{"as_of":"2026-08-22T17:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2264547465d95c3fac78b49d2516b523903c530d3b4f54e120c4caf7fbd70b2e","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:18:34.177210Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2504.13266/citation-record","integrity":"/paper/2504.13266/integrity","json":"/paper/2504.13266/citation-record.json","paper":"/paper/2504.13266"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:18:36.471184Z","title":"u rek, \\","venue":null,"work_id":"aa925c55-a369-45ab-85d2-666c623617b4","year":2024},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.023555Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:384f633b2cb3558fbc2ee1a7f439435c05ea9060e5ba79a33e55ae969d397356","observation_id":"550b7dff-44d6-4604-9ccf-6ea515a5be26","resolution":{"observed_at":"2026-08-16T12:18:36.531286Z","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":"2026-08-16T12:18:36.458909Z","title":"DSP: Efficient GNN Training with Multiple GPUs","venue":null,"work_id":"d7da4331-5709-4099-b38c-d4349bee1fe1","year":2023},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.129099Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:62ae09f75fccca764e64674417fb34b7efc393c13dc4de796016434e13a7ed74","observation_id":"06208c25-8f0e-482c-8cba-236e9ef6c74d","resolution":{"observed_at":"2026-08-16T12:18:36.462795Z","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":"1710.10568","last_updated":"2018-03-01T15:23:22Z","snapshot_observed_at":"2026-08-21T10:13:24.862589Z","submitted_at":"2017-10-29T06:14:00Z","title":"Stochastic Training of Graph Convolutional Networks with Variance Reduction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10568","snapshot_observed_at":"2026-08-16T12:18:33.176978Z","title":"Stochastic Training of Graph Convolutional Networks with Variance Reduction","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.176978Z"},"links":{"cited_paper":"/paper/1710.10568","citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:f89ba304c3e2283343c8980726455a45bdf8f80b4fc7ed379e46f1e3076fdff7","observation_id":"4decd93c-ffd5-4eaf-8583-1a0d7b3970b2","resolution":{"observed_at":"2026-08-16T12:18:33.176978Z","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":"2026-08-16T12:18:36.353336Z","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","venue":null,"work_id":"53d9d08e-af0a-45cd-bc25-d5791595a4dc","year":2018},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.182612Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:f16e39941f7346ec60ea2455d2a8b5f86f698353953d600c78d2030287f51c79","observation_id":"2899d217-167c-452c-90dd-8b3f15aaa514","resolution":{"observed_at":"2026-08-16T12:18:36.388119Z","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":"2010.15116","last_updated":"2020-12-02T16:46:23Z","snapshot_observed_at":"2026-08-18T04:05:09.539497Z","submitted_at":"2020-10-28T17:59:59Z","title":"On Graph Neural Networks versus Graph-Augmented MLPs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.15116","snapshot_observed_at":"2026-08-16T12:18:33.187558Z","title":"On Graph Neural Networks Versus Graph-Augmented MLPs","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.187558Z"},"links":{"cited_paper":"/paper/2010.15116","citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:dcbb775f2950549a1498092a2c2bba13001c2c667398686834b372d8a64e0dd3","observation_id":"dcf87627-0bb2-4075-a210-4cc504bbd5f6","resolution":{"observed_at":"2026-08-16T12:18:33.187558Z","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":"2026-08-16T12:18:36.340872Z","title":"Scalable Graph Neural Networks via Bidirectional