{"as_of":"2026-08-19T13:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2cc53ee24a7810b04c96c759e52332baa0d957a9f95fb76adc856b8e56436db","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T10:38:15.980249Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T20:18:20.158523Z","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":"2026-05-15T17:31:22.298494Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16435","snapshot_observed_at":"2026-08-12T20:18:20.158523Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09852","last_updated":"2025-09-11T18:51:53Z","snapshot_observed_at":"2026-08-16T05:37:36.514723Z","submitted_at":"2024-11-15T00:20:36Z","title":"InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction","version":4},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T20:18:20.158523Z"},"links":{"cited_paper":"/paper/2412.16435","citing_paper":"/paper/2411.09852"},"observation_digest":"sha256:ed93de618926237f8f564130d2c22bc072e88b07e55d6d5fa46838075018baa2","observation_id":"700e97ed-69cd-4e04-a2fb-3a6533d191c9","resolution":{"observed_at":"2026-08-12T20:18:20.158523Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16435","snapshot_observed_at":"2026-08-07T23:49:14.760975Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08767","last_updated":"2025-05-26T01:07:58Z","snapshot_observed_at":"2026-08-15T17:39:43.063793Z","submitted_at":"2025-02-12T20:13:56Z","title":"SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-07T23:49:14.760975Z"},"links":{"cited_paper":"/paper/2412.16435","citing_paper":"/paper/2502.08767"},"observation_digest":"sha256:83806831d755ea9ced34364e6aa7cdcd4cd8fa6a2d5b48515693ba359c4a1329","observation_id":"772ae33a-63f9-4afb-bd24-6d3d0176b90b","resolution":{"observed_at":"2026-08-07T23:49:14.760975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16435","snapshot_observed_at":"2026-08-07T14:35:00.361040Z","title":"Thegcn: Temporal heterophilic graph convolutional network","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18442","last_updated":"2025-05-24T00:45:07Z","snapshot_observed_at":"2026-08-10T16:44:21.993218Z","submitted_at":"2025-05-24T00:45:07Z","title":"Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-07T14:35:00.361040Z"},"links":{"cited_paper":"/paper/2412.16435","citing_paper":"/paper/2505.18442"},"observation_digest":"sha256:bf52be014789cba28ad5e798bc2541c4b9ed5c7c8704501973022eb705976ef9","observation_id":"b832d4ac-f511-4c7e-babe-82d3ffe72cda","resolution":{"observed_at":"2026-08-07T14:35:00.361040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"cited_work":{"arxiv_id":"2412.16435","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.16435","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"4db74401-ff10-4b33-aedb-341723b93747","year":2024},"citing_paper":{"arxiv_id":"2604.20858","last_updated":"2026-03-01T23:20:48Z","snapshot_observed_at":"2026-08-11T21:18:46.381745Z","submitted_at":"2026-03-01T23:20:48Z","title":"Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation","version":1},"reference_index":135,"source":"pdf_text","source_observed_at":"2026-05-15T17:30:44.919870Z"},"links":{"cited_paper":"/paper/2412.16435","citing_paper":"/paper/2604.20858"},"observation_digest":"sha256:1c505d42f00898b2e4be07fa7b1d6178e2f6d82b43f30595786e03cfe6008b43","observation_id":"86e5c2eb-f2ab-4dca-975d-da965463acee","resolution":{"observed_at":"2026-05-15T17:31:22.301309Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.16435/citation-record","integrity":"/paper/2412.16435/integrity","json":"/paper/2412.16435/citation-record.json","paper":"/paper/2412.16435"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:38:16.401581Z","title":"Adaptive graph convolutional recurrent net- work for traffic forecasting.Advances in neural information processing systems, 33:17804–17815,","venue":null,"work_id":"6369e6af-0669-41b1-a9ca-949d79f0102e","year":2020},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.833301Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:b2cbdb91cfc546691a8ab936759806c43b90853ee812624bd7e46be5dbbe3b6f","observation_id":"8ed25026-02c3-4e99-a1d7-91ee9404acbb","resolution":{"observed_at":"2026-08-11T10:38:16.404824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.369195Z","title":"Do we really need complicated model