{"as_of":"2026-08-07T15:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7de00c8acacfcda87c2a3c368269c72dbe976b4755099899e7f9bf202856dc8e","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:12:04.703179Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2506.19282/citation-record","integrity":"/paper/2506.19282/integrity","json":"/paper/2506.19282/citation-record.json","paper":"/paper/2506.19282"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:09.922104Z","title":null,"venue":null,"work_id":"8599fcf2-4f18-47e6-8a1a-d47599f061cc","year":null},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:01.769421Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:56795952a19a2e0665054412bd089adc36872ec28fb9101545979173cefb3a59","observation_id":"b58bf228-8dfd-4cd4-82d6-0dea39229bc3","resolution":{"observed_at":"2026-08-06T23:12:09.984318Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:09.742482Z","title":"Arghal, E","venue":null,"work_id":"2c45ffbe-d6b5-4f3b-ba3d-be27261123fa","year":2022},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:01.903983Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:fa1fdd0b5b2b6863a477dbc90dd8e36a0c2785c46ac2b1047e36f9aade133f4e","observation_id":"0bf46ab9-4c40-45f0-af31-eda8c2e20c90","resolution":{"observed_at":"2026-08-06T23:12:09.828953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:09.649454Z","title":null,"venue":null,"work_id":"3feb1783-a540-41fe-a989-1d5f6371591b","year":2021},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:01.944533Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:6b86a00d40ee4b7dce281ea0bd7b0c0bec16bfe6b8f011080eb13e818db0aab1","observation_id":"368e8f84-bdcd-4a54-99f6-5d652a7f1283","resolution":{"observed_at":"2026-08-06T23:12:09.703321Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:09.501571Z","title":null,"venue":null,"work_id":"cb1edd2b-8714-4173-b1f6-47ae200abb45","year":2019},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.029043Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:85c92e00fe264afc441f787db9e8883b83924b63db6e297fb125d01f0e841b8c","observation_id":"143bcd90-730b-492a-a36a-0cb688db44f9","resolution":{"observed_at":"2026-08-06T23:12:09.550493Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.00476","last_updated":"2024-05-01T12:23:16Z","snapshot_observed_at":"2026-07-06T18:08:09.361079Z","submitted_at":"2024-05-01T12:23:16Z","title":"A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00476","snapshot_observed_at":"2026-08-06T23:12:02.087994Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.087994Z"},"links":{"cited_paper":"/paper/2405.00476","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:6c4c7454f2ce50f478198a133988c517bb99c595ffea8cab9dbb7e8e15aaadfe","observation_id":"8a2bc3e0-0e9e-4134-bfa9-f57a404f68da","resolution":{"observed_at":"2026-08-06T23:12:02.087994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.01356","last_updated":"2025-07-02T11:28:06Z","snapshot_observed_at":"2026-07-06T16:42:16.200015Z","submitted_at":"2023-11-02T16:03:26Z","title":"Upper and lower bounds for the Lipschitz constant of random neural networks","version":4},"cited_work":{"arxiv_id":"2311.01356","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.01356","snapshot_observed_at":"2026-08-06T23:12:05.263304Z","title":"Upper and lower bounds for the Lipschitz constant of random neural networks","venue":"stat.ML","work_id":"e7d14b97-df72-4399-96a7-ca51f4c8a71a","year":2023},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.172706Z"},"links":{"cited_paper":"/paper/2311.01356","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:fa5b444dc468a465a261e9e367cd1c8043221e3883806df436d176fa1f38571c","observation_id":"df0748c1-b7d5-424b-b2ff-2d8e8dab72eb","resolution":{"observed_at":"2026-08-06T23:12:05.296721Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:09.348747Z","title":null,"venue":null,"work_id":"1cb92b76-7a43-4719-9c1b-5b77ea75843f","year":2018},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.232688Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:71c3224f8e1bd0850ca888b23eb2cb32212250dc2ddb0d8617028f492f414a80","observation_id":"007c6f6b-1bd3-491f-942d-9827ee460045","resolution":{"observed_at":"2026-08-06T23:12:09.385683Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:09.219702Z","title":null,"venue":null,"work_id":"48a5b1ae-0a67-4539-a402-8d9c0a1a8225","year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.268126Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:f992a2165e6f747ad352af0309128c269b8c7dd64f50f249d6a675aef024fe75","observation_id":"22ed8b43-4317-42da-b4fb-8439d6ae6562","resolution":{"observed_at":"2026-08-06T23:12:09.271850Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:02.331293Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.331293Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:28b086993d7cbcb6d520ce05f8ccbe71a8c2ef0e6021db766d3ff21b7cacc27e","observation_id":"d7b47829-7e56-4606-aa91-3b107f4273cc","resolution":{"observed_at":"2026-08-06T23:12:02.331293Z","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":"2026-08-06T23:12:02.373511Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.373511Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:68a42e4827f53ebc86e36bc0c1272f117fe582f9ef641d2c251cec27e8930b3a","observation_id":"53beb072-f074-4d7e-a588-c1ce1704eeab","resolution":{"observed_at":"2026-08-06T23:12:02.373511Z","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":"2026-08-06T23:12:09.061233Z","title":"Hamilton, Rex