{"as_of":"2026-08-22T22:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6acb16d0db9432476719841e94cf192bcce4d986a0ecf508a6d710f6e23eeba3","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T13:37:37.587899Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T22:52:59.081816Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T19:16:01.138485Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"cited_work":{"arxiv_id":"2411.16127","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.16127","snapshot_observed_at":"2026-07-01T19:16:01.138485Z","title":"Matthias, F., Jinu, S., Akihiro, N., Rishi, P., Manan, S., Blaˇz, S., Bendias, R., Barghi, A., Vid, K., Zecheng, Z., Xinwei, H., E., L","venue":null,"work_id":"ba39f44e-3c49-4fab-bb23-d2a23ee58a3a","year":null},"citing_paper":{"arxiv_id":"2605.31500","last_updated":"2026-05-29T16:22:45Z","snapshot_observed_at":"2026-08-14T23:52:33.085463Z","submitted_at":"2026-05-29T16:22:45Z","title":"On Efficient Scaling of GNNs via IO-Aware Layers Implementations","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T22:52:59.081816Z"},"links":{"cited_paper":"/paper/2411.16127","citing_paper":"/paper/2605.31500"},"observation_digest":"sha256:ef756b1ea35ea50d7ad5a694e577264020affe6efadb0913e495eac6269d1c0f","observation_id":"284776bb-06a3-452f-b213-9c0037792e6d","resolution":{"observed_at":"2026-07-01T19:16:01.140293Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.16127/citation-record","integrity":"/paper/2411.16127/integrity","json":"/paper/2411.16127/citation-record.json","paper":"/paper/2411.16127"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T13:37:37.473101Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.473101Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:63ee62fd4e091ce9f89152ab5ad7b43da4be9f359804b7dedc7243ce36afa4c1","observation_id":"4411b5c7-0a51-490d-b879-9f4eb29cf012","resolution":{"observed_at":"2026-08-12T13:37:37.473101Z","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":"2026-08-12T13:37:37.477577Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.477577Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:fda88e611e83085741f1f4038fc704622ac6a3d0feeb30c0f94ddcd9ba4c3cab","observation_id":"e2dd2b69-8937-469d-8fd2-b794f7a57932","resolution":{"observed_at":"2026-08-12T13:37:37.477577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.14491","last_updated":"2022-01-31T07:20:20Z","snapshot_observed_at":"2026-07-06T11:14:04.454155Z","submitted_at":"2021-05-30T10:17:58Z","title":"How Attentive are Graph Attention Networks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.14491","snapshot_observed_at":"2026-08-12T13:37:37.482448Z","title":"How attentive are graph attention networks? arXiv preprint arXiv:2105.14491, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.482448Z"},"links":{"cited_paper":"/paper/2105.14491","citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:91efde8aa7dddc06f593b551796e86650d63b068908529c28da80fb1e00b08f7","observation_id":"e530618f-e48e-4f96-a281-091384177706","resolution":{"observed_at":"2026-08-12T13:37:37.482448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.09699","last_updated":"2021-01-24T09:38:54Z","snapshot_observed_at":"2026-08-17T09:51:04.568396Z","submitted_at":"2020-12-17T16:11:47Z","title":"A Generalization of Transformer Networks to Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.09699","snapshot_observed_at":"2026-08-12T13:37:37.486846Z","title":"A generalization of transformer networks to graphs","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.486846Z"},"links":{"cited_paper":"/paper/2012.09699","citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:e8e10ad1f4d22473446c6f6b2f95ad05ea6479db0842880de05dace8994817ea","observation_id":"a2ca54ef-7b8d-4b4b-9fc0-295543dd67e3","resolution":{"observed_at":"2026-08-12T13:37:37.486846Z","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":"2026-08-12T13:37:37.921570Z","title":"Do transformers really perform badly for graph representation? Advances in Neural Information Processing Systems, 34:28877–28888, 2021","venue":null,"work_id":"216cd98b-61ab-45dd-b718-3138f9eb3e22","year":2021},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.492563Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:8f52baedd6f6967f0b7a8fc96833b359d56b25d1fdd4bbcdba00dbda34ddfaaa","observation_id":"42fe1a6b-688f-46ba-b00b-6700dd67b283","resolution":{"observed_at":"2026-08-12T13:37:37.925668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.909237Z","title":"Recipe