architectures for temporal networks? In The Eleventh Inter- national Conference on Learning Representations,","venue":null,"work_id":"230cd492-f9cc-4145-87fa-570656a470ca","year":2022},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.854285Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:20ce296547846bf22c3e5fb9f6ef674d8ba51127602ab63b3731d24d38e7e39d","observation_id":"57e8a058-a1e2-4a4c-9903-09cc14e9c10b","resolution":{"observed_at":"2026-08-11T10:38:16.373004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.346965Z","title":"Gcn-se: Attention as explainability for node clas- sification in dynamic graphs","venue":null,"work_id":"0f310b59-15e7-428d-8941-c22cdd724af7","year":2021},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.863438Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:44181c40144f782b0d8494a97a570a651279553df707f59e077fb2ead13a8361","observation_id":"541aeee7-7806-49ba-8a58-39bdb968b5e7","resolution":{"observed_at":"2026-08-11T10:38:16.350869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.336017Z","title":"Artificial neural networks (the multilayer percep- tron)—a review of applications in the atmospheric sciences","venue":null,"work_id":"dd44c7b0-dbba-4ea2-af0a-f1c062b7a405","year":1998},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.868423Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:ca623cfc83f2a31cb5d8cd7bd1d0a22961eec71a03fbc11e19e0df01029bf92c","observation_id":"c21505ab-37d2-46a8-a877-9cf226bc375a","resolution":{"observed_at":"2026-08-11T10:38:16.340171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:15.883711Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.883711Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:da58aeb88562013ff729ddc98c3da28dc83ba0ab07e311b9f17cf2d6c53fe3c1","observation_id":"6067e162-eb02-4479-abc2-efc5b29d99ec","resolution":{"observed_at":"2026-08-11T10:38:15.883711Z","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":"2026-08-11T10:38:16.307886Z","title":"Predicting dynamic embedding trajectory in tem- poral interaction networks","venue":null,"work_id":"51d86260-a901-4bff-bfea-ee0cfc921782","year":2019},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.892088Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:15d27d7555ca74d899c47374bb6f6312b75cae5c7a7c167d407de59ca137ca5d","observation_id":"56c6aa91-4e8e-4158-8674-bf8c367fd9d7","resolution":{"observed_at":"2026-08-11T10:38:16.311655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.296469Z","title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods","venue":null,"work_id":"e6d0168e-eba4-466a-84bd-48fe265f2002","year":2021},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.898942Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:daac5acebd5fd9a08d567220428cdce1824f46a2d275ed729ec184d206628fd8","observation_id":"d5746161-a193-4ca1-b2ae-01b6d2d12644","resolution":{"observed_at":"2026-08-11T10:38:16.301314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05641","last_updated":"2021-09-12T23:57:05Z","snapshot_observed_at":"2026-08-16T17:57:10.705002Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05641","snapshot_observed_at":"2026-08-11T10:38:15.901891Z","title":"Is heterophily a real nightmare for graph neural networks to do node classification? arXiv preprint arXiv:2109.05641,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.901891Z"},"links":{"cited_paper":"/paper/2109.05641","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:cf2b029fc43f146820e7bbec54630a900ea916f92e83247cb0e6c6bcf3666492","observation_id":"0ba5e8c2-1935-417c-81c1-2d9c4e9d6493","resolution":{"observed_at":"2026-08-11T10:38:15.901891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07606","last_updated":"2022-10-14T08:00:26Z","snapshot_observed_at":"2026-08-18T02:00:54.142495Z","submitted_at":"2022-10-14T08:00:26Z","title":"Revisiting Heterophily For Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2210.07606","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.07606","snapshot_observed_at":"2026-08-11T10:38:16.083076Z","title":"Revisiting Heterophily For Graph Neural