{"as_of":"2026-08-18T13:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:70d7a6f2f3c60674d4bbd25fdbf0b9b7f2699c96e7a0a3fce4b0ddc406499eba","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T17:05:46.879487Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T13:22:32.375169Z","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":"2026-05-25T04:55:23.296689Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.13028","snapshot_observed_at":"2026-08-12T13:22:32.375169Z","title":"P., and Sutherland, D","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.16278","last_updated":"2024-11-25T10:59:25Z","snapshot_observed_at":"2026-08-15T08:30:22.345765Z","submitted_at":"2024-11-25T10:59:25Z","title":"Even Sparser Graph Transformers","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T13:22:32.375169Z"},"links":{"cited_paper":"/paper/2411.13028","citing_paper":"/paper/2411.16278"},"observation_digest":"sha256:258f76817351973eea3f9bff5a31ad4f38aa552c9fe466b825a2870c01fbe488","observation_id":"5c315e0f-6257-48a1-936e-451c64faaca7","resolution":{"observed_at":"2026-08-12T13:22:32.375169Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.13028","snapshot_observed_at":"2026-08-07T15:32:43.545613Z","title":"A theory for compressibility of graph transformers for transductive learning.arXiv preprint arXiv:2411.13028, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.14919","last_updated":"2025-05-20T21:13:23Z","snapshot_observed_at":"2026-08-17T00:21:14.320545Z","submitted_at":"2025-05-20T21:13:23Z","title":"TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:32:43.545613Z"},"links":{"cited_paper":"/paper/2411.13028","citing_paper":"/paper/2505.14919"},"observation_digest":"sha256:5849a09ad2a6aabf2e72e462fb10fe7c914765786491cb965c3533e46f8e23c3","observation_id":"31f77bde-ec7e-40cc-b9af-8444f9176e7d","resolution":{"observed_at":"2026-08-07T15:32:43.545613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"cited_work":{"arxiv_id":"2411.13028","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.13028","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A theory for compressibility of graph transformers for transductive learning.arXiv preprint arXiv:2411.13028, 2024a","venue":null,"work_id":"c22fd6f3-4a75-4dc6-86ca-67af95ecdb33","year":null},"citing_paper":{"arxiv_id":"2605.23753","last_updated":"2026-05-22T15:26:31Z","snapshot_observed_at":"2026-08-13T22:35:49.423722Z","submitted_at":"2026-05-22T15:26:31Z","title":"SeedER: Seed-and-Expand Retrieval from Knowledge Graphs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-25T04:53:52.372584Z"},"links":{"cited_paper":"/paper/2411.13028","citing_paper":"/paper/2605.23753"},"observation_digest":"sha256:446f104500380f552f664a748963274b39bedad2d9d4f4d6b9284a2bb24a2410","observation_id":"88127997-c386-462f-8de5-662ba8b60a38","resolution":{"observed_at":"2026-05-25T04:55:23.299964Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.13028/citation-record","integrity":"/paper/2411.13028/integrity","json":"/paper/2411.13028/citation-record.json","paper":"/paper/2411.13028"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T17:05:47.439071Z","title":null,"venue":null,"work_id":"58894483-1fbb-4a38-a002-29138a7a69ea","year":2018},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.722142Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:e4a08b21fd2725fb96a85ff25f341cbde00f147f021df9f726d3a47b24872c98","observation_id":"726295ea-2664-4513-9055-07a51639c0fe","resolution":{"observed_at":"2026-08-12T17:05:47.442197Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-12T17:05:47.429662Z","title":"and Price, E","venue":null,"work_id":"70ab7503-573d-4a5f-b840-a6b47cf6788d","year":2019},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.726702Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:c261f78e451cf053d755112126dd0c202d91c4b85f69421b374d5a7684f646bd","observation_id":"52c1a057-2c06-4485-996d-b4f9998bb52f","resolution":{"observed_at":"2026-08-12T17:05:47.432645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01232","last_updated":"2024-04-06T23:26:26Z","snapshot_observed_at":"2026-08-16T14:13:29.033361Z","submitted_at":"2024-03-02T15:32:01Z","title":"Polynormer: Polynomial-Expressive Graph Transformer in Linear