{"as_of":"2026-08-15T07:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:624953bdc2f8c42fd75abf4965c17eea67ca14328f6b0af40ea16697ce95dec9","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:24:43.215903Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2608.09031/citation-record","integrity":"/paper/2608.09031/integrity","json":"/paper/2608.09031/citation-record.json","paper":"/paper/2608.09031"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:24:48.111902Z","title":"MixHop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","venue":null,"work_id":"b7c80aac-cc6e-4e50-8deb-655a9c70697c","year":2019},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:41.853064Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:55def9016b13acf7ac5be0633b0d1e3fa0c9c88a1b44a84bc3bb3442de40b995","observation_id":"e5e4613c-3764-433b-bfaf-49758d26b625","resolution":{"observed_at":"2026-08-14T04:24:48.134870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:48.038934Z","title":"On the bottleneck of graph neural networks and its practical implications","venue":null,"work_id":"3cda49a2-4347-4d21-aae2-a3a320b7cf33","year":2021},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:41.894864Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:296230e7ad5d2a7168f07f68224ffae2391e8652d9977b9c445e516dd4faf8d6","observation_id":"12d742e8-7f0b-4851-b3b8-0e2020fd00be","resolution":{"observed_at":"2026-08-14T04:24:48.047688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.934882Z","title":"On vanishing gradients, over- smoothing, and over-squashing in gnns: Bridging recurrent and graph learning.Advances in Neural Information Processing Systems, 38:74356–74393, 2026","venue":null,"work_id":"afef0bb0-6ad2-4ea3-90f7-3a62d549cd44","year":2026},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:41.907485Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:a2a35a2e57f1bde087adb2347d5bd92f03e07eb86f666deb9ee6bc8fa53b2377","observation_id":"b0d1cd9e-4cba-4a03-96ae-1a20cfbf956e","resolution":{"observed_at":"2026-08-14T04:24:47.985013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08678","last_updated":"2024-02-19T18:53:13Z","snapshot_observed_at":"2026-08-13T04:19:36.374757Z","submitted_at":"2024-02-13T18:58:17Z","title":"Graph Mamba: Towards Learning on Graphs with State Space Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08678","snapshot_observed_at":"2026-08-14T04:24:41.918525Z","title":"Graph mamba: Towards learning on graphs with state space models.arXiv preprint arXiv:2402.08678, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:41.918525Z"},"links":{"cited_paper":"/paper/2402.08678","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:5cd81a6bcfb1cc7f61ae84cd3b559c63f85de2b8ef00ae80ae6451c6dfbd3e83","observation_id":"32b0d751-b1ef-495a-8534-06a64517a1b2","resolution":{"observed_at":"2026-08-14T04:24:41.918525Z","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":"2026-08-14T04:24:47.849555Z","title":"Best of both worlds: Advantages of hybrid graph sequence models","venue":null,"work_id":"111f05c1-f1b7-4589-968e-e72c2f2fdee1","year":2025},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:41.947251Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:713b1be8851fa1a676848af452f5652e5d36cf04760d20152ddccaa11521ce1d","observation_id":"218d086d-2eeb-4b8b-a4a7-1849d53783ef","resolution":{"observed_at":"2026-08-14T04:24:47.858166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/focs.2015.86","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:24:43.378513Z","title":"Non-backtracking spectrum of random graphs: Community detection and non-regular ramanujan graphs","venue":null,"work_id":"31242a2c-1d60-4e32-81d7-b2dfb6d572f5","year":2015},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:41.981668Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:2b1ee9dc348cc1b0ebafeef19fa971e1b6696019ddbaeb0c8c94b2fef7746a72","observation_id":"686977ea-da7b-4370-99c3-72be226195f3","resolution":{"observed_at":"2026-08-14T04:24:43.390036Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.802030Z","title":"GNN-FiLM: Graph neural networks with feature-wise linear