Networks","venue":"cs.LG","work_id":"577ae962-6e17-4e5a-9dde-7e916f464f48","year":2022},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.905230Z"},"links":{"cited_paper":"/paper/2210.07606","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:3b50861067fbb1998b1081555d22255c397de4be03af8e673411650db2d2704c","observation_id":"a0454a08-6282-4bcf-aecb-8cbd00b8df44","resolution":{"observed_at":"2026-08-11T10:38:16.088710Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.284553Z","title":"Distributed repre- sentations of words and phrases and their compositionality","venue":null,"work_id":"b7820304-fae1-4cc7-a020-afd7b3de0cc5","year":2013},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.909602Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:8e55820e785f148c4eec17601a3144ed576b7143f1f605e1131db522ff688726","observation_id":"9997d171-78c8-4662-8c9d-582fa17c24f4","resolution":{"observed_at":"2026-08-11T10:38:16.288670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:15.917574Z","title":"Geom-gcn: Ge- ometric graph convolutional networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.917574Z"},"links":{"cited_paper":"/paper/2002.05287","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:323dbe55868201aa607cee83a142291cc5954c231898297c68ee2bf01ff876aa","observation_id":"c586bc73-121a-43d0-8248-e5b143d68786","resolution":{"observed_at":"2026-08-11T10:38:15.917574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10637","last_updated":"2020-10-09T11:39:32Z","snapshot_observed_at":"2026-08-07T10:11:23.671536Z","submitted_at":"2020-06-18T16:06:18Z","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10637","snapshot_observed_at":"2026-08-11T10:38:15.921705Z","title":"Temporal graph networks for deep learning on dynamic graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.921705Z"},"links":{"cited_paper":"/paper/2006.10637","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:3b047fea2e5005aa4d4a6c9c6e87dc23f4fd4376ab27e6fb5256855536f1df06","observation_id":"e7135020-04c8-4f3d-a803-f7a7d15b335b","resolution":{"observed_at":"2026-08-11T10:38:15.921705Z","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":"2026-08-11T10:38:16.264163Z","title":"Dysat: Deep neural rep- resentation learning on dynamic graphs via self-attention networks","venue":null,"work_id":"960944d8-1806-46e2-b8ec-384f5387f793","year":2020},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.925786Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:ffb20e0a74a32ec214ff1c05a8482fa2c5ca39d7d62e0a4da5608d2f094689fe","observation_id":"cf1d0cf0-e3af-4fc1-973d-e0d2fb77e95f","resolution":{"observed_at":"2026-08-11T10:38:16.267473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.254921Z","title":"Dyrep: Learn- ing representations over dynamic graphs","venue":null,"work_id":"91f56741-708b-4401-806e-0701f13f2b5d","year":2019},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.929647Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:9fdb2b809583105b66f6bfe75d8e01b60d6148013ccb707b78f69a5c44ea333a","observation_id":"e4ecc7b9-2408-4ed1-bc00-61709b48e149","resolution":{"observed_at":"2026-08-11T10:38:16.257973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-08-13T22:35:40.714745Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-11T10:38:15.933282Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.933282Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:d24f76b49c7f1af5095b1c8242fcd023ef4e29b8a178262095738f407d578fe3","observation_id":"bb8ea34d-fd2a-4797-8a4d-2c6874813330","resolution":{"observed_at":"2026-08-11T10:38:15.933282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11172","last_updated":"2022-06-17T15:36:56Z","snapshot_observed_at":"2026-08-18T17:13:32.500084Z","submitted_at":"2022-05-23T10:22:12Z","title":"How Powerful are Spectral Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11172","snapshot_observed_at":"2026-08-11T10:38:15.937126Z","title":"How powerful are spectral graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.937126Z"},"links":{"cited_paper":"/paper/2205.11172","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:2452368a15852a8cd71ee0c6358a7bed7faa59c52d3085eedda09eb8f263c424","observation_id":"e16872ea-5f22-489e-9d0e-ff55d67e9e4f","resolution":{"observed_at":"2026-08-11T10:38:15.937126Z","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":"2026-08-11T10:38:16.245129Z","title":"Streaming graph neural networks via con- tinual