{"as_of":"2026-07-22T05:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:16679453c86550f7ff7ac4e7d3be343fc5781de7d20708fb2af38dcc727a9f60","coverage":[{"denominator":53,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":53,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-24T08:44:23.340180Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-07-21T06:31:05.380196+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":"2026-07-01T06:10:26.634933Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-01T09:45:40.658923Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"cited_work":{"arxiv_id":"2305.09958","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.09958","snapshot_observed_at":"2026-07-01T09:45:40.658923Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","venue":"cs.LG","work_id":"892e3e0e-a4ab-4dd7-a899-7adf22206fa2","year":2023},"citing_paper":{"arxiv_id":"2606.32016","last_updated":"2026-06-30T17:47:39Z","snapshot_observed_at":"2026-07-07T00:05:37.068846Z","submitted_at":"2026-06-30T17:47:39Z","title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","version":1},"reference_index":123,"source":"arxiv_source","source_observed_at":"2026-07-01T06:10:26.634933Z"},"links":{"cited_paper":"/paper/2305.09958","citing_paper":"/paper/2606.32016"},"observation_digest":"sha256:abc66d2cc900ebeb2bdc48e14c419652c23cd91733d21a33e431b7fea6f1eb70","observation_id":"0a61fcb1-a327-4ae6-9da5-4a8979ac8bd7","resolution":{"observed_at":"2026-07-01T09:45:40.660564Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.09958/citation-record","integrity":"/paper/2305.09958/integrity","json":"/paper/2305.09958/citation-record.json","paper":"/paper/2305.09958"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Semi-supervised classifica- tion with graph convolutional networks","venue":null,"work_id":"b03f60cc-ca02-4f38-aa63-0fad387ae07d","year":2017},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:246e65c50a673f9abbc77895a8aea96a66cfa135dfa423fa0e5a74d0319f2b80","observation_id":"1fda8f56-0037-4691-b693-e07e171c61c4","resolution":{"observed_at":"2026-05-24T08:46:06.141300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":"479350dd-8d02-4aec-98b1-a699184b14e0","year":2017},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:43241991d4ac1984883235b2c48e4532dc49fe15697e985bfad8d03aa79df872","observation_id":"2e5c47e6-7f09-48bf-a78d-2e9aec3e14bf","resolution":{"observed_at":"2026-05-24T08:46:06.137908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.01057","last_updated":"2023-06-03T00:47:06Z","snapshot_observed_at":"2026-07-06T12:56:07.820484Z","submitted_at":"2022-04-03T11:54:22Z","title":"A Survey on Machine Learning Solutions for Graph Pattern Extraction","version":3},"cited_work":{"arxiv_id":"2204.01057","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.01057","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning-based approaches for graph problems: a survey","venue":null,"work_id":"f87e1623-57b1-4c1a-bc77-0209020105ac","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"cited_paper":"/paper/2204.01057","citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:0fe470ebcdd67db1978bd4e9dcd04a179fa5b22d170f2f81268f2a0ab87a2559","observation_id":"cbf8e8ae-c954-4f5f-a65f-72d0577c2556","resolution":{"observed_at":"2026-05-24T08:46:05.586310Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.02767","last_updated":"2022-08-02T15:56:51Z","snapshot_observed_at":"2026-07-06T13:07:05.427227Z","submitted_at":"2022-05-05T16:44:36Z","title":"Spiking Graph Convolutional Networks","version":2},"cited_work":{"arxiv_id":"2205.02767","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.02767","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Spiking graph convolutional networks","venue":null,"work_id":"6571b87f-a532-4e32-a49c-4f31316a8f50","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"cited_paper":"/paper/2205.02767","citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:3b79d98360d613d544985e7324be8ed275469bb4d8db870077d41ef2774502bd","observation_id":"78a4fd89-bdb9-408c-a5c0-1714b9929ac7","resolution":{"observed_at":"2026-05-24T08:46:05.576777Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Fusing global domain information and local semantic information to classify financial documents","venue":null,"work_id":"b20a88c4-6201-4feb-909b-bc10657771a2","year":2020},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:820dcefde28259006b5eb878edb59e433dcf5f5f0f11ffa4091965007e25af85","observation_id":"86efec72-cc49-4dac-b08d-0a0a35a7cf4f","resolution":{"observed_at":"2026-05-24T08:46:06.133514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Approximate