{"as_of":"2026-08-10T09:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b31fecef693587755ed6f3d3b45153eb2bdc3b6eb92c5bb3ae58e06a533ae096","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:18:42.395182Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2505.19408/citation-record","integrity":"/paper/2505.19408/integrity","json":"/paper/2505.19408/citation-record.json","paper":"/paper/2505.19408"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.01179","last_updated":"2021-06-04T14:52:04Z","snapshot_observed_at":"2026-08-09T07:21:16.437218Z","submitted_at":"2020-10-02T19:53:05Z","title":"The Surprising Power of Graph Neural Networks with Random Node Initialization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01179","snapshot_observed_at":"2026-08-07T14:18:36.259417Z","title":"The sur- prising power of graph neural networks with random node initialization.arXiv preprint arXiv:2010.01179, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:36.259417Z"},"links":{"cited_paper":"/paper/2010.01179","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:453c4d0ae5a78c4180f610da19289b1db3a14725e776821395cc97280833169a","observation_id":"61feebdb-84ea-42d3-bfd8-c862258f6ccc","resolution":{"observed_at":"2026-08-07T14:18:36.259417Z","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":"2026-08-07T14:18:50.455580Z","title":"Temporal graph neural networks for social recommendation","venue":null,"work_id":"d6f47792-6bfb-4b9f-875d-159ab5cee3fc","year":2020},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:36.437050Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:f93e93729dc846484b80dec3c327f84f2a488ba90db2b6d1e159a8855a698f6a","observation_id":"d64856af-77b1-4940-b849-2f6692b3fbf0","resolution":{"observed_at":"2026-08-07T14:18:50.621574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13660","last_updated":"2025-02-19T12:12:57Z","snapshot_observed_at":"2026-08-07T18:05:30.152233Z","submitted_at":"2025-02-19T12:12:57Z","title":"Towards Invariance to Node Identifiers in Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13660","snapshot_observed_at":"2026-08-07T14:18:36.573294Z","title":"Towards invariance to node identifiers in graph neural networks.arXiv preprint arXiv:2502.13660, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:36.573294Z"},"links":{"cited_paper":"/paper/2502.13660","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:918590f158abd78bc97dcba3a142f3e97a8e229e919a14dbf1ee4e411855d564","observation_id":"39082cb2-7242-457c-aef7-9d805df23ec5","resolution":{"observed_at":"2026-08-07T14:18:36.573294Z","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":"2026-08-07T14:18:50.128983Z","title":"Hot: Higher-order dynamic graph representation learning with efficient transformers","venue":null,"work_id":"f5c7ba27-75bf-44f6-a9ca-efe8f13a2d4f","year":2024},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:36.745736Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:40e097e6f4669e6c7dfd0958f47eae5e078ff75725035e801309559c73a95432","observation_id":"8ed18f6f-7543-472e-8ff2-e82ef7382a3a","resolution":{"observed_at":"2026-08-07T14:18:50.294355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.1078","last_updated":"2014-09-03T00:25:02Z","snapshot_observed_at":"2026-07-06T03:45:28.546418Z","submitted_at":"2014-06-03T17:47:08Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.1078","snapshot_observed_at":"2026-08-07T14:18:36.931839Z","title":"Learning phrase representations using rnn encoder- decoder for statistical machine translation.arXiv preprint arXiv:1406.1078, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:36.931839Z"},"links":{"cited_paper":"/paper/1406.1078","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:4e71f50836773e98fca40b8e969195d45ac25fca852f491e04b80c7998f64860","observation_id":"3d58dad3-1044-4198-9c2b-2ea08799da09","resolution":{"observed_at":"2026-08-07T14:18:36.931839Z","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":"2026-08-07T14:18:49.821234Z","title":null,"venue":null,"work_id":"299acbe9-d946-43ac-a5de-bf96ca65e789","year":2023},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:37.051349Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:be313a3532f096a231ba1f70e0d84638aa897918b969cab07fb921774a4269e0","observation_id":"80450f18-c75e-4c76-aa0c-e26841beb98e","resolution":{"observed_at":"2026-08-07T14:18:49.948802Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:49.509977Z","title":"Applications