f77-6f7a-4da0-b493-03c6ec357fcd","year":2025},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.065824Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:a8e4efe09a7434dfc206c5525e36d35833dd37337dc29330b283d3c7b267f492","observation_id":"7d9e18a6-4f85-4950-9285-49d7de1d8015","resolution":{"observed_at":"2026-08-15T20:43:51.200831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:51.186103Z","title":"Protein interface prediction using graph convolu- tional networks,","venue":null,"work_id":"2c612dbe-28e6-4fbe-862c-399488437c16","year":2017},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.159933Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:83fc13f5412e4940e34e1ac43f854b492e53298345ccf1dad015dbd3cb5192fb","observation_id":"c19f56ba-f89d-49fb-81ba-4fb704ce2d11","resolution":{"observed_at":"2026-08-15T20:43:51.189922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:48.275716Z","title":"A comprehensive survey on graph neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.275716Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:9ce5b1311add15ac8192b87f826ad0fa9d68411af93b10bbd263e36586fc6885","observation_id":"c246d356-8566-4fae-8847-14d600c75dae","resolution":{"observed_at":"2026-08-15T20:43:48.275716Z","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":"2026-08-15T20:43:51.166332Z","title":"Ugc: Universal graph coarsening,","venue":null,"work_id":"9e461eff-7a59-4812-9a3c-05f166232670","year":2024},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.320342Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:9021b37f83bca49c36efcaaae7ac0473d0034a9c23ecd81053c0ca204e2e197a","observation_id":"c5f06eaa-6659-42eb-8160-64fbb69de6a1","resolution":{"observed_at":"2026-08-15T20:43:51.170343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-17T10:49:36.026134Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-15T20:43:48.325364Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.325364Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:43866c203bb7aff1dafe8537d28a6bc4d04b4e07bfb9bd2c023a53709e70b648","observation_id":"f32d7d92-0e02-42d7-ae17-c9cdaba73b2f","resolution":{"observed_at":"2026-08-15T20:43:48.325364Z","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":"2026-08-15T20:43:51.154193Z","title":"Microsoft academic graph: When experts are not enough,","venue":null,"work_id":"b56e5972-6d51-4423-8bda-199ba68485e0","year":2020},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.331283Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:821bfa7f3a81709ea5c23c98c28bcca93f6f9b55aff7c2acff232d0c1d1dd0c0","observation_id":"d0fba84f-355a-4d32-b97b-fa1737a1620a","resolution":{"observed_at":"2026-08-15T20:43:51.158342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:51.142115Z","title":"Datasets and interfaces for benchmarking heterogeneous graph neural networks,","venue":null,"work_id":"753ea0ae-b8da-4147-ac2d-96c6959f55ad","year":2023},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.336725Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:c7c49ad196a969c8334e43d797547dd8645799dd995a524bbea8a9462e30069a","observation_id":"0b2119cf-d481-4d49-9be7-8e616e1a4ae7","resolution":{"observed_at":"2026-08-15T20:43:51.146714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:51.129927Z","title":"Heterogeneous network representation learning: A unified framework with survey and benchmark,","venue":null,"work_id":"e8ec9283-cb7f-465d-b920-82494f232224","year":2020},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.340968Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:1c194bda35b2f9abea95f8a09d9b11368c10fa48b8ecd7646228ee19f867130c","observation_id":"ca0fa76c-4ef5-4397-86da-df2d3e12fceb","resolution":{"observed_at":"2026-08-15T20:43:51.134089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:51.117204Z","title":"Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks,","venue":null,"work_id":"11e1d4a5-8d28-4596-9776-37447dccfcdf","year":2021},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.344871Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:3701951a05c4e493cbb6581df97ceb8256bc0cf6d77e327ccbd946c27aa9f546","observation_id":"6f2496f5-642b-4b53-8bce-e6be278cc073","resolution":{"observed_at":"2026-08-15T20:43:51.121893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:51.104655Z","title":"Benchmarking graph neural