graph propagation","venue":null,"work_id":"768955eb-a679-4718-bec5-7b5967a2dd46","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:cc1297844941ab64535241f2feda96dd610b1bebf6af502ca1206a31c13cd377","observation_id":"c4c7159d-dde3-4395-8839-3b53a762bf14","resolution":{"observed_at":"2026-05-24T08:46:06.130934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Scalable graph neural networks via bidirectional propagation","venue":null,"work_id":"1f07769d-a850-4574-8b6e-c7c99f3b27f2","year":2020},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:bb1e4e17e4c4f989991c38412873964ca0e7e272c50503daa5e3ddf2d165e0c9","observation_id":"9008b097-b683-45a4-9d6a-da603c6d9faf","resolution":{"observed_at":"2026-05-24T08:46:06.127709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":"1710.10903","doi":"10.48550/arxiv.1710.10903","metadata_source":"pith","pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-07-11T01:47:47.523783Z","title":"Graph Attention Networks","venue":"stat.ML","work_id":"7dd5bb04-b448-4f32-9719-5fc799641fd9","year":2017},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:dc47127efa89d31149051081c5d103d61d6c25516e8891edf42ee49f9f50e9e7","observation_id":"fbf45bd4-6124-4a59-8fc3-e4200ca355d6","resolution":{"observed_at":"2026-05-24T08:46:05.581982Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Predict then propagate: Graph neural networks meet personal- ized pagerank","venue":null,"work_id":"ea9dcc2d-8614-40a1-adc1-fda10462d05e","year":2018},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:e15eeea1057eae4c5fe96bcd22a72995895bb2c5ed9570e81750849612f1c680","observation_id":"2bcc8963-5fe5-4f5e-8387-2a0758cd5405","resolution":{"observed_at":"2026-05-24T08:46:06.124805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","venue":null,"work_id":"915c139d-1732-4796-92fe-fa13800e692a","year":2020},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:2720d5389aa92b65d5d276baf8d70f789841a7daaee0a5d84cd857903f78c84f","observation_id":"0644eefa-eb65-47de-9b16-8afe27ae3d2f","resolution":{"observed_at":"2026-05-24T08:46:06.121375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","venue":null,"work_id":"a9dd700e-96ae-4b4c-9081-11732a20f1bd","year":2019},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:5beb9fccd652a3b3551fe124f65636d6851df5b43f457f64a096f00f6175d330","observation_id":"aa2bb647-699f-41b2-aa49-5ed486194bb1","resolution":{"observed_at":"2026-05-24T08:46:06.118488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Geom-gcn: Geometric graph convolutional networks","venue":null,"work_id":"76364c26-bf4d-4cc6-bd99-fdc7375d521c","year":2020},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:3f2c42a9162dbf131ef6a28ba0ba09f7b1c01d61f72111071932077348973a5f","observation_id":"3128da36-7694-4d41-8dab-7c4271fa8595","resolution":{"observed_at":"2026-05-24T08:46:06.004580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Graph pointer neural networks","venue":null,"work_id":"42cdf5c8-919d-4e75-90bd-a9a63eaf8973","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:dcc8f3d243306e1a059a15d3a63f689ab8133ce2a6544c3cd6d8d7ce031c3aea","observation_id":"6776ae60-a44e-4174-9c60-7fa42c6974b9","resolution":{"observed_at":"2026-05-24T08:46:06.115288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Non-local graph neural networks","venue":null,"work_id":"9273017a-7918-4ed4-8d6e-b17b24b9bc5a","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:2daf7629a15c33237e976d6a89d01078985cf5ecdc853d4104f005ff9b0d33a4","observation_id":"72dcd47b-6a69-43d1-9f8d-5589927e47cb","resolution":{"observed_at":"2026-05-24T08:46:06.112729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Universal graph convolutional networks","venue":null,"work_id":"e7911cdf-9b9d-464c-9dc7-fc40093ee3db","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:39f4ed970a1eed11d75ee94e058418df5e141b215db71083b2a610a8d23190c1","observation_id":"5be7506e-15e2-4b6b-9268-5e7bf8c33ae8","resolution":{"observed_at":"2026-05-24T08:46:06.109780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Finding global homophily in graph neural networks when meeting heterophily","venue":null,"work_id":"12275f98-8169-4b55-823e-598a0d027451","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:c7d0180818853b5fc250f94e3b80de27de7032772a2dc218f139b573a2de5fda","observation_id":"e2d1797c-0d94-4578-a664-0ef5e7595686","resolution":{"observed_at":"2026-05-24T08:46:06.144486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Large scale learning on