Propagation","venue":null,"work_id":"bfd53e5c-27a1-45cf-9f62-bef1bbd8dd68","year":2020},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.192669Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:e229281b19b64a016c706b2bbd45aa808493daa164435e9faa703c05f049b57b","observation_id":"827f7090-e45d-4619-bc1a-8caacedf2c1f","resolution":{"observed_at":"2026-08-16T12:18:36.344996Z","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":"2026-08-16T12:18:36.240046Z","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","venue":null,"work_id":"1aeeb350-3133-47d5-883b-29ac22ea6902","year":2019},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.292969Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:b2e463eeb28ce2ecd459150f1e9b0b66b4bcdd3d565de233e7eedc2247d02d90","observation_id":"6f9c1a1e-73da-49e9-ac94-8e0107b99dee","resolution":{"observed_at":"2026-08-16T12:18:36.293235Z","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":"2026-08-16T12:18:36.227397Z","title":"Less is More: Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits","venue":null,"work_id":"91cac90c-e292-4aa1-8da3-6f5fbf9e420c","year":2024},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.330459Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:b2076ac4b354b40dbbe7b21caa447c4506d06f318bbc5097f03f7ca030b5441e","observation_id":"0ba5caaa-db22-4e91-8797-904fadacd0f3","resolution":{"observed_at":"2026-08-16T12:18:36.231342Z","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":"2026-08-16T12:18:36.150580Z","title":"On the Equivalence of Decoupled Graph Convolution Network and Label Propagation","venue":null,"work_id":"878511ee-715c-4f36-8da7-89568ef9ec9e","year":2021},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.335911Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:79f1303f597853d2b32b4b22b8474887d156fbb3be4c6ebd2b8936e8349d9c49","observation_id":"6f2b0742-346c-4f46-a3be-89495a1f22b7","resolution":{"observed_at":"2026-08-16T12:18:36.211828Z","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":"2004.11198","last_updated":"2020-11-03T19:20:22Z","snapshot_observed_at":"2026-08-18T16:51:06.422299Z","submitted_at":"2020-04-23T14:46:10Z","title":"SIGN: Scalable Inception Graph Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.11198","snapshot_observed_at":"2026-08-16T12:18:33.340214Z","title":"SIGN: Scalable Inception Graph Neural Networks","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.340214Z"},"links":{"cited_paper":"/paper/2004.11198","citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:8ffe9e7ad4bbc9717aef34dfe66d0edc7e3bffb2ccf9e4279b656950d8dee464","observation_id":"bc32c440-acc7-4c76-ad77-2bb078fb2560","resolution":{"observed_at":"2026-08-16T12:18:33.340214Z","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":"2026-08-16T12:18:36.139647Z","title":"Diffusion Improves Graph Learning","venue":null,"work_id":"7486a632-c74d-4576-9223-83b30dc9634a","year":2019},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.346355Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:a2872ed2129bec20abb7352636c1b7e03a2ea233c0057108baab717eeb16fe7a","observation_id":"ac1af4ab-3a54-441f-9bf0-d1d7d563a6f6","resolution":{"observed_at":"2026-08-16T12:18:36.143263Z","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":"2026-08-16T12:18:36.046548Z","title":"S., Riley, P","venue":null,"work_id":"624f83f1-6085-4554-a240-fad04fde114d","year":2017},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.351923Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:71e1c25514ac9d365835e98612820eb22cc3e66109a3b04d1ddc3f49f1e96885","observation_id":"225d65d8-42ee-4c1f-83de-2f900fd537af","resolution":{"observed_at":"2026-08-16T12:18:36.130386Z","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":"2026-08-16T12:18:36.034177Z","title":"Inductive Representation Learning on Large Graphs","venue":null,"work_id":"fac11aeb-1849-43eb-b732-44228cca4c69","year":2017},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.355900Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:d9f7f81bef1966e216dfb2e9600a2c90297e18f4efd3318c939d849fe34fdad9","observation_id":"5bbc11fc-a8fa-499d-adfc-867b9d7b8688","resolution":{"observed_at":"2026-08-16T12:18:36.038474Z","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":"2026-08-16T12:18:35.927507Z","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","venue":null,"work_id":"b3d4a1fb-d8c9-4dc8-822a-526803b369e7","year":2020},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.359891Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:3f6e37d035ccd0587ffbf6d8e55ca67fc67d3bd5aea24e3190a214c7cf599732","observation_id":"65b1e6f3-3a7c-43e2-9d36-9210086f6647","resolution":{"observed_at":"2026-08-16T12:18:35.980661Z","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":"2026-08-16T12:18:35.914741Z","title":"GE-SpMM: General-Purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks","venue":null,"work_id":"67397542-290d-430a-bbf1-260f74fadcb4","year":2020},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.363677Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:bb8a68dc96427b5bf87a50332c4e29fc9161d4455a2ae989331844fa5e300d88","observation_id":"6dcd5059-5210-4b44-ba6c-42c33fabccf8","resolution":{"observed_at":"2026-08-16T12:18:35.919286Z","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":"2026-08-16T12:18:35.892315Z","title":"WiseGraph: Optimizing GNN with Joint Workload Partition of Graph and Operations","venue":null,"work_id":"dce545c2-98a3-4051-bb4b-37c0de929382","year":2024},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.367442Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:a2d64e3f825926f3f9635d0bfb1f3594fd1a36a87f966f431ee9b1920896f8a0","observation_id":"e22c3500-deb8-468b-b0e9-eeefe06fd58e","resolution":{"observed_at":"2026-08-16T12:18:35.905689Z","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":"2026-08-16T12:18:35.818064Z","title":"E., and Chen, J","venue":null,"work_id":"76b426d9-0029-4185-b811-791fc41ab2f4","year":2023},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.413123Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:44b66cb0618077d65826028400f1d947747f29708323b99c8110e9901a4f5bea","observation_id":"0f0cbae5-8e10-49d4-b8c6-1c84dcaaea1d","resolution":{"observed_at":"2026-08-16T12:18:35.822391Z","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":"2026-08-16T12:18:35.806012Z","title":"S., Taleka, B., Ma, T., Song, X., and Hwu, W.-m","venue":null,"work_id":"3016b9d9-b678-4392-bf24-fd9d9feb9194","year":2023},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.492357Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:0dd2049eba834cfe522338b530bf6ac72c9da8bac09083781bec4996af747512","observation_id":"54df1c73-f0d3-4fa7-96fd-0b94403c4064","resolution":{"observed_at":"2026-08-16T12:18:35.809969Z","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":"2026-08-16T12:18:35.767262Z","title":null,"venue":null,"work_id":"144b7e92-fb7e-4c96-999a-035233ae91d9","year":2017},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.547364Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:852770833e328260c6d584fd5bd24b9e7e36f39f9ca166c66d4ee969e14119b5","observation_id":"c14ce95b-d0cd-4e89-8ef1-06f51213d528","resolution":{"observed_at":"2026-08-16T12:18:35.796712Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T12:18:35.723906Z","title":"SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization","venue":null,"work_id":"0603f5ea-1275-42ba-9dba-2a85b499d9ea","year":2022},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.551683Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:a63b02aef360612ab92011c2576cdb5aae134c6cb95e8458652a607e63c6360f","observation_id":"7655a84a-4668-4cda-a5fd-0e5f0cc89e41","resolution":{"observed_at":"2026-08-16T12:18:35.727988Z","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":"2026-08-16T12:18:35.711189Z","title":"LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings","venue":null,"work_id":"d136aa64-9377-4dff-9b90-88ca123c579f","year":2024},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.556447Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:477c4e6f01c8d5248f04b77881fe94e2e6f25a46429dd8f9d6204ec6595c3cf3","observation_id":"23256316-9d62-4fd5-ab1f-1b6849287e25","resolution":{"observed_at":"2026-08-16T12:18:35.715350Z","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":"2026-08-16T12:18:35.699021Z","title":"L., Gupta, V., Bhalerao, O., and Lim, S","venue":null,"work_id":"c8f08c9e-6500-47b2-9404-c59af2f0f537","year":2021},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.560787Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:ca7fa87d852a9d616ee6873c0f5fc8874ee79520f6c872f023c680c5300ba579","observation_id":"d1e747fc-abe6-4828-a5d5-9048a8b5fb03","resolution":{"observed_at":"2026-08-16T12:18:35.702667Z","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":"2026-08-16T12:18:35.605492Z","title":"PaGraph: Scaling GNN Training on Large Graphs via Computation-Aware Caching","venue":null,"work_id":"8ab30312-d9e3-4463-9f4e-a04dc9e0da1b","year":2020},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.565585Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:ef2e540ea2e1f66bb0a1031c5a0307e93eabea9c57eeb6d3991d2e5b801f6fc4","observation_id":"6e50e3ab-1d96-49c4-b638-b57cd12e0e9e","resolution":{"observed_at":"2026-08-16T12:18:35.651266Z","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":"2026-08-16T12:18:35.531476Z","title":"BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing","venue":null,"work_id":"150779c9-ee38-4d77-b9e7-55fd1f9842b6","year":2023},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.570056Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:db399cb5a8365dfdd46ce859b4a5112e704235744bd532c5830253c38066c29b","observation_id":"5a54a40b-cd1a-499e-ad8a-d3812070e4dc","resolution":{"observed_at":"2026-08-16T12:18:35.535437Z","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":"2026-08-16T12:18:35.518725Z","title":"Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling","venue":null,"work_id":"828a9a43-2c77-4e89-a98e-e79ffa762eea","year":2019},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.574226Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:3bc874918ac07285df844744c3159d35d1b92039ca9fc5cdfff3fc6100929f8c","observation_id":"767b9217-a787-481e-9ac7-0e095048bbad","resolution":{"observed_at":"2026-08-16T12:18:35.523972Z","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":"2026-08-16T12:18:35.400911Z","title":"Random Reshuffling: Simple Analysis With Vast Improvements","venue":null,"work_id":"ad663505-91ec-49b6-9854-332db45ade8a","year":2020},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.577901Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:64afd85f5853f18966cc51df66f646c2f9ee1707c201253df4855df0a2bfe9be","observation_id":"a1be8fbd-a344-4220-a019-950d40d2e645","resolution":{"observed_at":"2026-08-16T12:18:35.461909Z","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":"2026-08-16T12:18:35.388461Z","title":"T., Trahay, F., Domke, J., Drozd, A., Vatai, E., Liao, J., Wahib, M., and Gerofi, B","venue":null,"work_id":"1d07dd4a-4cc0-4404-9aed-5cf5fda28e33","year":2022},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.581606Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:21836000b8ffa2ff1bdb35382ddd4ed86fb7995e893df81ca7b89ef6b2720fac","observation_id":"24122ca3-39d4-463d-aef4-5a12c0d110ee","resolution":{"observed_at":"2026-08-16T12:18:35.393362Z","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":"1905.09550","last_updated":"2019-05-26T05:21:04Z","snapshot_observed_at":"2026-08-15T09:42:10.790008Z","submitted_at":"2019-05-23T09:27:21Z","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.09550","snapshot_observed_at":"2026-08-16T12:18:33.586299Z","title":"and Maehara, T","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.586299Z"},"links":{"cited_paper":"/paper/1905.09550","citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:6435e4cb7ce70d53bfff2429f4cd4067f0cd03950cc1089e6a906b78b4e4bd45","observation_id":"ce7c62e3-dba2-47d2-b853-f325a97ea6cc","resolution":{"observed_at":"2026-08-16T12:18:33.586299Z","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":"2026-08-16T12:18:35.376127Z","title":null,"venue":null,"work_id":"37e6069d-314a-4450-99ec-1b4c78b8d9cc","year":2022},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.590822Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:737fb08ce145dc87ce9c63cabb088aea4978775d9e70425528f85368401eb548","observation_id":"679681bf-49d5-4554-96b5-57d8bdc2c7dd","resolution":{"observed_at":"2026-08-16T12:18:35.380747Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T12:18:35.240515Z","title":"TPUGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs","venue":null,"work_id":"7bad9e82-3c7c-4e9f-8ebb-8603c9722e49","year":2024},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