Time","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01232","snapshot_observed_at":"2026-08-12T17:05:46.730973Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.730973Z"},"links":{"cited_paper":"/paper/2403.01232","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:18fde8a2f470409bf6d09fadce8440087269e32cd1a991c2786e609eff4c9d04","observation_id":"e91b557a-0937-405c-8d96-bb599f087c94","resolution":{"observed_at":"2026-08-12T17:05:46.730973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-12T17:05:46.735015Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.735015Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:377f1bf1b3ceeaff99801af130bf5b0113750d2776b2799b302bc60af30a75f4","observation_id":"f73ad74d-0324-4d8c-9471-d8dc17ee1c93","resolution":{"observed_at":"2026-08-12T17:05:46.735015Z","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":"2026-08-12T17:05:47.419594Z","title":null,"venue":null,"work_id":"19b252fd-eef9-4a67-be0e-80b4fa39cc14","year":2021},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.739037Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:bea672614afd9fb4d9f2f48f5447c037f484e02062fa9f253da87e03183aa17d","observation_id":"4e51d70c-6d3e-4516-a0cd-074da7aa8a95","resolution":{"observed_at":"2026-08-12T17:05:47.423019Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-12T17:05:46.742691Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.742691Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:4504973022dbe454b98a6d5ba3ba6354ae9a0d3a2a9097ae8fa8bc1227649431","observation_id":"f6f43ea0-016f-48f1-b793-0a24bb15107c","resolution":{"observed_at":"2026-08-12T17:05:46.742691Z","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":"2026-08-12T17:05:46.746635Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.746635Z"},"links":{"cited_paper":"/paper/2012.09699","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:82ac306c43b1f6d47f9a8165d671494d2a222886fe1be9fbf55e172a007c1422","observation_id":"5d00ffff-eebe-47d4-926a-69da9ad70a28","resolution":{"observed_at":"2026-08-12T17:05:46.746635Z","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":"2026-08-12T17:05:46.750020Z","title":"and Lenssen, J","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.750020Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:21937fd24a0afde58bf02a42909bc9fb718bf60b1059f037db80dd18a075891d","observation_id":"e863078e-2048-4497-910b-04a1e2071fab","resolution":{"observed_at":"2026-08-12T17:05:46.750020Z","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":"2026-08-12T17:05:46.753611Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.753611Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:1621c03ed2adb5db0d8405777da94344cc0d982ee6614c95fd1cc81ab5d35e6f","observation_id":"fa458707-0ece-49c8-b58e-650e2b6a952d","resolution":{"observed_at":"2026-08-12T17:05:46.753611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.09430","last_updated":"2021-10-20T22:40:40Z","snapshot_observed_at":"2026-08-16T18:38:23.179403Z","submitted_at":"2021-03-17T04:08:03Z","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.09430","snapshot_observed_at":"2026-08-12T17:05:46.756901Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.756901Z"},"links":{"cited_paper":"/paper/2103.09430","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:6b0d224701685091254762ea3de037214af2dc4c6730e29eedfdaea9bc77dc53","observation_id":"cb047a84-49c7-4002-a96e-bb93e93e5d87","resolution":{"observed_at":"2026-08-12T17:05:46.756901Z","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":"2026-08-12T17:05:46.760621Z","title":null,"venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.760621Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:6e8b073b84367446b0426fc9b291ebf293cf96fbb3478ca25acd6be08a87c66d","observation_id":"413ba3b7-3668-46e7-aab6-1a8612d9e95f","resolution":{"observed_at":"2026-08-12T17:05:46.760621Z","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":"2026-08-12T17:05:46.764764Z","title":"and Shakhnarovich, G","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.764764Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:2c28fc98dc1b506c2aad1d8a75cc8918529bdc99d1f07a0a897399672bca1b78","observation_id":"4686c4c3-9a4d-4883-808b-db285a305924","resolution":{"observed_at":"2026-08-12T17:05:46.764764Z","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":"2026-08-12T17:05:46.767940Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.767940Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:069085764d289d76b36f0e0624828ff4bf8b46b3bd0ba112702aa26f5eded86c","observation_id":"28ca2c38-86a2-4b8e-9b0c-7ff707cf9de1","resolution":{"observed_at":"2026-08-12T17:05:46.767940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03893","last_updated":"2021-10-27T16:09:50Z","snapshot_observed_at":"2026-08-16T18:18:58.106636Z","submitted_at":"2021-06-07T18:11:11Z","title":"Rethinking