non- homophilous graphs: New benchmarks and strong simple methods","venue":null,"work_id":"526ad8e0-e795-4da9-bf87-57472319a429","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:9d2c5831d33ba26ce6e1bdafd84880a1e10825ef1e8885dc099916e125f725d9","observation_id":"4f0c1710-624b-4a4a-8958-7e33a49dac76","resolution":{"observed_at":"2026-05-24T08:46:06.106333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Breaking the limit of graph neural networks by improving the assortativity of graphs with local mixing patterns","venue":null,"work_id":"a1dbddfa-16ff-48c9-8c90-893ab90fc3e1","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:49cfabb3a7566b4cab146461508b05f366d9e971ddbf0c1e25198b360346539a","observation_id":"040202a7-d89d-453e-964e-84d941651e86","resolution":{"observed_at":"2026-05-24T08:46:06.102797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Simrank: a measure of structural- context similarity","venue":null,"work_id":"cc563475-4424-4728-86a5-490d514ceb83","year":2002},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:3e33589531110a5e3fd2962ff73f9c8f1044aae8daba23a620a65e5127494a24","observation_id":"69ec7ecc-dbfc-4716-af08-766758e7df08","resolution":{"observed_at":"2026-05-24T08:46:06.097949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Cast: a correlation-based adaptive spectral clustering algorithm on multi-scale data","venue":null,"work_id":"531defee-8a00-45e1-bf31-dc95810fd3d4","year":2020},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:30677595d4ddc519a51159e2636d06eb7225f7f8f2cd0c4c3edab814c43a16e2","observation_id":"475776d3-b5a5-4c8b-9abc-512ef5f3ea7e","resolution":{"observed_at":"2026-05-24T08:46:06.094141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.06462","last_updated":"2022-11-28T16:08:41Z","snapshot_observed_at":"2026-07-06T10:40:47.631261Z","submitted_at":"2021-02-12T11:52:34Z","title":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","version":8},"cited_work":{"arxiv_id":"2102.06462","doi":"10.48550/arxiv.2102.06462","metadata_source":"arxiv_reference","pith_arxiv_id":"2102.06462","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks","venue":null,"work_id":"838c4711-d405-469b-bf3e-83e94a018af3","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"cited_paper":"/paper/2102.06462","citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:d707f1990d96d6fa6f6ea8510d6afabe4e34b636630c38f3185b8b71b02a3dbe","observation_id":"a765188a-2ced-40dd-bc56-2ed2fabae5d1","resolution":{"observed_at":"2026-05-24T08:46:05.596618Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Graph Neural Networks Beyond Compromise Between Attribute and Topology","venue":null,"work_id":"b2b8e15e-a667-4e7e-9ff5-949baee84198","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:698d11e8dbeb692ebc34c54e8382391fdb5b21e887f03899840f9ea12ef544f4","observation_id":"7b9f4f64-87f1-4eab-83da-eb9a7b41fdaf","resolution":{"observed_at":"2026-05-24T08:46:06.091436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Exact single-source simrank computation on large graphs","venue":null,"work_id":"2aa7b713-0490-45b6-9fcd-bed97df52a46","year":2020},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:28bc85368eeb2406772d4f9b0b4114dc975143d261148d8efae34dd26bd03f1f","observation_id":"4ed27430-c32f-4a82-a4da-9e14de4f0baa","resolution":{"observed_at":"2026-05-24T08:46:06.088144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Representation learning on graphs with jumping knowledge networks","venue":null,"work_id":"6f4dae38-0e94-403b-9191-5f7631955288","year":2018},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:83b3eebf9dc4883a2c5105e2c2aa081a30f1185b9d65667d783fd30e2896b326","observation_id":"28d8605b-bd21-4ffa-960e-e31a7201b5b9","resolution":{"observed_at":"2026-05-24T08:46:06.085037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Efficient top-k simrank-based simi- larity join","venue":null,"work_id":"4743fac1-ca02-4d31-aac2-b17d66f5e989","year":2014},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:64f56156d9ded016114a5797bebc100e619a8f158156a994bd0c46e28e5e84df","observation_id":"d3887145-a93c-4213-8161-b3c818f1c765","resolution":{"observed_at":"2026-05-24T08:46:06.081762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Efficient simrank track- ing in dynamic