of link prediction in social networks: A review.Journal of Network and Computer Applications, 166:102716, 2020","venue":null,"work_id":"5cfb3ac3-3345-4a85-922a-62f94b247ac2","year":2020},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:37.193075Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:566c1f10ae8b4c37dd32ff8e3009356e81ae1d5d33a37e9fc5a10a11f17c03a3","observation_id":"a52fb145-39e5-475d-bc41-0defc0978605","resolution":{"observed_at":"2026-08-07T14:18:49.687514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:49.249660Z","title":"Temporal link prediction: A survey.New Generation Computing, 38(1):213–258, 2020","venue":null,"work_id":"66d86d8d-b7a7-4e50-9a00-eba39bf12045","year":2020},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:37.334476Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:63983f8e26380bcf485514981cc72b1f54162ce8b6a9b59093b1cf16afebef9a","observation_id":"cbeb7328-bb2b-4398-a420-3650bea232ae","resolution":{"observed_at":"2026-08-07T14:18:49.356605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:48.915352Z","title":"Machine learning on dynamic graphs: a survey on applications.2023 IEEE Ninth Multimedia Big Data (BigMM), pages 32–39, 2023","venue":null,"work_id":"e915f6e9-be1e-4652-a4f3-bc5a75922e84","year":2023},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:37.455618Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:afba3cf7a5b57f23646378807dd76a4edbdca19bbfeae6ccfa7636c5edcb6113","observation_id":"6ea6176c-52ac-40ed-a107-c48e9ef31f3e","resolution":{"observed_at":"2026-08-07T14:18:49.059027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:48.611140Z","title":"A systemic analysis of link prediction in social network.Artificial Intelligence Review, 52:1961–1995, 2019","venue":null,"work_id":"8880ec98-f4c8-4f9d-9758-13393528ffc4","year":1961},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:37.617806Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:187e60ca4e2d01313d10e910989e5f9a03be3ec68ae59997549a99aaf36b403d","observation_id":"93f1d45d-f078-493a-ba28-e1adbe0abc1f","resolution":{"observed_at":"2026-08-07T14:18:48.738693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:48.353648Z","title":null,"venue":null,"work_id":"22eb2a04-3388-4c46-9e77-ab107fb47760","year":1971},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:37.739501Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:276360b7a3eed9f302c5775bfdac3c5a90ae638424451f28b36e25902e3d20f2","observation_id":"4ef4f8c5-47fb-4ed1-91ac-40459b0f773b","resolution":{"observed_at":"2026-08-07T14:18:48.485519Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:48.058274Z","title":"Tempo- ral graph benchmark for machine learning on temporal graphs.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"c7713a13-bb89-4a04-a950-4d0fdc340bcc","year":2024},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:37.896845Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:b378b012524e7ec3b1e92a061e3e746d08c21570fe8ca2c36b8fa1a31d7bc991","observation_id":"16856320-491e-415f-b26d-9adc55b0f361","resolution":{"observed_at":"2026-08-07T14:18:48.158231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:38.065114Z","title":"Self-attentive sequential recommendation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:38.065114Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:25bfbf229028f39a9ca137b66b1199ccbac4bb53d4010ba2c75969ba4f11686c","observation_id":"8a8c8993-b515-41ee-bd29-c64699a55b46","resolution":{"observed_at":"2026-08-07T14:18:38.065114Z","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":"2026-08-07T14:18:38.170311Z","title":"Representation learning for dynamic graphs: A survey.Journal of Machine Learning Research, 21(70):1–73, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:38.170311Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:367b0aadbbc176ee096712394fb8d42a08df4fe0d00e0680661d51334d3b7094","observation_id":"e1fdf86f-66b1-4cb0-aa15-28719e014b01","resolution":{"observed_at":"2026-08-07T14:18:38.170311Z","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":"2026-08-07T14:18:47.749158Z","title":"Learning temporal attention