Ying, and Jure Leskovec","venue":null,"work_id":"e1cd40bc-8deb-4a46-84a2-d955109c4702","year":2017},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.420518Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:88e570ec6e5b4cc05fb89136d1eef0bd7cdafa69b6a113585b23e5118b2f0510","observation_id":"b10df4ec-0910-4ec8-9747-89a4496c795a","resolution":{"observed_at":"2026-08-06T23:12:09.118895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:02.462283Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.462283Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:e59cdaae4f5111549c0e6547fd0941d527e180d8948a8769cba8c63879efb425","observation_id":"ce1288f4-fab0-4783-b97f-68e92f98f70e","resolution":{"observed_at":"2026-08-06T23:12:02.462283Z","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":"2026-08-06T23:12:08.752702Z","title":null,"venue":null,"work_id":"44683e8a-66f3-4428-ad73-64dc0af05ff6","year":2024},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.574236Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:42e5c6525fceb7ab78b12497acb3986aacb820e0deabda1a13e3f4e1d25d7816","observation_id":"a3e3c47e-0567-4564-8142-5d6269c55ea6","resolution":{"observed_at":"2026-08-06T23:12:08.827303Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:08.611881Z","title":null,"venue":null,"work_id":"6d019f93-33f6-4ce6-a897-6919c1d796f3","year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.652209Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:5181a54682ed2c10e4e321e8714cbeb98b1a9f8c476bcd9efa68205ff2008f85","observation_id":"fabcea6f-0cd3-45bd-ae61-b91aaa5009b0","resolution":{"observed_at":"2026-08-06T23:12:08.686181Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","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":"2026-08-06T23:12:02.731887Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.731887Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:ccf9cfe7953208858d42e076fd5ec39b60cdddc838431e756dbc0bed6957ea9c","observation_id":"1d932dcc-daa1-4fca-b007-3542984ab0a6","resolution":{"observed_at":"2026-08-06T23:12:02.731887Z","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":"2026-08-06T23:12:08.487243Z","title":null,"venue":null,"work_id":"89b1d451-45c9-4a52-9b3c-0fa4b7dffddb","year":2019},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.769254Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:bef9445c59ef45f3b433cf7883ea785f821cdd71417d7c8ba5011b8d34e57ba0","observation_id":"d7d513dc-4dad-4bb0-9a4a-84f045e97628","resolution":{"observed_at":"2026-08-06T23:12:08.570195Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:08.368674Z","title":null,"venue":null,"work_id":"a4d09565-387e-4cf5-81bb-eed69688fda3","year":2024},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.840213Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:ae8787c9474cf6b2cdb8e0c53f59fa6473b6d564bcfea30f510d6d8460d0bda4","observation_id":"91fa7373-fb5f-4004-ada1-3b47808ddc66","resolution":{"observed_at":"2026-08-06T23:12:08.429771Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:02.894199Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.894199Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:3842773d5a5f004bf2a4b047d20f6a742b2f6cee174298fe567d17db1f385e9a","observation_id":"d8e6747f-16d4-4869-94ce-846b73c135cb","resolution":{"observed_at":"2026-08-06T23:12:02.894199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.03273","last_updated":"2021-12-06T08:19:15Z","snapshot_observed_at":"2026-08-02T07:26:06.037222Z","submitted_at":"2021-12-06T08:19:15Z","title":"Dynamic Graph Learning-Neural Network for Multivariate Time Series Modeling","version":1},"cited_work":{"arxiv_id":"2112.03273","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.03273","snapshot_observed_at":"2026-08-06T23:12:05.079785Z","title":"Dynamic Graph Learning-Neural Network for Multivariate Time Series