graphs","venue":null,"work_id":"13036cca-483c-42b3-a0be-5b69ed2ac0e3","year":2018},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:ed9ac1e7f5682a854e162cf5d2e76e7697318f70acf03fa825244c38154abb98","observation_id":"c4a96a89-b119-4e33-b8d6-4e348fecbf5d","resolution":{"observed_at":"2026-05-24T08:46:06.078695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.06144","last_updated":"2023-04-30T11:29:34Z","snapshot_observed_at":"2026-07-06T13:41:11.010175Z","submitted_at":"2022-08-12T07:26:05Z","title":"GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs","version":2},"cited_work":{"arxiv_id":"2208.06144","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.06144","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gsim: A graph neural network based rele- vance measure for heterogeneous graphs","venue":null,"work_id":"628f7d63-37e6-43f2-b1fe-72b2d6240a52","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"cited_paper":"/paper/2208.06144","citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:841e40a0cd2333a64d25a330c092e6abf54885baf25019a4b0ee2510075bbb63","observation_id":"8af38ed1-6694-4c7e-bb3d-22dd54eeaf49","resolution":{"observed_at":"2026-05-24T08:46:05.590987Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.04015","last_updated":"2023-04-08T14:02:31Z","snapshot_observed_at":"2026-07-06T15:13:36.835356Z","submitted_at":"2023-04-08T14:02:31Z","title":"Massively Parallel Single-Source SimRanks in $o(\\log n)$ Rounds","version":1},"cited_work":{"arxiv_id":"2304.04015","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2304.04015","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Massively parallel single- source simranks in o(logn) rounds","venue":null,"work_id":"34a29a09-0bd9-4dbf-b010-dfebe7b99ce7","year":2023},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"cited_paper":"/paper/2304.04015","citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:8cc6862e4f52a1ccf52757fb0d0897cd7797b5450db5a007a6abb06d8eb2e74a","observation_id":"921a143c-2717-41ef-a74e-d9ae1ec0963a","resolution":{"observed_at":"2026-05-24T08:46:05.571391Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks","venue":null,"work_id":"ebd644ab-73a9-4142-891c-adf74615ae7e","year":2019},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:1d3bc8ea67501f436ded0023f9d3a20aafe2200a9996771c0fe78e2d3ddde5ac","observation_id":"f80d1b10-79a4-4d86-9fa1-1dfbc359bd5a","resolution":{"observed_at":"2026-05-24T08:46:06.075826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Adaptive universal generalized pagerank graph neural network","venue":null,"work_id":"11894436-c380-4cde-bf5c-7a526a53a4f6","year":null},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:d3cbae7cc28f5b64391176db42f21c94e06ee1c155b2700dee07fd4a49c9c727","observation_id":"3e402296-9402-457b-b8a1-ad96ab16d335","resolution":{"observed_at":"2026-05-24T08:46:06.072870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Available: https://openreview.net/forum? id=n6jl7fLxrP","venue":null,"work_id":"3c6cce2f-6cae-46d7-a08d-dcc0677ba0d3","year":null},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:e212c4d6e9009ebf93cd2fee034e7d72a6f7f02c029b33ed796aa7833ec376d9","observation_id":"51362c75-9eaf-403f-a012-c19340bab537","resolution":{"observed_at":"2026-05-24T08:46:06.069786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Dif- fusion Improves Graph Learning","venue":null,"work_id":"6e02ab81-e14c-4087-acf3-b7219bf0931f","year":2019},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:6678a67f642f3f6127c14170c6a0b3f7f014e0609cfd08ede6398dbe0b73e84c","observation_id":"f9bd65e2-2686-4e08-8b89-748e3e4e2fd8","resolution":{"observed_at":"2026-05-24T08:46:06.066694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Scaling graph neural networks with approximate pagerank","venue":null,"work_id":"86859725-9765-4ed2-b990-7023df6eb86d","year":2020},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:0cfb04d67da2ac4fd6d6168609b804142f41ee8af45aa8ce797642afa672b72f","observation_id":"831a43c9-33af-4e1a-aaaf-9197277141e8","resolution":{"observed_at":"2026-05-24T08:46:06.063484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Do transformers really perform badly for graph representation?","venue":null,"work_id":"d83628b0-c736-41c7-b798-d354113a2866","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:ff1e376f6f3b571fdcad6ad81d6cacc24176a39d49e88bcd0425d24e2332bc33","observation_id":"1ac9aa6a-1b71-4dce-8671-5972c76b8c2a","resolution":{"observed_at":"2026-05-24T08:46:06.060808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Simple and deep graph convolutional networks","venue":null,"work_id":"072f8cf2-24b8-4f4c-95cc-708c56f3deb0","year":2020},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:5b163876b9465664190557e1994611f4748f1ab4394f58ef5f9e81223758c125","observation_id":"15ac2f20-e8aa-4c80-bb90-7336a45445ce","resolution":{"observed_at":"2026-05-24T08:46:06.008735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Simplifying