Graph Transformers with Spectral Attention","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03893","snapshot_observed_at":"2026-08-12T17:05:46.771587Z","title":"L., L \\'e tourneau, V., and Tossou, P","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.771587Z"},"links":{"cited_paper":"/paper/2106.03893","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:cf14b644b3248ff0655ff0e3f0a083d9a771794ff1d9aaecef380358e686bd7e","observation_id":"4552ca4e-142a-4712-a62f-0045680b330d","resolution":{"observed_at":"2026-08-12T17:05:46.771587Z","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":"2026-08-12T17:05:47.383833Z","title":null,"venue":null,"work_id":"f9bb384d-e9df-4570-a056-1f287e78bf6a","year":2014},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.774929Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:a04ae082e35c1729d2dcdb8d055201b733037bddfd11122ad5316e998f608ba3","observation_id":"f4192465-96b8-453f-b989-adbf9707cb5a","resolution":{"observed_at":"2026-08-12T17:05:47.387362Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03764","last_updated":"2021-06-08T10:02:26Z","snapshot_observed_at":"2026-08-16T18:19:01.288355Z","submitted_at":"2021-06-07T16:30:28Z","title":"On the Expressive Power of Self-Attention Matrices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03764","snapshot_observed_at":"2026-08-12T17:05:46.778144Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.778144Z"},"links":{"cited_paper":"/paper/2106.03764","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:1ff4f22fbb0a79a380b959ed9d0bdcc11e796480bf48cde3e8bf7c97427210e9","observation_id":"e438c3b7-fe55-4df0-8a73-d28372071b9c","resolution":{"observed_at":"2026-08-12T17:05:46.778144Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.07321","last_updated":"2023-06-22T15:00:07Z","snapshot_observed_at":"2026-08-16T17:06:47.205346Z","submitted_at":"2022-04-15T04:02:06Z","title":"Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.07321","snapshot_observed_at":"2026-08-12T17:05:46.782138Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.782138Z"},"links":{"cited_paper":"/paper/2204.07321","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:744e08163dd05e12bde348ec28451c0e57e80eeed9724682f660ae5dde0e7b4b","observation_id":"87d6db91-d27a-4c05-bee3-26dfb9d01d8b","resolution":{"observed_at":"2026-08-12T17:05:46.782138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-08-12T17:05:46.785980Z","title":"and Hutter, F","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.785980Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:0f51bc397dd9a9f7471bf49c9febbe774fec5b05822bc717ce7ad9f84b2ea69d","observation_id":"16781d6d-d5b5-42e8-b749-0c9c041c715e","resolution":{"observed_at":"2026-08-12T17:05:46.785980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-12T17:05:46.790234Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.790234Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:8ed49ff01e5ed1b5de53d3b3aded5110d35059006866f4523f7025b311716058","observation_id":"2543d69a-b214-440a-9901-7572b5445306","resolution":{"observed_at":"2026-08-12T17:05:46.790234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.03199","last_updated":"2020-01-28T13:24:15Z","snapshot_observed_at":"2026-08-14T16:08:11.103528Z","submitted_at":"2019-07-06T22:26:17Z","title":"What graph neural networks cannot learn: depth vs width","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.03199","snapshot_observed_at":"2026-08-12T17:05:46.794392Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.794392Z"},"links":{"cited_paper":"/paper/1907.03199","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:21db30ec4b8576913d2747a001c0b77a760ac02c499e1180a2b7a4e9e4ed809c","observation_id":"a4e2f6c4-5333-4641-9b95-9622595d5936","resolution":{"observed_at":"2026-08-12T17:05:46.794392Z","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":"2026-08-12T17:05:47.373400Z","title":null,"venue":null,"work_id":"bba997ed-09f1-42da-9e0b-046af50748f8","year":2015},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.798219Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:472e349e9557dbd6ed04ad7ddf8d261b172addde78c7c5e612bbe8b75671f3c6","observation_id":"d60be399-b499-4561-9b87-50d7ac2cc23e","resolution":{"observed_at":"2026-08-12T17:05:47.377017Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.04181","last_updated":"2024-03-28T19:35:01Z","snapshot_observed_at":"2026-08-16T15:56:46.382341Z","submitted_at":"2023-02-08T16:40:11Z","title":"Attending