.594867Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:a5de798a4a07893b16620412639097c385948167aac49aabcbbb65409c4314c1","observation_id":"a891e56f-9889-4a2a-b7fe-6b7e533d4e5a","resolution":{"observed_at":"2026-08-16T12:18:35.287289Z","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":"2026-08-16T12:18:35.229242Z","title":null,"venue":null,"work_id":"52012d41-833b-4e38-9f68-2a81ac6364fb","year":2011},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.654768Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:7db1f81a978f1cad998ab8b4cfc2047de555d0be051d1d00f2857a941712f761","observation_id":"ee40437a-30ce-4695-a9bf-b31672b06722","resolution":{"observed_at":"2026-08-16T12:18:35.233191Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T12:18:35.217111Z","title":"u tt, K., Kindermans, P.-J., Sauceda Felix, H. E., Chmiela, S., Tkatchenko, A., and M \\","venue":null,"work_id":"fa4a7dec-25a4-4614-9741-3b20972b4d30","year":2017},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.735801Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:aa55df5dc248030048cd33ae1f771451cbbf39b812b624ebe08949013da20c5d","observation_id":"0b49d084-0be7-4238-bcef-750d92397805","resolution":{"observed_at":"2026-08-16T12:18:35.222107Z","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":"2026-08-16T12:18:35.004249Z","title":"Legion: Automatically Pushing the Envelope of Multi-GPU System for Billion-Scale GNN Training","venue":null,"work_id":"23cd8c04-d18f-40b4-8392-31f934021415","year":2023},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.740346Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:a8b12cb9a4142bf07809bd8db2a27d8ce36a10f454012a59f72d2414f7919f96","observation_id":"73e3678b-20ef-447b-8de8-c6b50ab27f61","resolution":{"observed_at":"2026-08-16T12:18:35.103010Z","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":"2305.10863","last_updated":"2023-05-18T10:34:23Z","snapshot_observed_at":"2026-08-18T04:05:57.483982Z","submitted_at":"2023-05-18T10:34:23Z","title":"Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10863","snapshot_observed_at":"2026-08-16T12:18:33.744211Z","title":"Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.744211Z"},"links":{"cited_paper":"/paper/2305.10863","citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:2ff69771080cf0a6255286d3a42e019533f856e823397f46c80328189358e473","observation_id":"11b2eb63-1460-4a4d-b110-c2ed54f386ab","resolution":{"observed_at":"2026-08-16T12:18:33.744211Z","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":"2026-08-16T12:18:34.990833Z","title":"and Newburn, C","venue":null,"work_id":"a2c10072-1ed4-4c0c-81fb-0b98e0a97fc2","year":2019},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.748960Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:feb052fe51698278d1f1a478845da78a5dee7ed1406cccd0cbfd196115c7c1bf","observation_id":"1b908e71-e700-4145-b59f-7c0873cbc07b","resolution":{"observed_at":"2026-08-16T12:18:34.995338Z","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":"2026-08-16T12:18:34.864265Z","title":"Graph Clustering with Graph Neural Networks","venue":null,"work_id":"2bebc417-ea6e-482b-8ca7-227f9360d7b5","year":2023},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.754352Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:e3dbac13dce65c895ec3cad9205f1a2fb58d7e7da54832483a5291074f7d3390","observation_id":"f99e4d19-5cff-41d9-abcb-c5eb0fdb1aeb","resolution":{"observed_at":"2026-08-16T12:18:34.983455Z","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":"2026-08-16T12:18:34.796219Z","title":"Graph Attention Networks","venue":null,"work_id":"11b2440f-e6c9-461b-849e-5c8d8e45f608","year":2018},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.759054Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:cdc71b5419bf259ea2bccd79da1ee99bae6be3e47a333903df2d95ee0b13fe2d","observation_id":"6c633d1c-51f7-449c-8ca7-b09e2dfc90bf","resolution":{"observed_at":"2026-08-16T12:18:34.855558Z","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":"2026-08-16T12:18:34.691944Z","title":null,"venue":null,"work_id":"4314f15c-7a2d-4e70-8f26-7a1ba0021264","year":2019},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.823318Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:fa06b632b71aeb54a2083992ee5ea503504f0fe08f0452cc3f0169a9704a8cc3","observation_id":"5c4a9470-802b-4e7a-960c-e263c1a49722","resolution":{"observed_at":"2026-08-16T12:18:34.727179Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T12:18:34.679482Z","title":"Simplifying