networks,","venue":null,"work_id":"64b73b24-936e-4134-a63a-117b4b3b17ca","year":2023},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.349684Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:ab03b00a79c688c37b3927971923e1f8bc4edf8158b20fada20d8c58d492ad13","observation_id":"6ee783af-9eff-4dcb-b5e1-ebbbef61bb7d","resolution":{"observed_at":"2026-08-15T20:43:51.109092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.959650Z","title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods,","venue":null,"work_id":"679b5364-545b-4db6-8cfd-0744c7c5416d","year":2021},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.354738Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:1528ba62b7541c02dd182aabe67ec0ff86ba0a0949d97e4405d4f2fdbd2aa95d","observation_id":"305db3aa-3348-4482-bcab-bdd62be8fb05","resolution":{"observed_at":"2026-08-15T20:43:51.039391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.853638Z","title":"Heterogeneous graph neural network,","venue":null,"work_id":"7b58d968-58f8-49f4-a144-c0f3baa65cc2","year":2019},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.360144Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:5112cdad6c0e9bec0eb8bc7f6297f9cd4b2834dbc0c15f6c17b68db24f010441","observation_id":"0233e7e6-f3d4-46ac-a00a-37fb1598df09","resolution":{"observed_at":"2026-08-15T20:43:50.874367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.841062Z","title":"Goat: A global trans- former on large-scale graphs,","venue":null,"work_id":"de6056e6-fc45-421a-a83c-2f5692adba90","year":2023},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.365686Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:8ac5688377e972808059dd90569c2b544b0ab480aa0ce85fc8f90fc3aa974cff","observation_id":"ec7d11b7-f806-4395-9fb8-0ef1384ed4b8","resolution":{"observed_at":"2026-08-15T20:43:50.845716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.04931","last_updated":"2020-02-16T00:42:48Z","snapshot_observed_at":"2026-08-17T15:19:05.606929Z","submitted_at":"2019-07-10T21:11:13Z","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.04931","snapshot_observed_at":"2026-08-15T20:43:48.369886Z","title":"Graphsaint: Graph sampling based inductive learning method,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.369886Z"},"links":{"cited_paper":"/paper/1907.04931","citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:6f525bba7f594507976a9e9cf39739e2423f7ce9159bbfd534498d1a1af1202c","observation_id":"3b948bfb-bb43-40a4-a346-eff6871ac35b","resolution":{"observed_at":"2026-08-15T20:43:48.369886Z","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":"2026-08-15T20:43:50.826350Z","title":"The extreme classification repository: Multi-label datasets and code,","venue":null,"work_id":"826dca4b-5915-4ab0-9471-543fab375fca","year":2016},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.375005Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:b27b57087860cc3ec6e662ba5c4a0fe8514427264f5e6b01aacfb496953bcfff","observation_id":"fdbe4c6f-e3cb-48dc-82ce-93b1e83b2ea0","resolution":{"observed_at":"2026-08-15T20:43:50.831445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.813521Z","title":"Spectral clustering with graph neural networks for graph pooling,","venue":null,"work_id":"c4e92b42-cf42-4d0e-bd4a-e12ecb86b56d","year":2020},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.379616Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:824e87202751878c611521f9f2d7aa2e280c6484ccd5e5f8ff73509661748c9f","observation_id":"e6453778-da95-4414-b2bc-688cb4b2094d","resolution":{"observed_at":"2026-08-15T20:43:50.817686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.801300Z","title":"Weighted graph cuts without eigenvectors a multilevel approach,","venue":null,"work_id":"c5532f07-e3ad-4eed-9625-1b4871983c1a","year":1944},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.383665Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:5fa125985edfb87fd7a5e4a82a902a075d1bc9c6b3c0f5257f7fd41eb2a170da","observation_id":"8d05a22c-7280-45ab-88e9-84448c0692d1","resolution":{"observed_at":"2026-08-15T20:43:50.805633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07580","last_updated":"2022-09-27T20:48:28Z","snapshot_observed_at":"2026-08-16T17:49:14.885073Z","submitted_at":"2021-10-14T17:42:14Z","title":"Graph Condensation for Graph Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07580","snapshot_observed_at":"2026-08-15T20:43:48.469476Z","title":"Graph condensation for graph neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.469476Z"},"links":{"cited_paper":"/paper/2110.07580","citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:8d26de2c3198cf5cded5e1bf54cfc5d27ec68365f2af2b5cb058c88c4e7d81e6","observation_id":"70d3ba93-af46-446f-9b7c-5698d65b9ffb","resolution":{"observed_at":"2026-08-15T20:43:48.469476Z","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":"2026-08-15T20:43:50.788675Z","title":"A unified framework for optimization-based graph