{"as_of":"2026-08-14T23:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8fe158ec445221fbc225f26345830791904c061278d6456f351262bc20d44e15","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T12:40:37.409071Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.02302/citation-record","integrity":"/paper/2502.02302/integrity","json":"/paper/2502.02302/citation-record.json","paper":"/paper/2502.02302"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:40:38.130435Z","title":"Learning graph representations with global structural information,","venue":null,"work_id":"f719636b-d625-45e1-b338-5f132a5d652c","year":2015},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.186213Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:5a3e981f284a16e004283586fdea8d73bd58a6f68e9252494e6ed9e7b3ba5126","observation_id":"e1cd5eef-71aa-4af2-b294-ff5f65b514ba","resolution":{"observed_at":"2026-08-09T12:40:38.134910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:38.115798Z","title":"Tabularnet: A neural network architecture for understanding semantic structures of tabular data,","venue":null,"work_id":"3ce965d4-80c0-4d9a-9e32-b3dacba867f5","year":2021},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.192146Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:94732b645252a776355705ac9b806646ce03ae4ba56dbb41c55b42008bd5bba4","observation_id":"ace485ff-aa6a-44c6-a184-35f0ccf076b2","resolution":{"observed_at":"2026-08-09T12:40:38.120412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:38.101682Z","title":"Structured subspace embedding on attributed networks,","venue":null,"work_id":"6d06182c-99b8-4089-83ec-4a0efca89561","year":2020},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.197321Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:1dd2fd3d5cd7b130fcb839c9dbee7e82c35980a98407017514709d32863a4812","observation_id":"e874d235-864d-4abb-a066-b3598410fe0f","resolution":{"observed_at":"2026-08-09T12:40:38.106318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:38.087483Z","title":"Structural deep network embedding,","venue":null,"work_id":"6d5f1094-9760-4694-b699-8ebc9f5cdd6b","year":2016},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.202520Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:05adeba112abd779b6eae945c3730baebb2befc248b9eff3c806b08102992d49","observation_id":"a5b8eea7-53dd-4442-b64b-784630e2d3fe","resolution":{"observed_at":"2026-08-09T12:40:38.092059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:38.072589Z","title":"Deep neural networks for learning graph representations,","venue":null,"work_id":"31cea270-54fa-4055-bcad-124c22fc1a96","year":2016},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.208330Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:59230f16cd37a710d758547d29586b6742ae1134832216c6d639469674688169","observation_id":"8306809b-2d38-46d3-bad1-b956f41c79fc","resolution":{"observed_at":"2026-08-09T12:40:38.077243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:38.056248Z","title":"Content to node: Self- translation network embedding,","venue":null,"work_id":"a8eb67e1-1720-4edc-aec4-98c3728c362c","year":2019},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.214114Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:da50a4d35eb9d341d60ee9ce13f92daaae9dd4dd40c0eb71038110487f227e6a","observation_id":"8df0dc5d-ccb3-4505-8ff9-da786ed980bf","resolution":{"observed_at":"2026-08-09T12:40:38.061375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.219516Z","title":"Graph attention networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.219516Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:478ad2d867fb63f5392303bf87782f85d7041109fa1972ef52e9d50aad9fb21c","observation_id":"fb709cc1-6181-4fc7-94d1-62c673cafdda","resolution":{"observed_at":"2026-08-09T12:40:37.219516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.00019","last_updated":"2015-10-17T05:06:11Z","snapshot_observed_at":"2026-08-14T22:46:30.846767Z","submitted_at":"2015-05-29T20:16:51Z","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.00019","snapshot_observed_at":"2026-08-09T12:40:37.224914Z","title":"A critical review of recurrent neural networks for sequence learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.224914Z"},"links":{"cited_paper":"/paper/1506.00019","citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:b4316cce1ee4e8cb8be675335cb067d3eb8ae34cd4f90c3911bdd72aa3fca696","observation_id":"c601eaa9-b447-4595-9b01-f625fd30acd5","resolution":{"observed_at":"2026-08-09T12:40:37.224914Z","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":"2026-08-09T12:40:38.039919Z","title":"Heterogeneous graph neural networks,","venue":null,"work_id":"546ceb48-37df-4f82-801a-eb5a7cc63b2e","year":2022},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.230109Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:5796850baf1963b72b152eaa3ad22dab24a0cdb10b61c934063e63bf6cafe833","observation_id":"773490f5-528d-4c64-b16f-c305a8b5a62a","resolution":{"observed_at":"2026-08-09T12:40:38.044739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:38.025572Z","title":"Heterogeneous graph attention network,","venue":null,"work_id":"2f70b0e2-7794-4071-adb3-6b25569c35d7","year":2019},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.234724Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:f7ccb10f9811a53ff52b5eb739911562be9271d00ef922da8be737af42603ae8","observation_id":"cb67eddb-12c4-41f5-a9be-bb9f73816199","resolution":{"observed_at":"2026-08-09T12:40:38.030137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:38.011183Z","title":"Explicit message-passing heterogeneous graph neural network,","venue":null,"work_id":"1298fde3-1e06-409c-b9f4-ac24b384e7eb","year":2022},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.239389Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:4fc180ec465c11fc5dec7176f8e63b6a81a0717cde1f36dc972d5efa5274c101","observation_id":"9485c01a-04a7-41ba-b3c2-00d15718eefd","resolution":{"observed_at":"2026-08-09T12:40:38.015921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.996087Z","title":"Diffmg: Differentiable meta graph search for heterogeneous graph neural networks,","venue":null,"work_id":"e5a3febf-a126-4446-b7bb-0a786a11929d","year":2021},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.244106Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:0ee534a2f69b8c988253f97a82523331d0ff2cacb11270836988d224b21157f9","observation_id":"82303fec-2eff-4ad2-8a6e-cf01976e3a15","resolution":{"observed_at":"2026-08-09T12:40:38.000670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-13T11:38:10.906031Z","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":"2026-08-09T12:40:37.248683Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.248683Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:95b96045814398794baa62c0532e98e5d0e68c0b977d21fbb42e5a221c3dd806","observation_id":"ac0bdb54-b275-4b0c-a9c3-de3230217c55","resolution":{"observed_at":"2026-08-09T12:40:37.248683Z","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":"2026-08-09T12:40:37.981376Z","title":"Multiplex heterogeneous graph convolutional network,","venue":null,"work_id":"06fec554-8a4b-4773-b89e-89bcf73e5e90","year":2022},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.253878Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:761d1548866cc267f799980eb17e0d17a851226329017b2eb234b41b3b0c0f9d","observation_id":"6f04d8e2-a238-4550-81e6-fc16fd6c96f6","resolution":{"observed_at":"2026-08-09T12:40:37.986024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1402.3722","last_updated":"2014-02-15T21:03:02Z","snapshot_observed_at":"2026-08-14T23:44:32.401718Z","submitted_at":"2014-02-15T21:03:02Z","title":"word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1402.3722","snapshot_observed_at":"2026-08-09T12:40:37.258411Z","title":"word2vec explained: deriving mikolov et al.’s negative-sampling word-embedding method,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.258411Z"},"links":{"cited_paper":"/paper/1402.3722","citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:dd16f82bce817b5e2d854b8db743b1448191e21000e809af791a730f371ebc42","observation_id":"78cc9fa5-ce79-44fe-a34b-a71d77701251","resolution":{"observed_at":"2026-08-09T12:40:37.258411Z","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":"2026-08-09T12:40:37.263311Z","title":"Nonlinear dimensionality reduction by locally linear