{"as_of":"2026-08-08T22:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:487536624d781a9746e5dfda0821f23aad8a7a10379e1a170c5931bce90ce580","coverage":[{"denominator":21,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":21,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T20:30:53.298773Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2602.23135/citation-record","integrity":"/paper/2602.23135/integrity","json":"/paper/2602.23135/citation-record.json","paper":"/paper/2602.23135"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T20:30:50.969900Z","title":"Dvgmae: Self- supervised dynamic variational graph masked autoen- coder.IEEE Transactions on Neural Networks and Learn- ing Systems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:50.969900Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:c52143697ae386ea751fc11bc8881ad2bdce248ec8743d592a0139fdfa37b350","observation_id":"74f2df86-8a32-4421-8931-2d3933f23794","resolution":{"observed_at":"2026-08-02T20:30:50.969900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-07-06T06:49:24.960992Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-02T20:30:51.477595Z","title":"Representation learning with contrastive predic- tive coding.arXiv preprint arXiv:1807.03748,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.477595Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:ef034df0d0cc73b3eaf6ff79a6770ddac5c5b0de06f7b24e199622db5e528273","observation_id":"bdaf186a-7216-426e-8746-75aff6b5c262","resolution":{"observed_at":"2026-08-02T20:30:51.477595Z","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":"2026-08-02T20:30:51.716541Z","title":"Towards better evaluation for dynamic link prediction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.716541Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:11decc86dba7efa9f4a9e360e04605ec6ae2af0c79577952fe1bb103f0ad166f","observation_id":"19069a9a-0cac-43ce-85d1-2efb8e41ac8d","resolution":{"observed_at":"2026-08-02T20:30:51.716541Z","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":"2026-08-02T20:30:51.923249Z","title":"Dysat: Deep neural rep- resentation learning on dynamic graphs via self-attention networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.923249Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:2c5d690b47c2d9bf480305dfe09aee0727f8c796f2579e9a6b7b4c5705a880d8","observation_id":"eef54c8b-3f0f-4fc6-ad0d-78ceba552211","resolution":{"observed_at":"2026-08-02T20:30:51.923249Z","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":"2026-08-02T20:30:52.052830Z","title":"Dyrep: Learn- ing representations over dynamic graphs","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.052830Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:cc064222c29fea87e6841e8df0198155cc07e1de9f301a5bd7aacbf6c68c8490","observation_id":"f10d943e-2e92-4f60-9927-db3d9ca6b452","resolution":{"observed_at":"2026-08-02T20:30:52.052830Z","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":"2026-08-02T20:30:52.109544Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.109544Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:1b12f8c229594d6987efc11ce85ac819bce5b7f36f36658dc6bfa69812aa9501","observation_id":"e3e9df9a-f966-405a-a1ee-2a765f5edeb9","resolution":{"observed_at":"2026-08-02T20:30:52.109544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07962","last_updated":"2020-02-19T02:05:37Z","snapshot_observed_at":"2026-08-07T16:55:19.222155Z","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":"2026-08-02T20:30:52.467145Z","title":"Inductive repre- sentation learning on temporal graphs.arXiv preprint arXiv:2002.07962,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.467145Z"},"links":{"cited_paper":"/paper/2002.07962","citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:b8284fa37d009602abf42f897524e55082ddaceee2060de36534434780dc1a20","observation_id":"df5e5110-af83-4328-89f9-05987bfbf15d","resolution":{"observed_at":"2026-08-02T20:30:52.467145Z","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":"2026-08-02T20:30:52.608482Z","title":"Cldg: Con- trastive learning on dynamic graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.608482Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:9780cb50e753f33eca38f9363a8ac13732b11da8a7463d66701a9972d21cdab2","observation_id":"caa9612d-261d-4d7e-9b3c-6f51652ac3a3","resolution":{"observed_at":"2026-08-02T20:30:52.608482Z","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":"2026-08-02T20:30:52.905209Z","title":"Dtgb: A comprehensive benchmark for dynamic text-attributed graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.905209Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:171470b223482e46806d3aba43e2cd05cd8cbc43a8efa4dd527f0ffb54e5a5c9","observation_id":"c2875186-f5f0-4441-9cca-c50b20eec58e","resolution":{"observed_at":"2026-08-02T20:30:52.905209Z","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":"2026-08-02T20:30:53.112532Z","title":"The underlying raw data originates from publicly available sources, cited below","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:53.112532Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:fad08978c31074bc4fb3283dce00eebaa28c355765678bf41161e1734f637129","observation_id":"2f0bd719-957b-490c-829a-9f058720ff18","resolution":{"observed_at":"2026-08-02T20:30:53.112532Z","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":"2026-08-02T20:30:53.298773Z","title":"GDELT4 is built from the Global Database of Events, Lan- guage, and Tone, recording international political events","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2002,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:53.298773Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:8a35e084ed7f0cd90e7d2479b0a45b8439f26b0d0503e5fb460aae977df1851f","observation_id":"3c436e87-f765-485e-9a82-8b0247445094","resolution":{"observed_at":"2026-08-02T20:30:53.298773Z","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":"2026-08-02T20:30:51.080683Z","title":"Tinybert: Distilling bert for natural language under- standing","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.080683Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:fed0cacb3d4183f8bab29595bdd691af9b13e29cdf2d02fa809b75b0fee73674","observation_id":"24e326bf-31ae-40c2-a7eb-723c7e8df012","resolution":{"observed_at":"2026-08-02T20:30:51.080683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.07944","last_updated":"2021-05-17T15:33:25Z","snapshot_observed_at":"2026-08-07T20:17:21.322116Z","submitted_at":"2021-05-17T15:33:25Z","title":"TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.07944","snapshot_observed_at":"2026-08-02T20:30:52.194265Z","title":"Tcl: Transformer-based dynamic graph modelling via contrastive learning.arXiv preprint arXiv:2105.07944,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.194265Z"},"links":{"cited_paper":"/paper/2105.07944","citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:4ff3722da8bf67ff5f30c90463928c851ca48a71f5f16730a1f105fd5cba8f03","observation_id":"9a673202-878b-408c-a3e4-7d1f552c4462","resolution":{"observed_at":"2026-08-02T20:30:52.194265Z","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":"2026-08-02T20:30:51.594943Z","title":"Schardl, and Charles E","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.594943Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:745811ff9911f5d2a8ce064b439676ff3f4cb5101547704adce9ae33a137993f","observation_id":"72386b53-f454-46d8-a8a2-cf4b161bbdf8","resolution":{"observed_at":"2026-08-02T20:30:51.594943Z","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":"2026-08-02T20:30:51.295034Z","title":"[Liuet al., 2025 ] Weixiong Liu, Junwei Cheng, Quanlong Guan, Zhongyu Pan, and Chaobo He","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.295034Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:fb5d2ebba32a33ae0cb7b4c8a884790badcc8bbe24dc7847a8aa379e0884d026","observation_id":"983b33fc-147f-4e9b-a733-7d5057f21841","resolution":{"observed_at":"2026-08-02T20:30:51.295034Z","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":"2026-08-02T20:30:51.163954Z","title":"Predicting dynamic embedding trajectory in temporal interaction networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.163954Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:b6fcfa12aac05675744def9ebf2a6de609b79165aaf146d62a2b0defec955cba","observation_id":"3b963974-1a71-42ba-9174-bd0bae0b365b","resolution":{"observed_at":"2026-08-02T20:30:51.163954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05974","last_updated":"2022-10-31T22:00:36Z","snapshot_observed_at":"2026-08-04T12:32:42.808936Z","submitted_at":"2021-01-15T05:47:26Z","title":"Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05974","snapshot_observed_at":"2026-08-02T20:30:52.308606Z","title":"Inductive representation learn- ing in temporal networks via causal anonymous walks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.308606Z"},"links":{"cited_paper":"/paper/2101.05974","citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:7b1ffab917b247c79759fd8231aaa9d6f32244987bf82391d879a06a4b83e66a","observation_id":"30861bbc-9f26-4d42-b1c9-29251b479073","resolution":{"observed_at":"2026-08-02T20:30:52.308606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10637","last_updated":"2020-10-09T11:39:32Z","snapshot_observed_at":"2026-08-07T10:11:23.671536Z","submitted_at":"2020-06-18T16:06:18Z","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10637","snapshot_observed_at":"2026-08-02T20:30:51.802324Z","title":"Chambers, Fabrizio Frasca, and et al","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.802324Z"},"links":{"cited_paper":"/paper/2006.10637","citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:ce2129e9202f4f6159c061f1eb2df2a5c95c2df3cedf5cbbbb053d8078fffa41","observation_id":"6e44826a-7b42-4086-8641-558258a18ecf","resolution":{"observed_at":"2026-08-02T20:30:51.802324Z","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":"2026-08-02T20:30:52.749524Z","title":"Towards better dynamic graph learning: New archi- tecture and unified library","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.749524Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:5fb0ed94068eb1c2c40e16ad2dfbe44c8bf539e955c14194552c963a6d3518de","observation_id":"8049befc-d7e1-4790-8563-c87563d7e5c3","resolution":{"observed_at":"2026-08-02T20:30:52.749524Z","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":"2026-08-02T20:30:52.957538Z","title":"Topology-monitorable contrastive learning on dynamic graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:52.957538Z"},"links":{"citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:3f380f573e088a4b238cfa7329e971ab2835e7ec5a520a2709aa34ced77c6748","observation_id":"279c62cd-b8bc-41bd-8ce9-127107083aed","resolution":{"observed_at":"2026-08-02T20:30:52.957538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-07-06T05:01:27.910364Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-08-02T20:30:51.017335Z","title":"Gaussian error linear units (gelus).arXiv preprint arXiv:1606.08415,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T20:30:51.017335Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/2602.23135"},"observation_digest":"sha256:c561d42fb913c080d24b08db77a96fce2ff0d47bea5045d5a7e87a7ca26af49d","observation_id":"8ed8787a-ce39-4088-b205-ba9b11cc053b","resolution":{"observed_at":"2026-08-02T20:30:51.017335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.23135","last_updated":"2026-06-27T09:53:28Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T03:38:30.966802Z","submitted_at":"2026-02-26T15:51:51Z","title":"DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs"},"reference_resolution":{"displayed":21,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":21},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2602.23135."}