to Graph Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.04181","snapshot_observed_at":"2026-08-12T17:05:46.801789Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.801789Z"},"links":{"cited_paper":"/paper/2302.04181","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:b866d9f1ba4a1a7df0327eb0194323b4fb0f898be481bdd76ce90fead9bc9079","observation_id":"7aaaadd8-bd1c-4dde-916c-1a306ae61845","resolution":{"observed_at":"2026-08-12T17:05:46.801789Z","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":"2026-08-12T17:05:47.362655Z","title":"P., and Yasuda, T","venue":null,"work_id":"7475d881-f06f-411c-a917-5c12ef7f3ad1","year":2022},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.805364Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:14ceefe47b3efd23fa1f0fcd842b24827dffa07f42421b2f28810a2e2486921d","observation_id":"44ab4783-73a8-4fd2-a5cf-bd6ce32b8bc4","resolution":{"observed_at":"2026-08-12T17:05:47.366207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-12T17:05:46.808690Z","title":"and Maehara, T","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.808690Z"},"links":{"cited_paper":"/paper/1905.09550","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:541bcbd521802a6411228103e6ecea75e8893ad1b5e8945cc58c6d310c240d98","observation_id":"66f46084-30e1-48ae-afb0-311c4b39305a","resolution":{"observed_at":"2026-08-12T17:05:46.808690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10947","last_updated":"2021-01-06T13:32:14Z","snapshot_observed_at":"2026-08-17T02:06:18.538217Z","submitted_at":"2019-05-27T02:59:06Z","title":"Graph Neural Networks Exponentially Lose Expressive Power for Node Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.10947","snapshot_observed_at":"2026-08-12T17:05:46.812455Z","title":"and Suzuki, T","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.812455Z"},"links":{"cited_paper":"/paper/1905.10947","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:e0bc747da1c39b07f4253c70354f13faf1298678795086d8b58b5351f9ed1f16","observation_id":"dcc4bf8b-7030-482f-94f3-817a642cc571","resolution":{"observed_at":"2026-08-12T17:05:46.812455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11640","last_updated":"2024-03-02T21:17:13Z","snapshot_observed_at":"2026-08-16T15:53:25.866662Z","submitted_at":"2023-02-22T20:32:59Z","title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11640","snapshot_observed_at":"2026-08-12T17:05:46.816309Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.816309Z"},"links":{"cited_paper":"/paper/2302.11640","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:6334c32510d1877532e3c17de46ba26a8595a6daf4e160488e7547a910fb2860","observation_id":"07605304-cfbb-4681-bcb1-6bbd7a12e925","resolution":{"observed_at":"2026-08-12T17:05:46.816309Z","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":"2026-08-12T17:05:46.820314Z","title":"P., Luu, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.820314Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:564d36a928ed028c6cdb5fcc4aa1684b8aad48c8e2a988b2d5032cd2e1579306","observation_id":"88b9c471-4d58-41e0-941e-5aad642bf858","resolution":{"observed_at":"2026-08-12T17:05:46.820314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11504","last_updated":"2024-12-09T14:03:33Z","snapshot_observed_at":"2026-08-16T13:17:42.742901Z","submitted_at":"2024-09-17T19:16:03Z","title":"Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11504","snapshot_observed_at":"2026-08-12T17:05:46.823721Z","title":"M., and Liebig, T","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.823721Z"},"links":{"cited_paper":"/paper/2409.11504","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:2ab255b7f21510c61c21482c8c1646512191fde04cc45636a901edf73417a832","observation_id":"27a6a294-9f3a-42b6-8f9c-34fb8129631a","resolution":{"observed_at":"2026-08-12T17:05:46.823721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.18512","last_updated":"2024-05-28T18:31:14Z","snapshot_observed_at":"2026-08-16T13:48:28.623355Z","submitted_at":"2024-05-28T18:31:14Z","title":"Understanding Transformer Reasoning Capabilities via Graph Algorithms","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.18512","snapshot_observed_at":"2026-08-12T17:05:46.827097Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.827097Z"},"links":{"cited_paper":"/paper/2405.18512","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:4bb04bf6a0ee8336536ec4ab0309cda218ae140299cb9f80e3ca10bb58c8d8a1","observation_id":"91ddec12-cd19-477e-a5da-070f062534e9","resolution":{"observed_at":"2026-08-12T17:05:46.827097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09268","last_updated":"2024-02-14T15:54:55Z","snapshot_observed_at":"2026-08-16T14:18:36.667442Z","submitted_at":"2024-02-14T15:54:55Z","title":"Transformers, parallel