learning","venue":null,"work_id":"3255096b-8aeb-49c3-af78-48282585676e","year":2020},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.941365Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:14e953cbae209a059499b8dc960aefe2874ec38885f79ab190da0a07461c897d","observation_id":"b7aaaf9a-192e-4589-a9ef-f2dd6fb1f4e1","resolution":{"observed_at":"2026-08-11T10:38:16.248838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.231650Z","title":"Apan: Asynchronous propagation attention network for real-time temporal graph embedding","venue":null,"work_id":"027eeb6c-1b28-4a6c-9b41-328a9c265f2d","year":2021},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.944807Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:bd2309142619cb2193766ea79741708109e4bc6419b63912ea2a077795577ac5","observation_id":"98840c26-447c-44c8-a168-76391c716106","resolution":{"observed_at":"2026-08-11T10:38:16.235647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.221270Z","title":"Rete: retrieval-enhanced temporal event forecasting on unified query product evolutionary graph","venue":null,"work_id":"0d258c1f-c193-4643-9403-25f9b0fe20e8","year":2022},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.948268Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:f07664aa04bf1a8b47cfa9e93f9237bb9cfab7ad4550ae596132e8a90e9de83b","observation_id":"cbae50af-41f2-4f90-b54d-838f0b76171f","resolution":{"observed_at":"2026-08-11T10:38:16.224992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.209963Z","title":"Sim- plifying graph convolutional networks","venue":null,"work_id":"e19fc5da-c7f4-4dc7-9346-e8c0754b3663","year":2019},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.951599Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:fb48cf18ce5fe83fe99e9804886231a029c4477f40a6976779273db43b5c5767","observation_id":"f03d4676-3662-4a88-b94b-158e523d10b6","resolution":{"observed_at":"2026-08-11T10:38:16.214356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07962","last_updated":"2020-02-19T02:05:37Z","snapshot_observed_at":"2026-08-18T19:24:58.405240Z","submitted_at":"2020-02-19T02:05:37Z","title":"Inductive Representation Learning on Temporal Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07962","snapshot_observed_at":"2026-08-11T10:38:15.955282Z","title":"Inductive repre- sentation learning on temporal graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.955282Z"},"links":{"cited_paper":"/paper/2002.07962","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:f4ee3a4e2a6533fdfb891b16a4aefd3cda9699eccda318f64792be4b9cea7077","observation_id":"9fa9aaa7-c417-4f63-943d-59f361ada49b","resolution":{"observed_at":"2026-08-11T10:38:15.955282Z","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":"2026-08-11T10:38:16.199150Z","title":"From trainable negative depth to edge heterophily in graphs","venue":null,"work_id":"7e06f5b5-31f7-46e3-96e5-3fdc5b2f71ab","year":2024},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.959091Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:3deb5a42221f7f0203f7b00ec862f43d1444c928d1ff39c30e07fe75b66bd25b","observation_id":"71b73050-da64-4c1d-b7f8-16c2e56095ef","resolution":{"observed_at":"2026-08-11T10:38:16.202917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.176317Z","title":"Link prediction based on graph neural networks","venue":null,"work_id":"73427e14-41e7-4201-afb2-657edb73a116","year":2018},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.966490Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:7519dccef4169fd7d0fa4f8b3eecb5a901547ad0c3c9a64d4b55344cf34fb264","observation_id":"7686de46-17ab-44a3-b236-c81cd7cca74b","resolution":{"observed_at":"2026-08-11T10:38:16.180254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07082","last_updated":"2026-04-18T08:18:16Z","snapshot_observed_at":"2026-08-02T07:00:41.767213Z","submitted_at":"2022-02-14T23:07:47Z","title":"Graph Neural Networks for Graphs with Heterophily: A Survey","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07082","snapshot_observed_at":"2026-08-11T10:38:15.970074Z","title":"Graph neural networks for graphs with heterophily: A survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.970074Z"},"links":{"cited_paper":"/paper/2202.07082","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:929c842d499b2ad0c7a460186a76a9fb49e1be0e180b4e51df7f71c68b64bf87","observation_id":"98733831-be3f-4f3d-b3c6-0231f94265db","resolution":{"observed_at":"2026-08-11T10:38:15.970074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.14883","last_updated":"2022-06-30T18:35:43Z","snapshot_observed_at":"2026-08-16T17:11:14.431080Z","submitted_at":"2022-03-28T16:41:18Z","title":"TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.14883","snapshot_observed_at":"2026-08-11T10:38:15.973270Z","title":"Tgl: A general framework for temporal gnn training on billion- scale graphs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.973270Z"},"links":{"cited_paper":"/paper/2203.14883","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:9e310d9ca4b6e1f1524ea9645f69ebddc461b8ffde07d9dccbc59f3f466691e1","observation_id":"5a21a132-2fc4-460a-97e9-3d848094332d","resolution":{"observed_at":"2026-08-11T10:38:15.973270Z","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":"2026-08-11T10:38:16.164936Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","venue":null,"work_id":"8fa055bc-aa61-4622-a896-55398671a92b","year":2020},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.977197Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:ac5eed35ad28794dab427c1a9e0f5c171b07a99c92824ed6f3c2ccfc9eb5c7f3","observation_id":"f59ed231-7831-4866-acad-ea70cf974d09","resolution":{"observed_at":"2026-08-11T10:38:16.168750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.154213Z","title":"Graph neural networks with heterophily","venue":null,"work_id":"6b268d1e-acf0-4b74-aca7-108b7bc29894","year":2021},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.980249Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:87d70ce3fdaf575a855542b581a98f7ce7dcd553efa9958cd51fbebde9c31a48","observation_id":"0e2c882b-72f7-4df6-9004-1ffd12bbfd79","resolution":{"observed_at":"2026-08-11T10:38:16.157896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.11273","last_updated":"2018-05-29T07:12:04Z","snapshot_observed_at":"2026-08-14T19:10:05.291699Z","submitted_at":"2018-05-29T07:12:04Z","title":"DynGEM: Deep Embedding Method for Dynamic Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.11273","snapshot_observed_at":"2026-08-11T10:38:15.872260Z","title":"Dyngem: Deep embedding method for dy- namic graphs","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.872260Z"},"links":{"cited_paper":"/paper/1805.11273","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:4de3a469d99ee2b81f153cc0cc896b7fa5a232f01e4c2ee74d377cb95dc8a944","observation_id":"6d3d8c43-d43f-49fa-ac6c-33d3a11bde0e","resolution":{"observed_at":"2026-08-11T10:38:15.872260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-11T10:38:15.848254Z","title":"Adaptive universal generalized pagerank graph neural network","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2001,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.848254Z"},"links":{"cited_paper":"/paper/2006.07988","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:53e3d63e0e041a3250884941394168ca880562d005cfbb5a9ebe5e0c62bfdd5b","observation_id":"e2818219-a217-4670-8c94-2ae8cf4a54d6","resolution":{"observed_at":"2026-08-11T10:38:15.848254Z","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":"2026-08-11T10:38:16.274401Z","title":"Continuous-time dynamic network embed- dings","venue":null,"work_id":"c015a698-e89c-40b2-aa8e-26606bcefc93","year":2018},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.913583Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:f8cb00414c2e1660e8357e4bf2cd8babb1ad6f600f722b2c177212902a942d8d","observation_id":"b0feacf2-ed2b-41ee-b708-cee051a63160","resolution":{"observed_at":"2026-08-11T10:38:16.278104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.05997","last_updated":"2022-04-05T11:39:26Z","snapshot_observed_at":"2026-08-18T15:06:05.060057Z","submitted_at":"2018-10-14T08:36:54Z","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.05997","snapshot_observed_at":"2026-08-11T10:38:15.887975Z","title":"Predict then propagate: Graph neural networks meet personalized pagerank","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.887975Z"},"links":{"cited_paper":"/paper/1810.05997","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:0eb4f484262eb02e6e1aecbb24c303c3698733c2f8e52d22be7a0ed3047ad79c","observation_id":"8a22d087-b40c-414f-ba08-718e31e183c0","resolution":{"observed_at":"2026-08-11T10:38:15.887975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:38:15.880193Z","title":"Bernnet: Learning arbitrary graph spectral filters via bernstein approximation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.880193Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:dd414ca77f864bb5c033d3a73e6f0a2a0fde8747991e63cb119fe4cd5d53b415","observation_id":"bf32da00-7616-4a75-b97e-5fe7ce2243ee","resolution":{"observed_at":"2026-08-11T10:38:15.880193Z","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":"2026-08-11T10:38:16.324766Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":"2f77aafd-a9e1-47b0-8d66-5b2e1674aedb","year":2017},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.876377Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:6ec92cbca162bd559fa5b4c5bff2d7899e7fc055258b1b79472ff70e6a287bbf","observation_id":"c5ec8fba-78f5-4b6f-b0b8-5538b26b2863","resolution":{"observed_at":"2026-08-11T10:38:16.328955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.07308","last_updated":"2022-05-15T15:24:26Z","snapshot_observed_at":"2026-08-16T17:00:13.267390Z","submitted_at":"2022-05-15T15:24:26Z","title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.07308","snapshot_observed_at":"2026-08-11T10:38:15.895432Z","title":"Find- ing global homophily in graph neural networks when meet- ing heterophily","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.895432Z"},"links":{"cited_paper":"/paper/2205.07308","citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:f50e6490e5e570dbeac001186c2eda4c4545cfc3f77ea73e57a08e52faa6b8ad","observation_id":"86194bda-4c6d-4507-8e56-a7c84522f27f","resolution":{"observed_at":"2026-08-11T10:38:15.895432Z","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":"2026-08-11T10:38:16.391484Z","title":"Beyond low-frequency information in graph convolutional networks","venue":null,"work_id":"128303f7-7028-42d9-9708-16cb8e930673","year":2021},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.838241Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:cd44604408f7b41c62bd36db136b63ed16dd6569bf253ef16b4ba455641625ad","observation_id":"459b4e9d-0f17-4279-aa5f-b1410a955f67","resolution":{"observed_at":"2026-08-11T10:38:16.394939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.379833Z","title":"Freeway perfor- mance measurement system: mining loop detector data","venue":null,"work_id":"1dd85149-c72c-44f2-adfc-892effd5150a","year":2001},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.843609Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:fcb0eb1ea3a375533f439c4517faf23a40f44c66f3b8e8a2d45630188d66f027","observation_id":"91fdd3e3-2e4a-4b41-9e14-8a84ccc4148e","resolution":{"observed_at":"2026-08-11T10:38:16.384142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.358441Z","title":"Gbk-gnn: Gated bi-kernel graph neural networks for modeling both homophily and heterophily","venue":null,"work_id":"bc444a70-d855-4ac8-82f0-efe50e7bc369","year":2022},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.859060Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:6fd62e873ad71cc6f6e0657de3b87b4e19f2592e5547441f28d9b809de1af11c","observation_id":"020c52af-65ee-4dbe-bb85-0869a7ea3fad","resolution":{"observed_at":"2026-08-11T10:38:16.362349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T10:38:16.188056Z","title":"Roland: graph learning framework for dynamic graphs","venue":null,"work_id":"a328c86c-36a2-443a-8ba2-d91e9bbf0c64","year":2022},"citing_paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-11T10:38:15.962715Z"},"links":{"citing_paper":"/paper/2412.16435"},"observation_digest":"sha256:18c10b70eabd9b99e62962b9d453d0139a1cfb1210caf0d1163fb50d3a27cd45","observation_id":"128a7a2a-7a51-4420-ab9d-5b4c2b6248ab","resolution":{"observed_at":"2026-08-11T10:38:16.191854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.16435","last_updated":"2025-01-10T19:49:12Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T19:33:37.526915Z","submitted_at":"2024-12-21T01:52:03Z","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":1,"verified_fuzzy":23},"total_outbound_references":38},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 4 inbound Pith citation observations for arXiv:2412.16435."}