for a general, powerful, scalable graph transformer","venue":null,"work_id":"4186b21f-f5e7-4bf5-94d3-79963de4dfdb","year":2022},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.496821Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:dcc33ab93f40d1d3c747d35fb8563f0902414f89576ab3cd978e9fe3a2c52a10","observation_id":"5d179db4-03c3-4c42-9bcf-a8a3c6240eb7","resolution":{"observed_at":"2026-08-12T13:37:37.913704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03735","last_updated":"2018-03-10T02:01:35Z","snapshot_observed_at":"2026-08-21T13:28:40.935606Z","submitted_at":"2018-03-10T02:01:35Z","title":"Attention-based Graph Neural Network for Semi-supervised Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03735","snapshot_observed_at":"2026-08-12T13:37:37.501244Z","title":"Attention-based graph neural network for semi-supervised learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.501244Z"},"links":{"cited_paper":"/paper/1803.03735","citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:08659e84711e3cc3b99fa787d6181c55ec8072688ff1e2230b7fed6bf63229d8","observation_id":"addeb81e-865b-44d0-8ddd-7e91b5a52bea","resolution":{"observed_at":"2026-08-12T13:37:37.501244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-17T10:49:36.026134Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-12T13:37:37.505423Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.505423Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:bbc27921d43f584ae5552c3dad3d4081bc8c72db1ad5e34e65b197baeab60589","observation_id":"c32b262e-339b-4467-96d2-298db7cb087c","resolution":{"observed_at":"2026-08-12T13:37:37.505423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00826","last_updated":"2019-02-22T19:15:54Z","snapshot_observed_at":"2026-08-21T22:36:44.881291Z","submitted_at":"2018-10-01T17:11:31Z","title":"How Powerful are Graph Neural Networks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00826","snapshot_observed_at":"2026-08-12T13:37:37.509600Z","title":"How powerful are graph neural networks? arXiv preprint arXiv:1810.00826, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.509600Z"},"links":{"cited_paper":"/paper/1810.00826","citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:f0a2e9ef5f5442615ec27d02ecb95c828d1833a772c3788e4b01aec60cc5b62b","observation_id":"647cc6d4-93a4-4ff8-92b1-0f513c5de19a","resolution":{"observed_at":"2026-08-12T13:37:37.509600Z","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":"2026-08-12T13:37:37.513789Z","title":"Link prediction based on graph neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.513789Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:89fbfd3927bb3b8517c3ad40204f4fa3e5539bf7a8b1ee966026fa5c6b723002","observation_id":"94591dbd-f286-42a8-9390-1eb513221c27","resolution":{"observed_at":"2026-08-12T13:37:37.513789Z","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":"2026-08-12T13:37:37.517389Z","title":"Neural bellman-ford networks: A general graph neural network framework for link prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.517389Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:9c961b0f5ceba0ff5ae841bc54ba676d7d5547adc99e4a4fb79180fe2f4871ba","observation_id":"58837d9f-9d39-4154-9c0d-dfce1a9f5fbe","resolution":{"observed_at":"2026-08-12T13:37:37.517389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.09893","last_updated":"2022-02-17T20:19:28Z","snapshot_observed_at":"2026-08-19T02:35:40.814401Z","submitted_at":"2019-12-20T15:40:50Z","title":"A Fair Comparison of Graph Neural Networks for Graph Classification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.09893","snapshot_observed_at":"2026-08-12T13:37:37.521340Z","title":"A fair comparison of graph neural networks for graph classification","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.521340Z"},"links":{"cited_paper":"/paper/1912.09893","citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:ff03c622dff85f98bc2ea5ef611a206ed6716dfd3798e4f49fe927ab63fd9435","observation_id":"ef7c833c-8326-4c0c-b557-14fc7f10de76","resolution":{"observed_at":"2026-08-12T13:37:37.521340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.01000","last_updated":"2020-01-17T16:20:00Z","snapshot_observed_at":"2026-08-18T22:53:19.441314Z","submitted_at":"2019-07-31T06:28:43Z","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01000","snapshot_observed_at":"2026-08-12T13:37:37.525747Z","title":"Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization.arXiv preprint arXiv:1908.01000, 