computation, and logarithmic depth","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09268","snapshot_observed_at":"2026-08-12T17:05:46.830380Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.830380Z"},"links":{"cited_paper":"/paper/2402.09268","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:61204d9bac9acf3a32ac6711b973d5af61d37cd62d09e12a6f388d3aa9c6c6c3","observation_id":"ab793125-4774-4c0d-be2a-16eed88b2c64","resolution":{"observed_at":"2026-08-12T17:05:46.830380Z","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":"2026-08-12T17:05:47.344927Z","title":"J., and Telgarsky, M","venue":null,"work_id":"e125a476-266d-4363-a467-12b67ed1f295","year":2024},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.833579Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:58d8e3caab3c66970780a4cc7f97a15c7464fbc287acb532213c130d42749a9e","observation_id":"392fca21-a569-45bb-a378-152e09183ea2","resolution":{"observed_at":"2026-08-12T17:05:47.348450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05868","last_updated":"2019-06-18T13:15:39Z","snapshot_observed_at":"2026-08-14T17:59:20.424546Z","submitted_at":"2018-11-14T15:53:19Z","title":"Pitfalls of Graph Neural Network Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.05868","snapshot_observed_at":"2026-08-12T17:05:46.836867Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.836867Z"},"links":{"cited_paper":"/paper/1811.05868","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:598a45b71700068005128a0dccb85e837de1ebfa6cbf7bf956217d4940a75674","observation_id":"99b30cdf-42a9-448a-800f-7a0bff882693","resolution":{"observed_at":"2026-08-12T17:05:46.836867Z","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":"2026-08-12T17:05:47.334220Z","title":null,"venue":null,"work_id":"f63a78cb-5c1c-4a88-a8ff-7e72eb9dc1c4","year":2024},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.840225Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:13a68e525f4fdc721c8d1fc33a026f8b4f9e7cdc6c04fbda2ecbe0d0fe5b6ee4","observation_id":"ec5c4046-b428-4cfa-aac7-fc78a86e5368","resolution":{"observed_at":"2026-08-12T17:05:47.337846Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-12T17:05:46.843474Z","title":"J., and Sinop, A","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.843474Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:cbcc2cfc0bc939db7852e33ad17f67dab7b5f1f151c650b4c879dd836564e03d","observation_id":"8629bff1-af7f-4c28-a773-2cd4d9611515","resolution":{"observed_at":"2026-08-12T17:05:46.843474Z","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":"2026-08-12T17:05:46.846880Z","title":"N., Kaiser, L., and Polosukhin, I","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.846880Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:53a0cb178a0ee621924a85caa891f1db189c15ad21bbfe652b4ebca83b9f40b0","observation_id":"dd8c1e6b-7912-440a-ac74-bde8af4158d6","resolution":{"observed_at":"2026-08-12T17:05:46.846880Z","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":"2026-08-12T17:05:46.849929Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.849929Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:b37c1456596002e960da418e05cbdf2c6b020f2f2b430ce9edeae7c17e60075b","observation_id":"78a4aa94-d3d7-476c-a0e3-96fa5f679c4e","resolution":{"observed_at":"2026-08-12T17:05:46.849929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.01315","last_updated":"2020-08-25T15:46:13Z","snapshot_observed_at":"2026-08-18T10:54:34.717319Z","submitted_at":"2019-09-03T17:10:28Z","title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.01315","snapshot_observed_at":"2026-08-12T17:05:46.852927Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.852927Z"},"links":{"cited_paper":"/paper/1909.01315","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:53d356b90485bff3ae59bee0212685091184d87b70eceb60a66b2cf317aad34e","observation_id":"d3126caa-14a9-4315-930f-84b33ebbbf4a","resolution":{"observed_at":"2026-08-12T17:05:46.852927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04768","last_updated":"2020-06-14T08:15:54Z","snapshot_observed_at":"2026-07-06T09:27:03.809621Z","submitted_at":"2020-06-08T17:37:52Z","title":"Linformer: Self-Attention with