coarsening,","venue":null,"work_id":"ce2a1b3f-167b-4d87-b48f-6d5f4a8c393b","year":2023},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.591772Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:c540d0158de1f6c7ae1b55e6a2ba4f359091630c61b0e0558db60c38d9ed1f69","observation_id":"ba7676a5-2885-4c08-a07a-aa8fefa8d4e8","resolution":{"observed_at":"2026-08-15T20:43:50.793155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.777139Z","title":"Graph reduction with spectral and cut guarantees.,","venue":null,"work_id":"b1627303-9a66-4795-9235-c4c1f64bd706","year":2019},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.631359Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:1a1d4372ed762d49a88b319a9f75ee815984bcda0700dd84210dbc0f6a997c7c","observation_id":"d926bb9e-dda6-464c-ba6c-190a7c3db841","resolution":{"observed_at":"2026-08-15T20:43:50.780795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.764081Z","title":"Locality-sensitive hashing scheme based on p-stable distributions,","venue":null,"work_id":"7ea88ed1-573f-4a3c-bc00-77fa7f0b2396","year":2004},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.635539Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:5651a2dc7d106f52dbe4e868407b30821193c853148489232e30becf4ef7a5af","observation_id":"d377c7de-c31f-4ec5-b88d-f1aa14f64709","resolution":{"observed_at":"2026-08-15T20:43:50.768688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.673655Z","title":"Linear complexity framework for feature-aware graph coarsening via hashing,","venue":null,"work_id":"48d46a68-b7e0-463d-9626-7e0127f09cff","year":2023},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.639609Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:eea1747cbd7e4e5bf194325cff032ab9d5345643b44c362ca79ace2f1fe0bce6","observation_id":"4f6a0a98-9a4e-44f3-b80b-2b1cbe9de683","resolution":{"observed_at":"2026-08-15T20:43:50.701608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.651202Z","title":"Consistent hashing and random trees: Distributed caching protocols for relieving hot spots on the world wide web,","venue":null,"work_id":"0817b9ef-2a86-48ae-a4cd-58431c25a186","year":1997},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.643483Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:c4ff99c5b862a3dd726ecd9847b7b75fd5e6ecbd7d138ec2138c20f292f68fbc","observation_id":"c7b9d0d0-67e9-4fcc-a5a7-2750adfea3c1","resolution":{"observed_at":"2026-08-15T20:43:50.655517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.638435Z","title":"Revisiting consistent hashing with bounded loads,","venue":null,"work_id":"be0b5a6c-f79d-46a7-8b73-06f26c6ec9cf","year":2021},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.647302Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:1afeb4cb08c57c786157697492b00a2273fb65300093e956009c5860c0460149","observation_id":"6fe4d930-c6c0-495b-887e-1fcf71503094","resolution":{"observed_at":"2026-08-15T20:43:50.642503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.625085Z","title":"Heterogeneous graph condensation,","venue":null,"work_id":"378da377-45fb-467e-a269-ca535015e6ba","year":2024},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.650750Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:b2b030039eac6186d05af122a3149d3936a016bcfc513f01b0797badd24e3d02","observation_id":"c4549633-5a1e-4b47-abfc-93d167a074ae","resolution":{"observed_at":"2026-08-15T20:43:50.630203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.612636Z","title":"Relaxation-based coarsening and multiscale graph organiza- tion,","venue":null,"work_id":"bb4fae95-c0fb-48fc-9ffb-65c705f4e5e8","year":2010},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.654418Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:ab057598b569de0a843f2320111097572a96d47121b7704318b15995d3a0d299","observation_id":"a79eb983-77ce-47b2-ada0-058f7cc8bca5","resolution":{"observed_at":"2026-08-15T20:43:50.617049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.600213Z","title":"Algebraic distance on graphs,","venue":null,"work_id":"f3c0e2ce-5b50-41fa-b620-f0e88e548a7c","year":2011},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.658069Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:9954d525873127dcd21d80dac99b411a2369c960de42301c6d756b04d771d802","observation_id":"f1ad93a2-4f15-445f-910f-56bee1a518bf","resolution":{"observed_at":"2026-08-15T20:43:50.604300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.587562Z","title":"Lean algebraic multigrid (lamg): Fast graph laplacian linear