Modeling","venue":"cs.LG","work_id":"3f978da6-277b-4923-b5d5-8156c7e68444","year":2021},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.954516Z"},"links":{"cited_paper":"/paper/2112.03273","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:e230350268e327af15c94eccfce2192f72f7f90bd7ce2f08999f6ad2cc411134","observation_id":"4cac62a6-e8da-40aa-b094-356cb71359ca","resolution":{"observed_at":"2026-08-06T23:12:05.170054Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:08.260696Z","title":null,"venue":null,"work_id":"7c30b8b2-7c8b-4c93-bf56-f82963346519","year":2017},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.019024Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:54d1369c2424c9057d53edb4e73ae53c1ace862aab4ee2d17b1b454822b7e633","observation_id":"90689471-5068-457b-98fb-5c63f3ebe8ba","resolution":{"observed_at":"2026-08-06T23:12:08.280180Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:03.066531Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.066531Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:39c62eebea892138811f388fe24b53fb3b97653963a6da43ece9ad5a95deecdf","observation_id":"5f3fafe1-291f-428b-8dda-bfa31875abda","resolution":{"observed_at":"2026-08-06T23:12:03.066531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05287","last_updated":"2020-02-14T01:47:35Z","snapshot_observed_at":"2026-08-03T10:05:45.128565Z","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":"2026-08-06T23:12:03.113234Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.113234Z"},"links":{"cited_paper":"/paper/2002.05287","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:560ca880b761e2bc9f0cbe421a45d36898e08825420e0cac02226d1ca8442718","observation_id":"08156981-c23e-4cab-9799-f5e1eece2a40","resolution":{"observed_at":"2026-08-06T23:12:03.113234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09338","last_updated":"2023-11-12T07:13:58Z","snapshot_observed_at":"2026-07-06T15:43:07.989730Z","submitted_at":"2023-06-15T17:59:27Z","title":"Understanding Optimization of Deep Learning via Jacobian Matrix and Lipschitz Constant","version":3},"cited_work":{"arxiv_id":"2306.09338","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.09338","snapshot_observed_at":"2026-08-06T23:12:04.888513Z","title":"Understanding Optimization of Deep Learning via Jacobian Matrix and Lipschitz Constant","venue":"cs.LG","work_id":"4ef25e7b-951c-4efa-90ba-cab3fadd4147","year":2023},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.201720Z"},"links":{"cited_paper":"/paper/2306.09338","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:b91c537a1669b6472b2e3f80e1edb008fa52d31656fdaf697c01de00dd5e5936","observation_id":"4f476f45-a5df-4ac4-8e56-e41bd833b06a","resolution":{"observed_at":"2026-08-06T23:12:04.988291Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-06T23:12:03.253416Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.253416Z"},"links":{"cited_paper":"/paper/2006.10637","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:98c9df4c1e59f09bffc503454007e36808c5b546be4664a0e7ffb706678ed271","observation_id":"ccfb032e-6b78-4206-ae7f-0970bb9b1ebe","resolution":{"observed_at":"2026-08-06T23:12:03.253416Z","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":"2026-08-06T23:12:08.099973Z","title":null,"venue":null,"work_id":"f42e56f2-67b9-4dc4-ba59-d0f5d25ca93a","year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.317954Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:6e238bc2ba2ffd7e6063b8c4c08997cc1a64517edae7a76be7637ecb024c52e5","observation_id":"6419544e-9410-427e-a956-1b37cee4e728","resolution":{"observed_at":"2026-08-06T23:12:08.158063Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:07.940649Z","title":null,"venue":null,"work_id":"eaaa3ea4-8e26-42d5-8b83-e4049c53e670","year":2021},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.424586Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:308310e5822862574f2787b6946c941af120d41ecda526086ed3751146a11388","observation_id":"161b8baa-cb6f-4253-8677-8fbc8b0208df","resolution":{"observed_at":"2026-08-06T23:12:08.021418Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04284","last_updated":"2024-02-26T09:23:12Z","snapshot_observed_at":"2026-07-06T17:26:27.288834Z","submitted_at":"2024-02-06T01:34:56Z","title":"PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04284","snapshot_observed_at":"2026-08-06T23:12:03.489658Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.489658Z"},"links":{"cited_paper":"/paper/2402.04284","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:3914bd053d1390bb69be52581bbb07efea678fd2c2fbcf18e7abb2a6ca1b0380","observation_id":"591511be-d439-43b3-a75d-da6d750b8d88","resolution":{"observed_at":"2026-08-06T23:12:03.489658Z","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":"2026-08-06T23:12:07.863865Z","title":"Szegedy, W","venue":null,"work_id":"d4ca7193-4b65-49c0-8f5d-7457d0d31578","year":2014},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.585992Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:a8ce04214db9bfb4200967165fc9e3d7d66b39443502200a8f