embedding,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.263311Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:2bc43de717309a2caa7200ab77a7d9ad00c7ceeb286b88e32126a63b04b3bbc3","observation_id":"cad66429-dc5e-4e1a-b953-2258efb85ac6","resolution":{"observed_at":"2026-08-09T12:40:37.263311Z","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":"2026-08-09T12:40:37.268123Z","title":"A global geometric framework for nonlinear dimensionality reduction,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.268123Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:127f11633bd34f72ee45fdd7c5d1ace753f6df7e2d6faffacb91b13bb6c56a97","observation_id":"f52ececd-5a65-43c3-ba23-2539640993cd","resolution":{"observed_at":"2026-08-09T12:40:37.268123Z","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":"2026-08-09T12:40:37.947994Z","title":"Laplacian eigenmaps and spectral techniques for embedding and clustering,","venue":null,"work_id":"3a171ae5-af59-44d5-bb4d-0dd020d83e50","year":2001},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.272677Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:85cf0384e81d567fac8e2643587aa94d0da65405ba2575191040bf05f8735c03","observation_id":"05b80dd7-666d-4339-bec1-da78ad66787b","resolution":{"observed_at":"2026-08-09T12:40:37.952521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.933833Z","title":"Dis- tributed representations of words and phrases and their compositionality,","venue":null,"work_id":"159ab5d5-f0ba-4b0b-b85e-3e579fce3a6a","year":2013},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.277248Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:9c2b06405a0430713c8ef339732c2b282642bb640cb8f07b0688c52a3d4d0222","observation_id":"77619370-b93f-4f15-ae72-608627cc78aa","resolution":{"observed_at":"2026-08-09T12:40:37.938484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.920115Z","title":"Deepwalk: Online learning of social representations,","venue":null,"work_id":"c004c0ca-32dc-4048-9266-f70912188e20","year":2014},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.281923Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:3746a6fa3f6c10cf9a48039b9aedbcd288786cc971a24abb3673d1a333ed27a2","observation_id":"cabdb0d1-0cc7-4abe-a9f4-d5a036f2783d","resolution":{"observed_at":"2026-08-09T12:40:37.924608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.906019Z","title":"node2vec: Scalable feature learning for networks,","venue":null,"work_id":"16c6da26-6c09-4da7-b6eb-cc599531c59f","year":2016},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.286520Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:6ce9381589613d89538b2cb6e146bf2fba954394e4c4edca6a6df9157a78da3b","observation_id":"23271826-f3a2-47e4-bf6e-bfcab29c9271","resolution":{"observed_at":"2026-08-09T12:40:37.910530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.891942Z","title":"Community preserving network embedding,","venue":null,"work_id":"d1f6a9ca-6b7a-43af-89c5-bd66a7f34faa","year":2017},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.291015Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:21a9805b8847630b6c3340985daee2a14b82155107ea17c8f4b076e3871dfee3","observation_id":"7f689b13-4422-46f1-a4d6-c19681780d10","resolution":{"observed_at":"2026-08-09T12:40:37.896357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.877906Z","title":"Attributed network embedding with micro-meso structure,","venue":null,"work_id":"72fc75a4-02c9-43e8-9c67-f97011df5766","year":2021},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.295513Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:134adb392b6449da21b35e719d6f57b33451b304eb79db5ec041f1114e3448b2","observation_id":"1422a455-9082-41c4-9a4f-cd33dea30fbc","resolution":{"observed_at":"2026-08-09T12:40:37.882322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.863466Z","title":"Extracting semantic representations from word co-occurrence statistics: A computational study,","venue":null,"work_id":"967c6e1a-65c1-4c8e-a405-0b554f7cfb5c","year":2007},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.300057Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:647b5fb93a98a95e69d04c5589852f7a2520d6027229965ae702eab41f77dd80","observation_id":"a7d3093b-c6b6-4eef-8082-a6a8c69823f2","resolution":{"observed_at":"2026-08-09T12:40:37.868052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.849097Z","title":"Cane: Context-aware network embedding for relation