in dynamic graphs with bilinear interactions.Plos one, 16(3):e0247936, 2021","venue":null,"work_id":"03a643af-ae63-4340-8c7f-3fbaea4e80fb","year":2021},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:38.316908Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:b97ce41239738b8404cd896b3e4dd4189c1b21a077d26094493a41132258be9e","observation_id":"18f4b958-0f57-4370-b834-a0cbc0668e78","resolution":{"observed_at":"2026-08-07T14:18:47.879261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:38.447173Z","title":"Predicting dynamic embedding trajectory in temporal interaction networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:38.447173Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:79516f764f15f2482f58b53710dc25d98ba28f7f1a4ef812142361c4b2ab68c0","observation_id":"fb7521a0-37ed-46db-800f-b066f8ccc594","resolution":{"observed_at":"2026-08-07T14:18:38.447173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08520","last_updated":"2024-11-04T06:32:35Z","snapshot_observed_at":"2026-08-10T05:00:58.364757Z","submitted_at":"2023-12-13T21:15:29Z","title":"Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)","version":2},"cited_work":{"arxiv_id":"2312.08520","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.08520","snapshot_observed_at":"2026-08-07T14:18:43.171320Z","title":"Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)","venue":"cs.AI","work_id":"5f37e49d-9619-412c-b9b3-dac18980f0c5","year":2023},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:38.569906Z"},"links":{"cited_paper":"/paper/2312.08520","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:ef24e4f8c55d5fdd73f571a6f61949d1ef922f8baaf7dcd92d4ff4985af6d0bc","observation_id":"51ba5196-d008-4311-a6b1-a48c0fa2aa29","resolution":{"observed_at":"2026-08-07T14:18:43.252097Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.03199","last_updated":"2020-01-28T13:24:15Z","snapshot_observed_at":"2026-08-09T01:25:36.003122Z","submitted_at":"2019-07-06T22:26:17Z","title":"What graph neural networks cannot learn: depth vs width","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.03199","snapshot_observed_at":"2026-08-07T14:18:38.716308Z","title":"What graph neural networks cannot learn: depth vs width.arXiv preprint arXiv:1907.03199, 2019","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:38.716308Z"},"links":{"cited_paper":"/paper/1907.03199","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:f7b8a60062dc2c82b62021e77f274fde603af513f1de1fc018d7615082405cc1","observation_id":"3f7f895e-d2f0-4647-a086-30823c06b47f","resolution":{"observed_at":"2026-08-07T14:18:38.716308Z","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":"2026-08-07T14:18:47.491439Z","title":"Neighborhood-aware scalable temporal network representation learning","venue":null,"work_id":"2dbc5884-dc9b-4b5d-b5a8-8e55af522d9e","year":2022},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:38.861542Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:7b6808948afc20534368a4956c5c2854e307c51dd37eada9dae9779e5faa1858","observation_id":"3060d87d-07c1-47a0-bab8-a7d0f9b2f2c5","resolution":{"observed_at":"2026-08-07T14:18:47.624297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:47.211404Z","title":"The neural hawkes process: A neurally self-modulating multivariate point process.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":"09a0e5a5-c997-47a9-8183-bb8fdbed4a69","year":2017},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:38.983824Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:9a9adc0beeed13427929c17006d6c41dda064756534881e1c02aa8fdadcd27fa","observation_id":"54e2954f-c2c1-48a5-9175-d805a5fa9475","resolution":{"observed_at":"2026-08-07T14:18:47.349414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:46.883849Z","title":"de Rijke","venue":null,"work_id":"d73c7cae-ebeb-42ab-a43c-1efbac6bc585","year":2020},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:39.138254Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:1bc26805e55bbd9d4a0ec8df88dfd3e57d659bc6e0efec36dbee93550a7aa673","observation_id":"6362e3c1-9f25-4803-a5df-8fae95cc95eb","resolution":{"observed_at":"2026-08-07T14:18:47.060391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:46.618663Z","title":null,"venue":null,"work_id":"1d851932-1abe-4525-97ec-2f15e2862dea","year":2009},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:39.261524Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:c1e989b75a47e2b544c0d40cc2b045d1ef0dfc3eba5b53fe924d590b4482e0dd","observation_id":"3ef68453-b7ac-41b0-a534-0c6c07b093a4","resolution":{"observed_at":"2026-08-07T14:18:46.777450Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:46.328108Z","title":"Towards