Graph Convolutional Networks","venue":null,"work_id":"e5841539-e09b-4d0a-9af8-09121d71a66b","year":2019},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.862946Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:76951a2f061f28c379eb8af0f97dccd014b16ee02684b51e1690d77e6b767089","observation_id":"4bc53d4e-def9-494e-97f3-237131a06615","resolution":{"observed_at":"2026-08-16T12:18:34.683956Z","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":"2026-08-16T12:18:34.571249Z","title":"Gamora: Graph Learning Based Symbolic Reasoning for Large-Scale Boolean Networks","venue":null,"work_id":"aa03809a-6cba-488b-ba56-5b2c0c05fed8","year":2023},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.867385Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:0c7ec859c5102f26c7240df6c25ca0a5967c30d301d5c39da52c703aa1cdb854","observation_id":"de61f03a-3ea0-4f15-951c-8af3e66a855b","resolution":{"observed_at":"2026-08-16T12:18:34.626948Z","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":"2026-08-16T12:18:34.558232Z","title":"and Cong, G","venue":null,"work_id":"6dd93451-b720-4927-8d9d-35c810c4868f","year":2019},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.871940Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:e0008675024dddc16fb581222b1ad4c929dca7e3832778c29ec44fff5917c4da","observation_id":"fadf6970-6c53-4764-8790-304968e55032","resolution":{"observed_at":"2026-08-16T12:18:34.562439Z","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":"2026-08-16T12:18:34.544875Z","title":"GNNLab: A Factored System for Sample-Based GNN Training Over GPUs","venue":null,"work_id":"0a113329-7b11-4add-b437-983734d42868","year":2022},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.876105Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:18140e913ab32970b58e03babda81df163ee4d4444ccfeaea526b9ca1c345319","observation_id":"b0e6b9da-d762-42fa-8336-b7a5acd47da8","resolution":{"observed_at":"2026-08-16T12:18:34.549496Z","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":"2026-08-16T12:18:34.494117Z","title":"L., and Leskovec, J","venue":null,"work_id":"e7b6b57c-850b-45c5-8be7-172afbc5fb77","year":2018},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:33.880451Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:da9372c7c65105f58ac9916d75bf3f12e7976e18b504d2bfb5b3d7e8ed830b32","observation_id":"374175e6-f212-43ee-bbfa-23c4abe7740b","resolution":{"observed_at":"2026-08-16T12:18:34.497836Z","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":"2026-08-16T12:18:34.481977Z","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","venue":null,"work_id":"15f62298-fe52-4116-b602-74e2bd4ddea9","year":2018},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.025399Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:a6e62e97ec790bbffadd275a68cefa83d29ad7e7c0a1e37c717690bffa62c2c4","observation_id":"e7b0e79d-92f3-425f-940c-a319b242f2c2","resolution":{"observed_at":"2026-08-16T12:18:34.486173Z","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":"2011.09679","last_updated":"2020-11-19T06:03:35Z","snapshot_observed_at":"2026-08-18T04:05:56.979304Z","submitted_at":"2020-11-19T06:03:35Z","title":"Scalable Graph Neural Networks for Heterogeneous Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.09679","snapshot_observed_at":"2026-08-16T12:18:34.057379Z","title":"Scalable Graph Neural Networks for Heterogeneous