graph convolutional networks","venue":null,"work_id":"8fb5d138-351d-4f6e-af3f-fc0eab26a01c","year":2019},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:2b71d7c8d4202a055825b355f54a2284d8fba784fbdd2f2f5f20dfddd32f99e2","observation_id":"0079e326-297d-4861-8181-beb665851298","resolution":{"observed_at":"2026-05-24T08:46:06.058099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Gbk-gnn: Gated bi-kernel graph neural networks for mod- eling both homophily and heterophily","venue":null,"work_id":"af70e88e-ba04-47f9-8e33-5d957b938326","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:cc404a8001c37ddaee72e8c72bacb7dc46d0eb1dad5c178b792707841f86aa6a","observation_id":"95f4396f-19e4-4575-a6b5-89e57ca80963","resolution":{"observed_at":"2026-05-24T08:46:06.054943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Powerful graph convolutional networks with adaptive propagation mechanism for homophily and heterophily","venue":null,"work_id":"d77b18d7-37cc-4dc5-b3e5-00ad2556aec4","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:ad4ab06d3b29d952cb8b036b09afbf3c0a1589193266af7e49468e59a9dce6ab","observation_id":"0e6d40b5-84b4-4939-a2bb-872753350891","resolution":{"observed_at":"2026-05-24T08:46:06.051936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Similarity-navigated graph neural networks for node classification","venue":null,"work_id":"4c892daf-6ac5-4e38-aabd-e69c314f483c","year":2023},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:3d4d7c0cd67260a08b00fd7c8f59cdcf7369fc36c0b4024ca29570e80d712591","observation_id":"07b40a9e-472c-4943-be85-e72e0b6802ae","resolution":{"observed_at":"2026-05-24T08:46:06.048263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Predicting global label relationship matrix for graph neural networks under heterophily","venue":null,"work_id":"12611a01-f691-4ade-b9fa-56163fdb0d2e","year":2023},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:311264872d03c07c8b26e40a782181073e69e6dfe43d59a4ee71de16256aba4c","observation_id":"3551c6fb-ddae-4a09-bbc8-73a4fbbbd65a","resolution":{"observed_at":"2026-05-24T08:46:06.045283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Scara: Scalable graph neural networks with feature-oriented optimization","venue":null,"work_id":"2de23310-e9db-4ba2-84b7-41be10f4cbe9","year":2022},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:f12e4fb89b94c968afc44626b28eaebf1046954f7954e8c4ae8e4a876d2bc52e","observation_id":"b8653f1b-3434-4aa3-9d12-c6a40dc58e75","resolution":{"observed_at":"2026-05-24T08:46:06.041299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"LD2: Scalable heterophilous graph neural network with decoupled em- bedding","venue":null,"work_id":"885a6176-32d3-4541-bdc5-3aa45f68ee8e","year":2023},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:1ac2b18980271999cf29c4268b7b6a1bc39a1df57b5e474b6fb83f133d561947","observation_id":"2c8ad3b2-1e6f-48c1-9582-54ee4d72d1a2","resolution":{"observed_at":"2026-05-24T08:46:06.011654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s00778-023-00829-6","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scalable decoupling graph neural networks with feature-oriented optimization","venue":null,"work_id":"486ed16f-30d9-49bc-b2b6-605583ab55f3","year":2024},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:cbe8933e58ae92b1343d8ca5d4e953739af7a3eec6c58d7f8299823b0380513b","observation_id":"429987cd-1873-4a6c-a849-a20b54fcf960","resolution":{"observed_at":"2026-05-24T08:46:05.497459Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Bird: Efficient approximation of bidirectional hidden personalized pagerank","venue":null,"work_id":"d1ce539c-bc5e-4d01-bb4f-228275ed2997","year":2024},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:816c9dfee671348240f46f06f169fa35154570f791f2d80b02ef4685e4b0b470","observation_id":"6fa18203-3be0-4da1-81f6-03fe8b1d3fe0","resolution":{"observed_at":"2026-05-24T08:46:06.038704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Agenda: Robust personalized pager- anks in evolving graphs","venue":null,"work_id":"50110cb1-cfe3-4758-bb8e-2bfc70974d11","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:63571b8f532b3cd1fc80546f381156a0960916b2a5028a576066da071021b1ab","observation_id":"ada2281c-3f08-4885-aabd-9ceb9bd2993e","resolution":{"observed_at":"2026-05-24T08:46:06.035304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Topology- monitorable contrastive learning on dynamic