solver,","venue":null,"work_id":"a5a8bf95-d8f1-4523-9442-8907196de42f","year":2011},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.662070Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:514586cb935019d5d7f9147b2fefcbeb43d349194acb2587e76114e80eec586e","observation_id":"bf4ea34e-0bbb-4094-b7f6-aabeefdec2d4","resolution":{"observed_at":"2026-08-15T20:43:50.591930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:48.666365Z","title":"Kron reduction of graphs with applications to electrical networks,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.666365Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:1d240ef5b34af660fcb53d4b3d0fb3935e4fe04e9cd366b04e8d2ce6602db02c","observation_id":"24677346-cda9-4bc0-b79c-f2421d6a2b28","resolution":{"observed_at":"2026-08-15T20:43:48.666365Z","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":"2026-08-15T20:43:50.565110Z","title":"Graph condensation for graph neural networks,","venue":null,"work_id":"e56d0084-835a-4317-a36e-14bc0f398f08","year":2021},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.669882Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:97ef9ee788229470c169d20b0e123c4df235153a0617077a271e4900b6da1f9c","observation_id":"229c9649-ce84-41fb-9d1c-1af3b668ff27","resolution":{"observed_at":"2026-08-15T20:43:50.569698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.550426Z","title":"Structure-free graph condensation: From large-scale graphs to condensed graph-free data,","venue":null,"work_id":"fb57c30e-259f-4166-ae48-e06d6c2fdc79","year":2024},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.673590Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:16af6898811551189d999dc0a724152ddcb9d064bbf57cf6a6b7e368b4beb1f0","observation_id":"cce06530-4fe7-4f0c-9d9d-ec0c6f8787fa","resolution":{"observed_at":"2026-08-15T20:43:50.555659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.518632Z","title":"Approximate nearest neighbors: Towards removing the curse of dimensionality,","venue":null,"work_id":"2e92c820-9a90-48b6-80bc-efd57f15c683","year":1998},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.677249Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:c25397827cdaa717a473ee473f2ecf2b2b239b5b2addfe08a956f010ee6f48fa","observation_id":"98c96afc-b9da-418e-abca-212e8be2dd50","resolution":{"observed_at":"2026-08-15T20:43:50.541164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.430573Z","title":"Revisiting semi-supervised learning with graph embeddings,","venue":null,"work_id":"accc0954-13cb-484f-b476-6598a20f79fa","year":2016},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.680969Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:58c3c876fb2c784b40655f5ecdec3265b519e376c87a06f7ebcbd7866957c521","observation_id":"bd48e9ad-d872-4215-a2e4-86da0c17e486","resolution":{"observed_at":"2026-08-15T20:43:50.481670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.280049Z","title":"Pitfalls of graph neural network evaluation,","venue":null,"work_id":"78bbf4cb-4dbe-4ef0-8cb7-d9af86ba3fee","year":2018},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.685404Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:49d9eaeb3707f44387d000e0d5b262c068b62c4bba488da6e856ada487d51ebd","observation_id":"7a6d792f-2cda-4f48-aa69-c384ec348247","resolution":{"observed_at":"2026-08-15T20:43:50.339469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.266718Z","title":"Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding,","venue":null,"work_id":"700665ea-cf56-4798-b238-e318b60f5b19","year":2020},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.699509Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:9bc3afc3e1f49ad809c7c5be64fe8add0862ef213a63857e98c860273b5b47f9","observation_id":"7cdeed34-3705-4906-a6d4-b8cc4e6e7f0c","resolution":{"observed_at":"2026-08-15T20:43:50.271515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.252422Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs,","venue":null,"work_id":"d8b32c61-9f76-4237-bf40-f2f2c5b566d6","year":2020},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.759502Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:990371f69dbfca82a0f87c7934b1c39d63d3bf2a9ba5367b9dcc77e49a2076ac","observation_id":"2b961469-b619-451a-bfa5-66bbf7b8ed28","resolution":{"observed_at":"2026-08-15T20:43:50.256689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05287","last_updated":"2020-02-14T01:47:35Z","snapshot_observed_at":"2026-08-10T23:39:48.575656Z","submitted_at":"2020-02-13T00:03:09Z","title":"Geom-GCN: Geometric Graph Convolutional Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05287","snapshot_observed_at":"2026-08-15T20:43:48.792075Z","title":"Geom-gcn: Geometric graph convolutional