Linear Complexity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04768","snapshot_observed_at":"2026-08-12T17:05:46.856049Z","title":"Z., Khabsa, M., Fang, H., and Ma, H","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.856049Z"},"links":{"cited_paper":"/paper/2006.04768","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:442131ea330dff03df23b548c82d6111eb8e85be49e3b212bf53ea9fbf961c27","observation_id":"952657f3-3394-4ea8-b6da-6626f01fb363","resolution":{"observed_at":"2026-08-12T17:05:46.856049Z","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":"2026-08-12T17:05:47.301691Z","title":null,"venue":null,"work_id":"e38a3fe0-c7d6-4944-9b55-fe64f7be844c","year":2014},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.859209Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:ab2bc921d9c120fcdcd21d5e049e2e1bce8279839971df4d2420e4697ecf038f","observation_id":"bf6274b9-93cc-4cc7-a559-7ad564acd163","resolution":{"observed_at":"2026-08-12T17:05:47.307089Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-12T17:05:46.861996Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.861996Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:32ec075ce4ca6912d19a13615ece12acdc6a5047750a06baaaa8367bc0f23f57","observation_id":"35be007d-a992-4bb8-8cfa-2605db5f9718","resolution":{"observed_at":"2026-08-12T17:05:46.861996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.09474","last_updated":"2023-05-28T09:19:49Z","snapshot_observed_at":"2026-08-16T16:00:44.202084Z","submitted_at":"2023-01-23T15:18:54Z","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.09474","snapshot_observed_at":"2026-08-12T17:05:46.865095Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.865095Z"},"links":{"cited_paper":"/paper/2301.09474","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:923451e2df08a56f021ceb88870ddbec1597c2a20774571b11f0db38dba7eb73","observation_id":"98f95dc5-a8b8-42b8-8da6-f00a21135288","resolution":{"observed_at":"2026-08-12T17:05:46.865095Z","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":"2026-08-12T17:05:46.868519Z","title":"P., and Yan, J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.868519Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:ed87f2d184f040dac95f7c2a1d3a982df6cf6c82602dcc6ae0992f47320e3cfc","observation_id":"ff8fc27c-0378-462a-b836-fb3740e6f2fd","resolution":{"observed_at":"2026-08-12T17:05:46.868519Z","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":"2026-08-12T17:05:46.872287Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.872287Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:f8c64503ae4915ee387f122f91542532dddc77c5313b7b3793010e161d7a9112","observation_id":"64b8f0f2-adde-4ac1-a883-54605fe4aeea","resolution":{"observed_at":"2026-08-12T17:05:46.872287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.05234","last_updated":"2021-11-24T01:39:16Z","snapshot_observed_at":"2026-08-18T11:13:06.706112Z","submitted_at":"2021-06-09T17:18:52Z","title":"Do Transformers Really Perform Bad for Graph Representation?","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.05234","snapshot_observed_at":"2026-08-12T17:05:46.875599Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.875599Z"},"links":{"cited_paper":"/paper/2106.05234","citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:6189d5dac10c340b6531a855083cfd2bafd40721253d981137f6efeef91c1890","observation_id":"7589b553-6c72-457e-a1ea-30c121dff50b","resolution":{"observed_at":"2026-08-12T17:05:46.875599Z","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":"2026-08-12T17:05:46.879487Z","title":"A., Ainslie, J., Alberti, C., Ontanon, S., Pham, P., Ravula, A., Wang, Q., Yang, L., et al","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-12T17:05:46.879487Z"},"links":{"citing_paper":"/paper/2411.13028"},"observation_digest":"sha256:80b19f928b23c193bc552c8e11d95385350ea3e8969376e27b1f26430309add3","observation_id":"38212b63-321e-40c3-9dba-aef51f58b573","resolution":{"observed_at":"2026-08-12T17:05:46.879487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.13028","last_updated":"2024-11-20T04:20:17Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T17:41:41.193965Z","submitted_at":"2024-11-20T04:20:17Z","title":"A Theory for Compressibility of Graph Transformers for Transductive Learning"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":42,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":45},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 3 inbound Pith citation observations for arXiv:2411.13028."}