modeling,","venue":null,"work_id":"3988ebb5-f428-42d3-bffb-554da38e05c8","year":2017},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.304557Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:3920e64a9ab1f9b51838154dd2734ff410fc8874f9b643de7cbfb256be88c779","observation_id":"10d7e1aa-f951-4eb9-a125-00c99e0995a5","resolution":{"observed_at":"2026-08-09T12:40:37.853630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.834312Z","title":"Content to node: Self-translation network embedding,","venue":null,"work_id":"99d6dce3-1c35-4265-b9c7-2849f90c9bc8","year":2018},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.308967Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:8f96346fa30ba5d8342ffb73dafab4e220f4ca95f4166ef80b58ec5d53c4b813","observation_id":"07509191-0281-4a18-b118-287b8b71e295","resolution":{"observed_at":"2026-08-09T12:40:37.839167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.819515Z","title":"Deep attributed network embedding,","venue":null,"work_id":"1755e879-12db-42e1-912c-423a363799f2","year":2018},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.313292Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:15b3f4d847809e3f900ebf4c9ce8675cac9993e2bedd6030e7761cd7bcda31e6","observation_id":"29033539-f5a1-49b2-85a1-d7fc69cc8f7b","resolution":{"observed_at":"2026-08-09T12:40:37.824718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.805262Z","title":"Self-paced network embedding,","venue":null,"work_id":"ee7f2ab6-6ed9-415e-837a-5fe9aeb894f6","year":2018},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.317774Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:027105960f5ab296b03b32269e01e7b32fafbdc88e2a77403d99e373a1904513","observation_id":"3e7bea3d-48fe-4fda-8e2a-ed421e7af0d8","resolution":{"observed_at":"2026-08-09T12:40:37.810021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.789747Z","title":"Deep network embedding for graph represen- tation learning in signed networks,","venue":null,"work_id":"e4dc8b96-1c3d-4186-a04a-b5de68a78a3f","year":2018},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.322493Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:159d123a73f30451002785c9b9a456d15c3737b741aa6c2bf992a8cc644ef1f3","observation_id":"a3f70c59-becf-4923-b666-f419774a4dc1","resolution":{"observed_at":"2026-08-09T12:40:37.794818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.774940Z","title":"Node pair information preserving network embedding based on adversarial networks,","venue":null,"work_id":"20b48675-6942-4134-986c-034b227713a7","year":2020},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.326938Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:4d3aeaa4ff821675b7ed3fe09d4127dc95a5ec7734e4282576297a9bd9599a5b","observation_id":"e50dbfe5-b3ae-41f5-a95a-a766a62b9ba3","resolution":{"observed_at":"2026-08-09T12:40:37.779657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06667","last_updated":"2019-06-10T08:35:03Z","snapshot_observed_at":"2026-08-14T17:17:03.025114Z","submitted_at":"2019-02-13T09:58:44Z","title":"Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06667","snapshot_observed_at":"2026-08-09T12:40:37.331570Z","title":"Hierarchical graph convolutional networks for semi-supervised node classification,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.331570Z"},"links":{"cited_paper":"/paper/1902.06667","citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:ba374b69084d3fe576124c12370f82657eb7c5fc665fd81d465fa115f57ee0ae","observation_id":"1679ae50-e655-41a2-92cf-40fabf23dc42","resolution":{"observed_at":"2026-08-09T12:40:37.331570Z","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":"2026-08-09T12:40:37.760402Z","title":"Relation-aware graph convolutional networks for agent-initiated social e-commerce recommendation,","venue":null,"work_id":"bcb072c6-b2d9-4b33-a678-cdd2a1ebdf7b","year":2019},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.336790Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:aa298b78909bffea792cc38ba6e42058989c376095d9d0a5046e55ace987a47d","observation_id":"4aa00e4a-c818-45cf-99cf-78078c00146c","resolution":{"observed_at":"2026-08-09T12:40:37.765094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.746199Z","title":"Dynamic hypergraph neural