networks,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.792075Z"},"links":{"cited_paper":"/paper/2002.05287","citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:a59b71c60302d49a315c3d969f93848db3fbc5e30875f52364d5ac88e56ca2f9","observation_id":"3d518039-f980-45ed-a06f-963aea5f4f88","resolution":{"observed_at":"2026-08-15T20:43:48.792075Z","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":"2026-08-15T20:43:50.239563Z","title":"Graph neural networks with heterophily,","venue":null,"work_id":"d8d06cb7-71c4-4360-b7de-16ec038da60d","year":2021},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.821067Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:05a1a28d5385da87a1815da9df1805f542a51f5288b5e4d8637fb3813158aa7a","observation_id":"8471d217-6427-455e-af88-421f798145f0","resolution":{"observed_at":"2026-08-15T20:43:50.244088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.227556Z","title":"Gbk-gnn: Gated bi-kernel graph neural networks for modeling both homophily and heterophily,","venue":null,"work_id":"b6d8c078-dc5a-4376-a834-954bd1951ede","year":2022},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.826132Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:54d6d882bf5f4a95260ad02a61cd7cde9772f63c00b5509e03a6e01275c53b99","observation_id":"9bbdac64-3698-448f-bf64-08fc4f9b7806","resolution":{"observed_at":"2026-08-15T20:43:50.231564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:50.066017Z","title":"Inductive representation learning on large graphs,","venue":null,"work_id":"b15d688f-b212-4dc0-919f-d6dd3ecc441c","year":2017},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.830372Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:346484ecf9e3d6ca17d9ded4007df4440d6227d9ec0bb08bea4882bc4bff1255","observation_id":"619aadbc-c7cf-4eed-8bfb-82d6f68662dc","resolution":{"observed_at":"2026-08-15T20:43:50.181885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.898779Z","title":"Graph attention networks,","venue":null,"work_id":"0ceb2674-19dd-434c-a56e-ef82ebff5c03","year":2018},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.834740Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:3d285eae6270d0dc186695fd432ea4ee7a637299a26b965639bcbe2e1634e2b3","observation_id":"64e48545-4be6-4b81-b705-1d1238da28f7","resolution":{"observed_at":"2026-08-15T20:43:49.936266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00826","last_updated":"2019-02-22T19:15:54Z","snapshot_observed_at":"2026-08-13T05:06:48.606308Z","submitted_at":"2018-10-01T17:11:31Z","title":"How Powerful are Graph Neural Networks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00826","snapshot_observed_at":"2026-08-15T20:43:48.838935Z","title":"How powerful are graph neural networks?,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.838935Z"},"links":{"cited_paper":"/paper/1810.00826","citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:01aa366ff6797636fce5cae2ef96b627ac798b01e3a47d0b8585b35e0b5b43d0","observation_id":"afb34c76-b858-40d7-b9b1-c2f51d596020","resolution":{"observed_at":"2026-08-15T20:43:48.838935Z","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":"2026-08-15T20:43:49.876261Z","title":"Scaling up graph neural networks via graph coarsening,","venue":null,"work_id":"39f4118a-95ec-44b8-9167-7435be7a81f7","year":2021},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.843675Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:0a8cc00e38ae1ec747ddc31032c32ea33e05a7688d16da37fb5212416b7cb7af","observation_id":"7111615d-5c43-470f-af9b-4586e048934b","resolution":{"observed_at":"2026-08-15T20:43:49.880724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07988","last_updated":"2021-10-26T20:07:59Z","snapshot_observed_at":"2026-08-14T06:24:06.038319Z","submitted_at":"2020-06-14T19:27:39Z","title":"Adaptive Universal Generalized PageRank Graph Neural Network","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07988","snapshot_observed_at":"2026-08-15T20:43:48.848191Z","title":"Adaptive universal generalized pagerank graph neural network,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.848191Z"},"links":{"cited_paper":"/paper/2006.07988","citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:d20d3a772adec46dfb26dc52cb28795cfec4788dad9296c6e9b9a45a999d834c","observation_id":"958d8c14-26bc-4334-8e89-f355268f0bd4","resolution":{"observed_at":"2026-08-15T20:43:48.848191Z","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":"2026-08-15T20:43:49.862149Z","title":"Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing,","venue":null,"work_id":"1eaad7ae-8cc0-4263-bdfc-76fb51ab76fb","year":2019},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.853357Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:3207799e16a