graphs","venue":null,"work_id":"ed9d0e65-76c8-4005-8059-818dacb920de","year":2024},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:ff513083ce6d487a2164fb2139c4280f58d3c17cff628f43eb425860f1646234","observation_id":"41b971c1-7db5-4263-8677-23ed5d779736","resolution":{"observed_at":"2026-05-24T08:46:06.032515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05641","last_updated":"2021-09-12T23:57:05Z","snapshot_observed_at":"2026-07-06T11:46:50.543914Z","submitted_at":"2021-09-12T23:57:05Z","title":"Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?","version":1},"cited_work":{"arxiv_id":"2109.05641","doi":"10.48550/arxiv.2109.05641","metadata_source":"arxiv_reference","pith_arxiv_id":"2109.05641","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Is heterophily a real nightmare for graph neural networks to do node classification?arXiv preprint arXiv:2109.05641","venue":null,"work_id":"d51f8592-bfc6-4d6a-9722-3453ff767385","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"cited_paper":"/paper/2109.05641","citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:1241ce7417db26522ec15d6a94735181d09b18ef2fc11ba43e26cc4aa342eb42","observation_id":"4f4ab57c-a739-4046-adfb-216a0cb03f98","resolution":{"observed_at":"2026-05-24T08:46:05.567538Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Multi- scale attributed node embedding","venue":null,"work_id":"8d08c76d-a742-4e65-bc88-0f6c30520db9","year":2021},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:209915a13d1cb4dd00baacaff216fb9d625a37f95aa419b1b9ad0621bd1c4559","observation_id":"7a874d70-85ee-451a-b6ef-bf69c31b4b68","resolution":{"observed_at":"2026-05-24T08:46:06.029362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking","venue":null,"work_id":"91a97845-4325-4502-bb83-98b934afebfe","year":2018},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:5040d40221c5b5ba2540d1c1f476ce5955c15f6df37bae2a700b48907c69f9d6","observation_id":"ba6c690d-0c18-41ed-b93b-3edfac5061cb","resolution":{"observed_at":"2026-05-24T08:46:06.026899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Collective classification in network data","venue":null,"work_id":"3aae71be-038a-4d4b-9ee9-6693ff693acf","year":2008},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:8b31b86397b375611f5448a2d20a6d0ff0cb0c629582d0d148b3e6057e00eaea","observation_id":"8f4acaec-2be3-46ae-b1c6-6e349633205d","resolution":{"observed_at":"2026-05-24T08:46:06.015242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Query-driven active surveying for collective classification","venue":null,"work_id":"d293879a-ccb8-49d7-be05-d03d8abc7f90","year":2012},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:774823a633acd30ce811a66dd415fa53d3c9b5fe71d0dde5b040b7c4fd28ae59","observation_id":"93ec8bb5-286d-4105-ac5e-8040fd118755","resolution":{"observed_at":"2026-05-24T08:46:06.023808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"On the use of arxiv as a dataset","venue":null,"work_id":"e5ca5789-7db3-431a-8f42-c8351ba3bb84","year":2019},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:275190f09384423836e517dcadad469d88d6213aeb7b3d197accf47f8c03e9f1","observation_id":"cdc21e7b-37a0-4b87-854b-959960e806e7","resolution":{"observed_at":"2026-05-24T08:46:06.020790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+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":"2026-06-05T21:23:00.469572Z","title":"Snap datasets: Stanford large network dataset collection","venue":null,"work_id":"9b2c6129-694d-449a-ada5-1c6e23c05f80","year":2014},"citing_paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation","version":5},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-24T08:44:23.340180Z"},"links":{"citing_paper":"/paper/2305.09958"},"observation_digest":"sha256:eda9cf0c07aefb3c5bec0162f48182830b6f61963cd2e3d61711312c2179f203","observation_id":"ef58ca05-3e5f-4794-8b2f-0af59f92c2f2","resolution":{"observed_at":"2026-05-24T08:46:06.017864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2305.09958","last_updated":"2026-04-12T14:15:20Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T15:28:28.566025Z","submitted_at":"2023-05-17T05:35:49Z","title":"SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation"},"reference_resolution":{"displayed":53,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":8,"verified_fuzzy":45},"total_outbound_references":53},"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":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"thesis":"As of 22 July 2026, this Paper Citation Record lists 53 of 53 outbound references and 1 inbound Pith citation observation for arXiv:2305.09958."}