better evaluation for dynamic link prediction.Advances in Neural Information Processing Systems, 35:32928–32941, 2022","venue":null,"work_id":"4fd53d9e-872d-47c8-9759-d5a5344c06a5","year":2022},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:39.384406Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:a4c0c622edb3364c9ca4588c8ffda5901b9d5faeab473ef0cd3da2b87845b161","observation_id":"b7d30cfb-2885-4f17-875e-3853ae3c5cb0","resolution":{"observed_at":"2026-08-07T14:18:46.472907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:46.071574Z","title":"Temporal graph learning for financial world: Algorithms, scalability, explainability & fairness","venue":null,"work_id":"dd0e7611-f2c9-4751-b71b-8cd2f77cea27","year":2022},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:39.535700Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:753ca41806adbde21fae2ce3971389f3bb5c1de68e40787eab2d70cb771bb894","observation_id":"dc0842eb-d6ae-42e7-9c6b-130af9252398","resolution":{"observed_at":"2026-08-07T14:18:46.211790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1205.2618","last_updated":"2012-05-09T18:25:09Z","snapshot_observed_at":"2026-07-06T02:47:58.266745Z","submitted_at":"2012-05-09T18:25:09Z","title":"BPR: Bayesian Personalized Ranking from Implicit Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1205.2618","snapshot_observed_at":"2026-08-07T14:18:39.720960Z","title":"Bpr: Bayesian personalized ranking from implicit feedback.arXiv preprint arXiv:1205.2618, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:39.720960Z"},"links":{"cited_paper":"/paper/1205.2618","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:c1199289cc742a5f6859df2040a039434dc49b3a437e980cd27593770ed1955a","observation_id":"cd2a629b-0fcd-4970-af8a-a4caa873520a","resolution":{"observed_at":"2026-08-07T14:18:39.720960Z","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":"2026-08-07T14:18:45.815982Z","title":"Temporal graph networks for deep learning on dynamic graphs","venue":null,"work_id":"8284b427-dfff-4555-9346-e2249bdc623e","year":2020},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:39.862888Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:adace6fbfc21f63e5bfc1b75400d02497bec0699533c0bfe719cc90bce78507d","observation_id":"36ef97a9-3938-41ed-9d9a-105acba1a267","resolution":{"observed_at":"2026-08-07T14:18:45.922340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:40.007248Z","title":"Methods and metrics for cold-start recommendations","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:40.007248Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:bacaf390fbde54f02f24efec220a411580b6f9a34be625b17f83b40ef7c2556a","observation_id":"ba21ce28-fafd-4d7f-959b-a256eb4108b0","resolution":{"observed_at":"2026-08-07T14:18:40.007248Z","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":"2026-08-07T14:18:45.539763Z","title":"Foundations and modeling of dynamic networks using dynamic graph neural networks: A survey.iEEE Access, 9:79143–79168, 2021","venue":null,"work_id":"1c0fc1e7-f20c-4517-bc7e-c17895a03cdb","year":2021},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:40.159349Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:abbb9bfddab5c18f37d7f2e7bfde2960901708b47307f5a91e6a27dd1019fcab","observation_id":"1a3616ae-3d40-4a63-8cb9-9d1fedb57b16","resolution":{"observed_at":"2026-08-07T14:18:45.682629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:45.271415Z","title":"Co-author rela- tionship prediction in heterogeneous bibliographic networks","venue":null,"work_id":"7feadc62-d4ef-4c9d-b878-29a21319127b","year":2011},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:40.295194Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:09123029b36a5c450aa866949b96ceefecd84ea1a40310a3f63738c922490142","observation_id":"f19a5c2e-b25d-492b-8b0c-ae2e7cc1ae94","resolution":{"observed_at":"2026-08-07T14:18:45.419336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:40.461567Z","title":"Mlp-mixer: An all-mlp architecture for vision.Advances in neural information processing systems, 34: 24261–24272, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:40.461567Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:77993c9ca4f81f038c7b986d417862f5c438d6ce85a264ffa59f04d622e47f30","observation_id":"b64ac4bc-0124-4dc0-8b2d-817d55060ecd","resolution":{"observed_at":"2026-08-07T14:18:40.461567Z","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":"2026-08-07T14:18:44.952152Z","title":"Dyrep: Learn- ing representations over dynamic graphs","venue":null,"work_id":"70c237ac-bb7e-4979-acd5-e3f068f18826","year":2019},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:40.566477Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:28472db949e6e83459956b1617a59438191ff55932e5c6ec5e89c299dd632fe6","observation_id":"7d4f746f-4933-4236-891c-17a805df200c","resolution":{"observed_at":"2026-08-07T14:18:45.086193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:40.710609Z","title":"Attention is all you need.Advances in Neural Information Processing Systems, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:40.710609Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:fda19da4c7b14fe3bfdb3b28f7b6f69355dabd67b8ff671b67cbb4998e1a07a2","observation_id":"81867d02-3006-44ac-9139-67c7ed1f4f5e","resolution":{"observed_at":"2026-08-07T14:18:40.710609Z","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":"2026-08-07T14:18:40.876674Z","title":"Tcl: Transformer-based dynamic graph modelling via contrastive learning.arXiv preprint arXiv:2105.07944, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:40.876674Z"},"links":{"cited_paper":"/paper/2105.07944","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:eead1ef9e440839c492f930065edd1d015425e18a2319a6c6c305a755e731749","observation_id":"c388405f-2670-41ec-900a-3b06788d562c","resolution":{"observed_at":"2026-08-07T14:18:40.876674Z","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":"2026-08-07T14:18:44.746336Z","title":"Inductive representation learning in temporal networks via causal anonymous walks","venue":null,"work_id":"930b89f1-5092-4cc5-8f9f-b53fd66e810e","year":2021},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:41.006458Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:c53cf6c08f0719f75d287cf0ae5622f8722b7a5d24ded5c6b921ea2aed25d5c7","observation_id":"43c6eaa9-352c-4a9b-8691-e10ef4bb5f87","resolution":{"observed_at":"2026-08-07T14:18:44.852877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:44.479125Z","title":"Trend: Temporal event and node dynamics for graph representation learning","venue":null,"work_id":"17d2fcea-66e8-4910-a0cb-8b9cced2e400","year":2022},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:41.139974Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:796a7c24275adaef539c00e60f0763cd4ace172372afcc478d50b0f832715faf","observation_id":"e3ce770e-b795-4a5a-9ce6-af685778ae83","resolution":{"observed_at":"2026-08-07T14:18:44.618638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:44.251826Z","title":"Recurrent recommender networks","venue":null,"work_id":"2e40d39b-732d-44e5-9590-3f53e1f63887","year":2017},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:41.292364Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:00262323248bdc38cdbe85f81e556267ae9f295ab6b6979b3bf44d431b45530e","observation_id":"8ae5f9b9-0a05-44f5-98c9-050f8745a1e5","resolution":{"observed_at":"2026-08-07T14:18:44.367437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:44.029837Z","title":"On the feasibility of simple transformer for dynamic graph modeling","venue":null,"work_id":"e867ddac-1ef6-47df-af92-a91381a5a8df","year":2024},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:41.472877Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:17e45c403fa0732d01ebf0dd3180061e9354edd7b042cba7e8aeca5448c50fdb","observation_id":"376cac0e-2920-4197-b07a-9711ec7b2b72","resolution":{"observed_at":"2026-08-07T14:18:44.126495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:43.802022Z","title":"Inductive representation learning on temporal