7738ec6bb163a1218c0625b384753d334ecc9e93a83cd13ba55a1","observation_id":"1434c5df-4125-4d55-adf3-52fea3b90bdf","resolution":{"observed_at":"2026-08-15T20:43:49.866946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.847324Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs,","venue":null,"work_id":"e9aa9f9e-268c-4817-8454-e12914386ae1","year":2020},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.906089Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:a22cddec6d4c2618a16db685ccefac1d5499eb935e90b00cfca18dd6b8cfeee4","observation_id":"7ea9188c-3865-40c6-8174-52147b4a245b","resolution":{"observed_at":"2026-08-15T20:43:49.852403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.829341Z","title":"Simple and deep graph convolutional networks,","venue":null,"work_id":"8ec4a800-555d-4b3f-8d57-84729acf58a2","year":2020},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.985478Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:3a9daf246ebb78fc0fe9b11ff10d9f161349144b52d961538047a8d6293248bc","observation_id":"a1b94c91-09ec-4160-a4fe-94b965259f99","resolution":{"observed_at":"2026-08-15T20:43:49.836794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.816096Z","title":"Representation learning on graphs with jumping knowledge networks,","venue":null,"work_id":"0d2ef892-b166-4b65-8329-c909b91ef577","year":2018},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.991693Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:d12c143cf18670446d2115ff0d25efdce0c97949c978559e160180b4bb47c760","observation_id":"38ebba92-a56f-4028-809e-bfa57a6d61ce","resolution":{"observed_at":"2026-08-15T20:43:49.820266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:48.996704Z","title":"Simplifying graph convolutional networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:48.996704Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:c3f42c161cfa81ea7d895057924176c650d47ba0a3f0ee4a8041e83b003f9170","observation_id":"9cd4f824-4066-469d-a32d-7678cd2282ef","resolution":{"observed_at":"2026-08-15T20:43:48.996704Z","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":"2026-08-15T20:43:49.795576Z","title":"Kernelized locality-sensitive hashing for scalable image search,","venue":null,"work_id":"dda2ef96-ff4c-45b6-a631-ef6399b54dfe","year":2009},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.001926Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:e7f9cb0292ef4bbb20f432f1c9274d3bf840c7c503b61ad07def74ada0739c64","observation_id":"ccdbf906-13c4-4db8-8239-35d321c9a0e2","resolution":{"observed_at":"2026-08-15T20:43:49.800136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.783615Z","title":"Efficient large-scale sequence comparison by locality-sensitive hashing,","venue":null,"work_id":"e0e92a2c-b4ca-46d4-9fe0-0c77ac00036f","year":2001},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.007006Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:451b657b19a14202882b20e274a05833ea52270d6c99658b79f120524197984c","observation_id":"ffac6016-aff7-4b40-b505-715d42be8c1c","resolution":{"observed_at":"2026-08-15T20:43:49.787978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.772675Z","title":"Scalable near identical image and shot detection,","venue":null,"work_id":"1e9c0cb9-ea89-4dce-91d8-b2b7e110adcb","year":2007},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.015837Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:9f6730f6d770712a2852308a683f5f17562a7ffd994dae949c74718e953a85ee","observation_id":"8a72c10a-4ee0-410f-8e54-8eec000bd3ab","resolution":{"observed_at":"2026-08-15T20:43:49.777014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.715815Z","title":null,"venue":null,"work_id":"1d43b1a2-202b-4b75-9891-15bb57570bc6","year":2004},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.021692Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:a148d2cd7f79edf214cd3a7c08598b03d0483de54c125fd699e3963f1f864923","observation_id":"f2ca7e3f-a311-4fcd-8b69-7f2147ce19cc","resolution":{"observed_at":"2026-08-15T20:43:49.763651Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.617751Z","title":"Hyperdefender: A robust framework for hyperbolic gnns,","venue":null,"work_id":"6696a26b-58e0-438c-9443-27135e5d060a","year":2025},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.026759Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:bfc5c1ccd87fbe37ceee1c4cf998f17a256dff045bc44fa4033ab27622a9e6fd","observation_id":"d5452809-d1af-4792-b8ce-968b4b07d050","resolution":{"observed_at":"2026-08-15T20:43:49.665673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.527429Z","title":"Encoding social information with graph convolutional networks forPolitical