2019","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.525747Z"},"links":{"cited_paper":"/paper/1908.01000","citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:380b5e438a7c342a2b15a00d31e050bf4b123906cc5e98301a7b72d22e624a3d","observation_id":"a3088a84-760d-4c36-a10c-1a50f2bcfe51","resolution":{"observed_at":"2026-08-12T13:37:37.525747Z","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":"2026-08-12T13:37:37.881184Z","title":"Deep graph library: Towards efficient and scalable deep learning on graphs","venue":null,"work_id":"a3adbf58-a042-4639-9aca-814f099a7b84","year":2019},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.529747Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:6c9bbdbe18bf4521ff21b6073ae5007cbe131e5ccf1c917ae74f13a99a7f6431","observation_id":"9bb86616-9626-4ae4-b588-1b35757dce90","resolution":{"observed_at":"2026-08-12T13:37:37.885544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.02428","last_updated":"2019-04-25T10:06:09Z","snapshot_observed_at":"2026-08-02T18:54:43.326912Z","submitted_at":"2019-03-06T14:50:02Z","title":"Fast Graph Representation Learning with PyTorch Geometric","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.02428","snapshot_observed_at":"2026-08-12T13:37:37.533268Z","title":"Fast graph representation learning with pytorch geometric","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.533268Z"},"links":{"cited_paper":"/paper/1903.02428","citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:3af87c937a36d1f2d7f5b541163c2d1e16805d3de5714505bd0991622098b17b","observation_id":"aa208e5d-89ae-4eab-b14b-58852f1633c8","resolution":{"observed_at":"2026-08-12T13:37:37.533268Z","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":"2026-08-12T13:37:37.537152Z","title":"Neural message passing for quantum chemistry","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.537152Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:4dccd25863e7e848129c435e6a44a5865093ef5a5ea00170ef36b7cd138d5d08","observation_id":"5515057b-5f25-4647-9d34-96d121e1187b","resolution":{"observed_at":"2026-08-12T13:37:37.537152Z","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":"2026-08-12T13:37:37.859823Z","title":"Seastar: vertex-centric programming for graph neural networks","venue":null,"work_id":"259a38f1-dbb6-4fe9-904a-fc16ffb46d5d","year":2021},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.540907Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:de97e4a5c6f0ac6bb83f140cd79ff710cf9e0bbd5946c7bd0c16812172ccb32f","observation_id":"d4171d66-fb79-4e21-be87-28093046482b","resolution":{"observed_at":"2026-08-12T13:37:37.864306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.846550Z","title":"Understanding gnn computational graph: A coordinated computation, io, and memory perspective","venue":null,"work_id":"4e6b8608-9232-4b75-bf9e-fb5974e04a66","year":2022},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.544444Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:a207aa62b6b2ee3fe0f3dee7d96e981a8d3eebf422ce70f33f70710969a0b176","observation_id":"eaaea74e-26b7-42d1-84a8-4cd8730ce540","resolution":{"observed_at":"2026-08-12T13:37:37.850887Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.833142Z","title":"Tlpgnn: A lightweight two-level parallelism paradigm for graph neural network computation on gpu","venue":null,"work_id":"0983e4b7-4a08-47e7-b3e5-37205e91f545","year":2022},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.548225Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:f5451072d8e9e918eaf5456709fdbdb4ac2a2419aaa49021da36c82dab91edbc","observation_id":"cc04967d-1646-49ff-970f-ff1ba851155f","resolution":{"observed_at":"2026-08-12T13:37:37.838329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.820651Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":"18d20207-e42a-4fc1-957f-3a106649db20","year":2019},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.551892Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:15cc9ba7f4750158127b4d9e887c200b10fcf85b94ed2b00bf0d864622f05dcc","observation_id":"7aa34703-6eaa-45b1-8c0d-5087eee17270","resolution":{"observed_at":"2026-08-12T13:37:37.825061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.555725Z","title":"Flashattention: Fast and memory-efficient exact attention with io-awareness.Advances in Neural Information Processing Systems, 