graphs","venue":null,"work_id":"c7624b03-9c0a-4337-9ddb-af5862931df8","year":2020},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:41.666200Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:156855d1ed21aad30a14f4c7883cc5b780bb5094ee9763b54786a0f69c9dd083","observation_id":"d3edf47b-432e-4f9e-8955-58259871869c","resolution":{"observed_at":"2026-08-07T14:18:43.923534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20256","last_updated":"2024-12-28T20:02:29Z","snapshot_observed_at":"2026-07-06T20:14:08.237082Z","submitted_at":"2024-12-28T20:02:29Z","title":"Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours","version":1},"cited_work":{"arxiv_id":"2412.20256","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.20256","snapshot_observed_at":"2026-08-07T14:18:42.876783Z","title":"Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours","venue":"cs.LG","work_id":"ded6034c-d238-465f-84f0-393a96252612","year":2024},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:41.835629Z"},"links":{"cited_paper":"/paper/2412.20256","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:d8f9fcbb47acdae8b3bfc16ac83028d4f3d0764fcd893229cac0ee103cb7af6c","observation_id":"66fd8a9b-53ea-49a8-8930-c4b7de6ce524","resolution":{"observed_at":"2026-08-07T14:18:42.977402Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:43.645842Z","title":"Tgb-seq benchmark: Challenging temporal gnns with complex sequential dynamics","venue":null,"work_id":"dfdce312-3e98-40bd-8987-ab43f6c6228b","year":null},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:41.986832Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:73f0617831e39a41a42f475042b38183c8b576a60208001220fa1e45aed234e3","observation_id":"1a587110-2258-4436-a7e8-bb1623b04e92","resolution":{"observed_at":"2026-08-07T14:18:43.715961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.12510","last_updated":"2023-10-15T09:18:23Z","snapshot_observed_at":"2026-08-08T03:51:02.752405Z","submitted_at":"2023-07-24T03:52:11Z","title":"An Empirical Evaluation of Temporal Graph Benchmark","version":5},"cited_work":{"arxiv_id":"2307.12510","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.12510","snapshot_observed_at":"2026-08-07T14:18:42.605532Z","title":"An Empirical Evaluation of Temporal Graph Benchmark","venue":"cs.LG","work_id":"ee646213-cdbc-4da0-a816-b08b46501053","year":2023},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:42.124827Z"},"links":{"cited_paper":"/paper/2307.12510","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:76fff61fd1126ce9b235329e601a016d6a4d9748e0bbc2b1c376cdd453d290d0","observation_id":"a695844f-5ba7-4343-b13f-441549782454","resolution":{"observed_at":"2026-08-07T14:18:42.710026Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:18:43.509693Z","title":"Towards better dynamic graph learning: New ar- chitecture and unified library","venue":null,"work_id":"af04ae1d-4548-4f26-887f-35c102614a4b","year":2023},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:42.244686Z"},"links":{"citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:5131a9a2ee0719b23c4f701ad8c7df1a24ac264d636ecfa69c07b247eb2a1205","observation_id":"e4561d95-d4b5-40bb-9d3f-c95739ca272e","resolution":{"observed_at":"2026-08-07T14:18:43.546894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18211","last_updated":"2024-04-28T15:07:48Z","snapshot_observed_at":"2026-08-09T11:42:18.602047Z","submitted_at":"2024-04-28T15:07:48Z","title":"A survey of dynamic graph neural networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18211","snapshot_observed_at":"2026-08-07T14:18:42.395182Z","title":"A survey of dynamic graph neural networks.arXiv preprint arXiv:2404.18211, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:42.395182Z"},"links":{"cited_paper":"/paper/2404.18211","citing_paper":"/paper/2505.19408"},"observation_digest":"sha256:ce59c7d3bba7d35d6be569414a517deea03de4fddd947839af47df1181bf8c09","observation_id":"24304d45-1834-4771-95e3-a1c05f01d0d6","resolution":{"observed_at":"2026-08-07T14:18:42.395182Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.19408","last_updated":"2025-05-26T01:53:27Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T01:26:31.176700Z","submitted_at":"2025-05-26T01:53:27Z","title":"Future Link Prediction Without Memory or Aggregation"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":3,"verified_fuzzy":24},"total_outbound_references":43},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2505.19408."}