networks","venue":null,"work_id":"43248123-3412-4fc1-b72e-695c8773114b","year":2019},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.341449Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:f1819d1ef977eb70a4616c65094cf702aac1f6537f7f3f5295076fc16e47345b","observation_id":"ba3af17f-3f05-4872-9409-548f5f62feb6","resolution":{"observed_at":"2026-08-09T12:40:37.750657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.731862Z","title":"Inductive representation learning on large graphs,","venue":null,"work_id":"b3abcf46-c379-4ce6-8510-62893837c860","year":2017},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.345861Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:2b105430f91fa7ef86f9859586509dcf6e76ab09f035cd06372407571416a649","observation_id":"109590f5-fcf3-4d87-a69e-813a28a68d8d","resolution":{"observed_at":"2026-08-09T12:40:37.736281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.717345Z","title":"Learning graph embedding with adversarial training methods,","venue":null,"work_id":"8112ad0a-dc70-41bc-8953-a957faea6f59","year":2019},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.350427Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:e22b693e16c0008f0cdc920218dd6d53c2d0d934ebd4f7ef04b91a39506d122b","observation_id":"7700a03a-79e5-4b08-a2da-0ad247c2a5f8","resolution":{"observed_at":"2026-08-09T12:40:37.722157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.702351Z","title":"Censnet: Convolution with edge-node switching in graph neural networks","venue":null,"work_id":"6597dd69-3042-44b9-a8b9-a65a19d86beb","year":2019},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.354745Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:e4f4c442ca9ada8e71472e6d6c4255ba2c208257293152359a0c9a3b4a69f305","observation_id":"f9477aba-e681-4a1f-bb00-d00fec7b6496","resolution":{"observed_at":"2026-08-09T12:40:37.707273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.688206Z","title":"A vectorized relational graph convolutional network for multi-relational network alignment","venue":null,"work_id":"d474dbd8-7c4c-406c-88fd-386a50535b4f","year":2019},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.359282Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:4388888bbfaafc08c4182c72431969796bede72717d35e0847b974563ed7750f","observation_id":"6e587cbc-6080-41bb-949d-eacf86e3f5cc","resolution":{"observed_at":"2026-08-09T12:40:37.693082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.11747","last_updated":"2021-09-10T18:58:03Z","snapshot_observed_at":"2026-08-13T20:42:02.537812Z","submitted_at":"2020-12-21T23:30:04Z","title":"RealFormer: Transformer Likes Residual Attention","version":3},"cited_work":{"arxiv_id":"2012.11747","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.11747","snapshot_observed_at":"2026-08-09T12:40:37.445048Z","title":"RealFormer: Transformer Likes Residual Attention","venue":"cs.LG","work_id":"7d105c30-96e6-454e-a133-7b419b2e0f05","year":2020},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.363721Z"},"links":{"cited_paper":"/paper/2012.11747","citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:e69a2fb3adc132881a1f2165591eb135e24af40e6348caa9650103451b868b13","observation_id":"50d6db17-386d-4fb3-bc41-a61cda45b2ab","resolution":{"observed_at":"2026-08-09T12:40:37.452100Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.673793Z","title":"Freebase: a collaboratively created graph database for structuring human knowledge,","venue":null,"work_id":"9b87f448-601b-4464-ad9b-18c9877413a6","year":2008},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.368463Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:fc3aa4a05c75e4d85ae48e610c2223bdf3cd532bb9d109164da642d5d8ccecb6","observation_id":"21c6b700-220d-4451-ad04-197ce1ec2d31","resolution":{"observed_at":"2026-08-09T12:40:37.678461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.658859Z","title":"Heterogeneous network representation learning: A unified framework with survey and benchmark,","venue":null,"work_id":"4b834900-e817-471a-a0ed-b71e730210db","year":2020},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.373229Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:dde0aeffa0a47721ae4e5668499bff3d3242cd40cbd5c36473c991140a6d99ae","observation_id":"c01f377f-5ba8-4f40-87e5-ec688c59f897","resolution":{"observed_at":"2026-08-09T12:40:37.663359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.644511Z","title":"Graph