35:16344–16359, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.555725Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:6895c27a7aaed67342733fa2221c113368488e3e0559336fbbed8c38cca9ef92","observation_id":"8cb83550-dbde-47fa-b180-67e7896a11a5","resolution":{"observed_at":"2026-08-12T13:37:37.555725Z","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":"2026-08-12T13:37:37.800649Z","title":"Fusedmm: A unified sddmm- spmm kernel for graph embedding and graph neural networks","venue":null,"work_id":"ea11cbaa-8471-43b8-83f0-cc82d6045354","year":2021},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.560350Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:78fcca9ae6ea264387fcae0fb779d118642df8d8e6e99d3582febb7e0d17992f","observation_id":"3a53d581-2266-4163-bd2a-71ab0b666581","resolution":{"observed_at":"2026-08-12T13:37:37.805243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.788489Z","title":"Graphiler: Optimizing graph neural networks with message passing data flow graph","venue":null,"work_id":"31c8af91-135b-4122-85d5-829b1d73deae","year":2022},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.564177Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:eb70a47cdbbfbc8fa8c1a8da7a75c483d78cc0e52e9dcd340462c235b6fe7e84","observation_id":"5854c556-9ab3-4bec-b861-8a284a84e0e8","resolution":{"observed_at":"2026-08-12T13:37:37.792306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.776698Z","title":"Featgraph: A flexible and efficient backend for graph neural network systems","venue":null,"work_id":"aee1dc0a-597c-4372-b7c9-fb326049dbe8","year":2020},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.567985Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:0a53d9177d94c109c8efa71c97137285f0e3b32049253b13452ef09f7efb32ba","observation_id":"886782a8-186e-4365-94d4-cfd5846c88e4","resolution":{"observed_at":"2026-08-12T13:37:37.780688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.764870Z","title":"Sparsetir: Composable abstractions for sparse compilation in deep learning","venue":null,"work_id":"2286f0e9-90d1-46ee-b8fe-dec04cda88e8","year":2023},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.571960Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:99b35c8680fb368263f9a769905fb5ec9e6257898298f81646600b9ad43911b8","observation_id":"db46f5bc-c77d-4e93-ba3e-ee11f1763e79","resolution":{"observed_at":"2026-08-12T13:37:37.769328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.752418Z","title":"Exploiting online locality and reduction parallelism for sampled dense matrix multiplication on gpus","venue":null,"work_id":"3433b0fc-e531-4646-b422-85f26163f4f1","year":2021},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.575737Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:b17255f467c709e956c577d22c54906c7ccbe70f64532daa18cd1b0df39086e4","observation_id":"403deb5a-32be-4b8b-867f-c67643769c19","resolution":{"observed_at":"2026-08-12T13:37:37.757292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.739930Z","title":"Rapids cugraph, 2024","venue":null,"work_id":"56969463-5130-4d4d-8460-39cd33515389","year":2024},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.579843Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:fae20a3e46fa3e532da5755710fcb8018e26008f681b46a8100bed6b7fbce395","observation_id":"0bb250aa-fea5-4394-ae35-ce7c4b8afe4a","resolution":{"observed_at":"2026-08-12T13:37:37.744306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T13:37:37.583717Z","title":"Benchmarking graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.583717Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:cae50cbe323f8c339a4f2deebe48c0007032d51a7d0ace864a2c877d1068194b","observation_id":"d64824cd-d8b5-4038-8ad2-40db77298c95","resolution":{"observed_at":"2026-08-12T13:37:37.583717Z","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":"2026-08-12T13:37:37.718167Z","title":"Long range graph benchmark","venue":null,"work_id":"770452f3-225d-4aba-8d99-863bd92e529e","year":2022},"citing_paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:37.587899Z"},"links":{"citing_paper":"/paper/2411.16127"},"observation_digest":"sha256:740ed3724aef2bdd0452bed586fd9cb54199f71fb900adcafb5ddd3ee3a1d890","observation_id":"8e68939d-f988-4b5b-bb7d-dddb891f2ba0","resolution":{"observed_at":"2026-08-12T13:37:37.723489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.16127","last_updated":"2024-11-25T06:26:58Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-21T08:41:35.480885Z","submitted_at":"2024-11-25T06:26:58Z","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":14},"total_outbound_references":29},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 1 inbound Pith citation observation for arXiv:2411.16127."}