Graphs","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.057379Z"},"links":{"cited_paper":"/paper/2011.09679","citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:95427e3fa421452db78333651b5541363f4edb63783b5c90a086f4ec05997b99","observation_id":"5ff191e6-2e00-4153-a87d-3cd296c43e8b","resolution":{"observed_at":"2026-08-16T12:18:34.057379Z","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":"2026-08-16T12:18:34.410834Z","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","venue":null,"work_id":"aacf4847-6e6f-4691-8e3e-537002839826","year":2020},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.123531Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:be77aaf2131b244a90bab3765add7cb3a5f02d597bba1568cb0ac313dd064254","observation_id":"0915bcbb-6d58-4786-bd9d-931ce1088133","resolution":{"observed_at":"2026-08-16T12:18:34.473340Z","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":"2026-08-16T12:18:34.391159Z","title":"and Chen, Y","venue":null,"work_id":"e676651e-0402-40fc-98fc-6b99257b18f3","year":2018},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.159388Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:30bf8aa5bea342d44d79774e950e16c47ee8682d3797c21bb683d7f492d69912","observation_id":"5a8b177d-ec94-45cc-a369-1dcd5ae5b87b","resolution":{"observed_at":"2026-08-16T12:18:34.395140Z","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":"2026-08-16T12:18:34.378228Z","title":"Graph Attention Multi-Layer Perceptron","venue":null,"work_id":"bbe4ac4b-0ef6-415a-b98e-b95983b59279","year":2022},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.162717Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:89b877b1332bb49146d86315ea92502ea42d4526f42d1cdf8e945940fb61b259","observation_id":"74f60e6c-b6a5-412e-aea7-5c5d3768c122","resolution":{"observed_at":"2026-08-16T12:18:34.383089Z","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":"1906.01210","last_updated":"2019-06-04T06:01:10Z","snapshot_observed_at":"2026-08-18T04:05:58.076407Z","submitted_at":"2019-06-04T06:01:10Z","title":"Attributed Graph Clustering via Adaptive Graph Convolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.01210","snapshot_observed_at":"2026-08-16T12:18:34.165793Z","title":"Attributed Graph Clustering via Adaptive Graph Convolution","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.165793Z"},"links":{"cited_paper":"/paper/1906.01210","citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:d634a94e70b763e2627a096e5ad697feba73da5791e23f40ac2967e07e7cf055","observation_id":"5abfd239-4079-4cac-a5e7-ec54af4b6154","resolution":{"observed_at":"2026-08-16T12:18:34.165793Z","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":"2026-08-16T12:18:34.364783Z","title":"and Koniusz, P","venue":null,"work_id":"a628cabc-54fa-49a8-b82d-abb4ae9452c8","year":2020},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.170035Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:cd9c004e577bdc56c814dbce64a1472aa8d500e4c54efd902d051112b1dab70c","observation_id":"dc05354b-718c-44e1-8d12-acbc182a0ac4","resolution":{"observed_at":"2026-08-16T12:18:34.369397Z","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":"2026-08-16T12:18:34.290379Z","title":"Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks","venue":null,"work_id":"3630cc7c-a38c-4a2c-b55c-04b483b6dfa1","year":2019},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.173547Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:7f67c2d36c0eb48cfab9157398ba769b5bff991fabb1d7a2cdffb3d4a945cb6f","observation_id":"3d2d71bc-d314-42ce-9557-780247ae9a2d","resolution":{"observed_at":"2026-08-16T12:18:34.356078Z","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":"2026-08-16T12:18:34.177210Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-16T12:18:34.177210Z"},"links":{"citing_paper":"/paper/2504.13266"},"observation_digest":"sha256:fc132efa09b341413c03f8dcdb02ce3fe64f2f39962e81745f82c5a706bd8aac","observation_id":"7f2e4d63-fc37-4e8d-8337-d6005ff33c58","resolution":{"observed_at":"2026-08-16T12:18:34.177210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.13266","last_updated":"2025-04-17T18:20:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T04:04:12.351124Z","submitted_at":"2025-04-17T18:20:40Z","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":40},"total_outbound_references":52},"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 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2504.13266."}