transformer networks,","venue":null,"work_id":"7dc5b0b7-9be2-498f-a50c-29e78d71b593","year":2019},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.377696Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:e82772649b7f7572b83e673404cb95b23d08d2161fc4f3b86e8b6c4aa77e9245","observation_id":"2a776a54-c838-4516-870e-172eb0e0e521","resolution":{"observed_at":"2026-08-09T12:40:37.649219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.629933Z","title":"Heterogeneous graph transformer,","venue":null,"work_id":"5cb8724d-8c7b-4cf2-b1f0-9ae60739c1a7","year":2020},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.382213Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:6368fca86068b27bb7c3424961606e441dd4351f33876ce052b79a0c8cdfcadd","observation_id":"d8b9847e-a89f-4487-8e56-d7bf7af7d41f","resolution":{"observed_at":"2026-08-09T12:40:37.634544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.613887Z","title":"Modeling relational data with graph convolutional networks,","venue":null,"work_id":"ec5c4604-a99c-4d16-b79f-13e8f12576d5","year":2018},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.386512Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:6a7f5f024b37ab6fbbe6d1b1e107f407854f3c45fea1598761e8c851c2df1f6b","observation_id":"704f2c7f-7a8e-4712-93c6-77e78ff82ee7","resolution":{"observed_at":"2026-08-09T12:40:37.618895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.598261Z","title":"Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding,","venue":null,"work_id":"6e00bc1d-6988-4503-942b-a06275cf5a2f","year":2020},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.390776Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:1dfd82691adc92c368d93841f158e0f4f3b5ae2464afad1e7bed8f7894c1dd8f","observation_id":"fe1e8eef-5484-4b5a-b648-73ccbc1fe307","resolution":{"observed_at":"2026-08-09T12:40:37.602923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.583356Z","title":"Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks,","venue":null,"work_id":"a63a17eb-7685-4a0b-aa42-aa87d7d6d416","year":2021},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.395466Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:5242e11b3ad0879905b8ec886d5edcbbf53baf009e58a30083fcf7972dde858b","observation_id":"17f617e3-434a-4859-98c1-88a97f6b5e0a","resolution":{"observed_at":"2026-08-09T12:40:37.588310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.568414Z","title":"Simple and efficient heterogeneous graph neural network,","venue":null,"work_id":"e6c71054-120f-42de-bbbb-86d97bf9cd83","year":2023},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.400196Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:ab91a005d29c43fbfacb1828d2741ad866fa2a5a70c7592f9efd7b4fd141dcb7","observation_id":"939fb67d-69c3-4bda-b825-cb3cd4cd6c17","resolution":{"observed_at":"2026-08-09T12:40:37.573261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.553198Z","title":"Multi-hierarchical spatial- temporal graph convolutional networks for traffic flow forecasting,","venue":null,"work_id":"3ce76f90-85be-4f69-8f1b-9cb5161f0ba3","year":2022},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.404602Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:251e6d2806824f844c6cb7944cbf7704ba2a5412c11f95b31b44f4553261aa35","observation_id":"87290539-4637-4013-8257-0169aa5e3020","resolution":{"observed_at":"2026-08-09T12:40:37.557926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-09T12:40:37.536491Z","title":"Attributed social network embedding,","venue":null,"work_id":"abaa6c6e-0351-4796-a8b0-b9fe0a0ac194","year":2018},"citing_paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T12:40:37.409071Z"},"links":{"citing_paper":"/paper/2502.02302"},"observation_digest":"sha256:d227fd6bd6c57235c2756fe2064f569b953cdd41cf5ffb9b0e58fc2affadb0fb","observation_id":"e1081a5f-3702-4fee-8a21-fe33cd646bb8","resolution":{"observed_at":"2026-08-09T12:40:37.541259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.02302","last_updated":"2025-02-04T13:16:54Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T10:04:14.689240Z","submitted_at":"2025-02-04T13:16:54Z","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":1,"verified_fuzzy":40},"total_outbound_references":48},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2502.02302."}