perspective detection in news media,","venue":null,"work_id":"0ef3ef79-020e-4a31-a22e-a2905d5e7f9b","year":2019},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.031008Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:94d62e4a170ca7d6a0c0fb8a5deda23ac67ca6335f7522ad90a11d1135a27f79","observation_id":"8d1d5c84-2b4d-46da-b9d0-0838578faac6","resolution":{"observed_at":"2026-08-15T20:43:49.567669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.514563Z","title":"Reinforced genetic algorithm learning for optimizing computation graphs,","venue":null,"work_id":"c3510fe5-4e23-4bc5-aa32-0a27a013e01d","year":2019},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.111653Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:305c070096c2eb393c72e18fda421d24d9f04a21397606ed91e58b3ac78fd190","observation_id":"e4ea0c19-437e-493a-b103-b46319d5ecf8","resolution":{"observed_at":"2026-08-15T20:43:49.518626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03409","last_updated":"2021-06-18T16:32:43Z","snapshot_observed_at":"2026-08-16T19:15:13.406583Z","submitted_at":"2020-10-07T13:34:49Z","title":"Learning Mesh-Based Simulation with Graph Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03409","snapshot_observed_at":"2026-08-15T20:43:49.186384Z","title":"Learning mesh-based simulation with graph networks,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.186384Z"},"links":{"cited_paper":"/paper/2010.03409","citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:61a995a97245b753c733705a64a3ca109de71c0768a5412c60d8375649c5a606","observation_id":"1eaf2d1d-36b6-4739-9790-8299dbd33a84","resolution":{"observed_at":"2026-08-15T20:43:49.186384Z","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":"2026-08-15T20:43:49.500084Z","title":"Graph convolu- tional neural networks for web-scale recommender systems,","venue":null,"work_id":"732e6f2d-1ce6-450f-a8ca-bb086b260d35","year":2018},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.193668Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:a2f53d757396997ea17b613951003cd9e9e05edacc410570635f73ed4d801d34","observation_id":"7ecaf076-67f6-4a10-aada-65192e1a19cb","resolution":{"observed_at":"2026-08-15T20:43:49.504865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.485345Z","title":"A unifying framework for spectrum-preserving graph sparsification and coarsening,","venue":null,"work_id":"a5e19579-1dca-4602-bcb7-e61483b7c33c","year":2019},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.198525Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:d76a956dc7c29d5e072d41e6fc1612e7b8931f8e123dded8939c86590cc52a72","observation_id":"0ffa2031-9a9f-41f6-b457-55204d94eb14","resolution":{"observed_at":"2026-08-15T20:43:49.489482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.471268Z","title":"Graph summarization methods and applications: A survey,","venue":null,"work_id":"78bf0c36-f11a-4a48-b61b-e7ca6166467c","year":2018},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.203986Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:38db9f641aae6d495b98f8ab6a51d949c180e89b3e12d2f936e0221c6e83afbf","observation_id":"a5afff38-5ca5-4332-ac66-8d0cb7f9bfa3","resolution":{"observed_at":"2026-08-15T20:43:49.476925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.433800Z","title":null,"venue":null,"work_id":"c4b68583-9321-4c6b-bf1b-63c1017c2903","year":null},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.210518Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:14cd0c154f6ebfb613230c654847cc4132fbdf36a7502299269326b0c4e5fd01","observation_id":"ddaa2523-70ef-4df6-8abd-8ee9312b83cf","resolution":{"observed_at":"2026-08-15T20:43:49.461099Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:43:49.340086Z","title":null,"venue":null,"work_id":"00a9d515-bb0f-4138-a22f-c4280ae55f76","year":null},"citing_paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T20:43:49.216345Z"},"links":{"citing_paper":"/paper/2505.15842"},"observation_digest":"sha256:2c4b8da10b5d1e125c6eb1a6c23bbb0f0d60b4eb4f6e2322c031b82be299d5b0","observation_id":"fac252d1-77a1-4fdf-99ae-a19f77a61371","resolution":{"observed_at":"2026-08-15T20:43:49.397481Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.15842","last_updated":"2025-05-18T09:57:33Z","latest_version":1,"primary_category":"cs.SI","snapshot_observed_at":"2026-08-16T17:12:31.224404Z","submitted_at":"2025-05-18T09:57:33Z","title":"AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening"},"reference_resolution":{"displayed":62,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":49},"total_outbound_references":62},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2505.15842."}