7b7e826031d7bc","observation_id":"40b30211-68bb-4dc1-88f3-431c4501c4d7","resolution":{"observed_at":"2026-08-06T23:12:07.910441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:07.617234Z","title":null,"venue":null,"work_id":"95a6ee36-a793-42a3-a368-3c84b6e7d074","year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.623600Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:9f4bff09a3611a6615d7980721e3e3b9e31892cb54f7bdca07f48083ebb7642a","observation_id":"4d284501-88ea-463c-8469-3a06ca97ee95","resolution":{"observed_at":"2026-08-06T23:12:07.710313Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-06T23:12:03.704804Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.704804Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:a38a9344ec8fcda343351e3d5a9ee7ab821f9cbfc1d4ef606bbd67af021dcef8","observation_id":"332b55c3-25a1-4657-8b93-a40aaa1ed182","resolution":{"observed_at":"2026-08-06T23:12:03.704804Z","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":"2026-08-06T23:12:07.402827Z","title":null,"venue":null,"work_id":"f1da0a4f-cbd7-410e-9e9c-f1b94f97a7a9","year":2024},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.782486Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:c7176966ced0a220f86889e2adcbbf6064e551eaeb57229d1210a8012b2d75cb","observation_id":"d85c2999-205d-4041-9999-d9a04ee30308","resolution":{"observed_at":"2026-08-06T23:12:07.518484Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:07.178074Z","title":null,"venue":null,"work_id":"b95fae2c-9a1e-4995-a091-e58e602d5530","year":2021},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.843793Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:d5de20e42de907a3dc57ae1ed2b2c59104a93861c50612b10d24e7689b2d4c03","observation_id":"1564a082-e6c6-4517-bebb-3575418e22aa","resolution":{"observed_at":"2026-08-06T23:12:07.292488Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:06.914903Z","title":null,"venue":null,"work_id":"32c624ff-f0a4-4839-8383-260754c5d5e1","year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.925662Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:a0a58943d9ed7d8bf0a4c0e506961a5af3d99098aeebbdbae519075270a1dc79","observation_id":"ae663a5d-650a-4eb4-bb80-9757dffb7890","resolution":{"observed_at":"2026-08-06T23:12:07.060441Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:03.976862Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:03.976862Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:01ebd08d063383106e5e079e45998a5f752f7351681fa26b439f040a8d51dfbb","observation_id":"58891532-5e85-4054-a810-85761be6eb2d","resolution":{"observed_at":"2026-08-06T23:12:03.976862Z","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":"2026-08-06T23:12:04.035417Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.035417Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:3526e41618abe8cf9c31193452d93c05ffdef17d56f8b9089818054dfc2e2bdf","observation_id":"5855fcc8-731b-4e88-b3c2-db2edbcc4c08","resolution":{"observed_at":"2026-08-06T23:12:04.035417Z","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":"2026-08-06T23:12:06.673085Z","title":null,"venue":null,"work_id":"6a486936-f59c-49f2-bdc6-8dcd9b162984","year":2023},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.151682Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:3ebb6763385ef41cb9ba98351ce643140609682dc3bf8803fb6dbd480827d6a9","observation_id":"1a13bc4d-3022-4932-9950-0b3f7ea4f1b1","resolution":{"observed_at":"2026-08-06T23:12:06.775343Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:06.397987Z","title":"Hamil- ton, and Jure Leskovec","venue":null,"work_id":"cc390744-35b0-4284-8251-6a7d9a069064","year":2018},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.233418Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:749db4873a594cf1907ebdaa862cb2eddd66de0575bc522f28bf62c6ea3f482a","observation_id":"e5784359-d934-4e7f-a347-3019b5d27aca","resolution":{"observed_at":"2026-08-06T23:12:06.524334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07962","last_updated":"2020-02-19T02:05:37Z","snapshot_observed_at":"2026-07-06T08:58:21.130247Z","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":"2026-08-06T23:12:04.111354Z","title":"arXiv preprint arXiv:2002.07962 (2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.111354Z"},"links":{"cited_paper":"/paper/2002.07962","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:870dca545280e3fb7d1fc1718daa2be9cdee1823aa606c73510b3d7149e839c5","observation_id":"0059f42a-9cdf-4a54-84e3-06e3aca0b649","resolution":{"observed_at":"2026-08-06T23:12:04.111354Z","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":"2026-08-06T23:12:05.932161Z","title":null,"venue":null,"work_id":"81bede43-90ed-4a1b-bb96-0b6523fa33e7","year":null},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.379516Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:94bfbb44c1f90c04c364837a277e28e3cae97ae631a1df209dfd8c940fd9f522","observation_id":"9e309b1e-4a22-4e10-a5b9-f2c14c376a8f","resolution":{"observed_at":"2026-08-06T23:12:06.016562Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.14883","last_updated":"2022-06-30T18:35:43Z","snapshot_observed_at":"2026-07-06T12:53:43.089970Z","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":"2026-08-06T23:12:04.524177Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.524177Z"},"links":{"cited_paper":"/paper/2203.14883","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:72bb7afce1707f09bfcb8af61fac5d17b19dcb155aa7f582a0ab0a4fccbc83b5","observation_id":"6823225b-f6b5-4cd2-b4ef-fe36ab1ea90f","resolution":{"observed_at":"2026-08-06T23:12:04.524177Z","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":"2026-08-06T23:12:06.163411Z","title":"Mueller, R","venue":null,"work_id":"3d79314b-0e2f-4024-acba-09f58b59fa83","year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.312617Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:3d9419a3f71025a280711dfdb368a2168cc2e58c14625286325db776cc3688b2","observation_id":"09687911-6a94-4a9c-a990-745bc56cdf5c","resolution":{"observed_at":"2026-08-06T23:12:06.268427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:05.678591Z","title":null,"venue":null,"work_id":"5017d995-8e83-405d-8fb4-c4299b8bb84b","year":2018},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.665466Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:99b0bf98289ad9ef260ee2af19566b04bc5e5dac0c0caffcc8c770f5a534fee5","observation_id":"311939f6-b004-4e8d-abf9-e3d25af0d122","resolution":{"observed_at":"2026-08-06T23:12:05.739361Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:05.830414Z","title":null,"venue":null,"work_id":"1803a4c0-8c79-41df-833e-fc8ef2cd5657","year":null},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.467841Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:69479248b91b5649e61750a6c6fd4c08ab3465293dc60998e2be397ad04ab29f","observation_id":"96719a7e-a689-44be-b5df-e8c4cdfdc030","resolution":{"observed_at":"2026-08-06T23:12:05.871938Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:04.607710Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.607710Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:aa373fad67aeab2b510728d6d14aa857438a4670d0b881995f23dc448e04a4aa","observation_id":"7d394e6e-15e5-47fa-825a-68771aa3099e","resolution":{"observed_at":"2026-08-06T23:12:04.607710Z","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":"2026-08-06T23:12:05.509483Z","title":null,"venue":null,"work_id":"3faaf2b2-893a-4dba-a21c-fc048250d3fd","year":2023},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:04.703179Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:e8e8a41057e6a824be345284e91221b21c4f1d979b6fddb19098953afcae6c5a","observation_id":"529f0795-0179-4031-97e5-050813803db2","resolution":{"observed_at":"2026-08-06T23:12:05.600728Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.08391","last_updated":"2020-11-07T17:15:56Z","snapshot_observed_at":"2026-07-06T09:29:12.454335Z","submitted_at":"2020-06-15T13:23:34Z","title":"On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory","version":2},"cited_work":{"arxiv_id":"2006.08391","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.08391","snapshot_observed_at":"2026-08-06T23:12:05.369389Z","title":"On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory","venue":"cs.LG","work_id":"0a8dd145-1fe9-46bd-8b48-17301d80d624","year":2020},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:01.858488Z"},"links":{"cited_paper":"/paper/2006.08391","citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:b105f59b39ef15cbbe9908994f66cf7ce9b5fbe0134b7b7ff20f195daa92a4d6","observation_id":"3f54cb03-1b82-4c11-9620-bf04c8d8f626","resolution":{"observed_at":"2026-08-06T23:12:05.452275Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T23:12:08.918194Z","title":"In Neural Information Processing Systems","venue":null,"work_id":"2f458118-2095-49bb-96ac-81b86e4051a4","year":null},"citing_paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:02.528938Z"},"links":{"citing_paper":"/paper/2506.19282"},"observation_digest":"sha256:1b906e68dec8c25daa346a22cc3e256c85ba17ba8c86fabaa35f16e99ce7870f","observation_id":"ce95b0dd-7fe4-4514-af8c-8bc45c22da4e","resolution":{"observed_at":"2026-08-06T23:12:08.982282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.19282","last_updated":"2025-06-24T03:31:43Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T02:46:32.003410Z","submitted_at":"2025-06-24T03:31:43Z","title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":36,"verified_exact":3,"verified_fuzzy":6},"total_outbound_references":47},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2506.19282."}