modulation","venue":null,"work_id":"0484678a-22df-42d8-9035-707c20504d12","year":2020},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.013978Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:24f8c62abf4415242e28e4379b2fdf435f4a3b6ff02cd9333a9d968b8fe07b11","observation_id":"496e49db-2257-464d-8b29-5eb508cdb0a7","resolution":{"observed_at":"2026-08-14T04:24:47.824384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18728","last_updated":"2026-05-26T08:20:42Z","snapshot_observed_at":"2026-08-14T09:58:06.733761Z","submitted_at":"2025-05-24T14:53:07Z","title":"Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.18728","snapshot_observed_at":"2026-08-14T04:24:42.034756Z","title":"Message-passing state-space models: Improving graph learning with modern sequence modeling.arXiv preprint arXiv:2505.18728, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.034756Z"},"links":{"cited_paper":"/paper/2505.18728","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:5014c730bbd69a57ebb3318e66febf721a1636e70033af31144ffe3ef958c9a9","observation_id":"4335ca89-a3b0-4e3c-8c4a-80a0d8d61e12","resolution":{"observed_at":"2026-08-14T04:24:42.034756Z","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":"2026-08-14T04:24:47.696906Z","title":"Simple and deep graph convolutional networks","venue":null,"work_id":"276b41e5-a431-4f31-b4da-ab16b754ab70","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.072039Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:becfa4a43e3404a3d8cc4171f93ec017b043a0fab610b71b731c7ad7ec219e31","observation_id":"61cdba44-b528-4e02-913c-5ef83cd27ba3","resolution":{"observed_at":"2026-08-14T04:24:47.726531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.574745Z","title":"Adaptive universal generalized PageRank graph neural network","venue":null,"work_id":"234b68ce-d7af-4a5f-a0a5-245ac5673d45","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.104140Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:ced92c52d9684dcd20573df644f338384b23094d12fe91e7fb242a17493925c5","observation_id":"195cf970-cfe5-45c4-8371-2bf83db8d8f4","resolution":{"observed_at":"2026-08-14T04:24:47.604580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.351262Z","title":"Chung.Spectral Graph Theory","venue":null,"work_id":"610a5bee-82a8-4f6d-a543-8fb56247bcab","year":1997},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.139543Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:21c3dd5f0be83427f145cf9a71018aae7ca6eb223f04bacf1a4a3d5e38ecc86d","observation_id":"a4030367-a2fe-4105-8948-f53b1f382c02","resolution":{"observed_at":"2026-08-14T04:24:47.363222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.296850Z","title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","venue":null,"work_id":"59f1953c-02c9-41d7-ae8f-6888e0bc1062","year":2024},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.159746Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:fbb40fb04927c8dc63ae29d2b4b1c85dad7084519c3c3ad26d839d68eee6aae2","observation_id":"4f4165fd-f86a-4d64-97f2-88f570f2e519","resolution":{"observed_at":"2026-08-14T04:24:47.321259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.178100Z","title":"Convolutional neural networks on graphs with fast localized spectral filtering","venue":null,"work_id":"509c9758-d7b7-468c-a827-00546e115f78","year":2016},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.185203Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:b7ce898c466eab491c79dff0ee3cec0dcba737260e1b3a76988a2ba621271ce7","observation_id":"a159441d-fd1b-4871-ad23-54f74b4d8cb8","resolution":{"observed_at":"2026-08-14T04:24:47.204973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.131599Z","title":"Konstantin Rusch, Michael M","venue":null,"work_id":"c5747f80-66a8-425e-aadd-8b9500972175","year":2024},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.208622Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:805c8f5b4c7d31a11d82dfcd4f2e7636a500f6e81184c966f4321a0bf8b08f51","observation_id":"2f6b04f1-c4c9-46ce-9fab-e8bb2f904241","resolution":{"observed_at":"2026-08-14T04:24:47.142206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.020109Z","title":"Long range graph benchmark","venue":null,"work_id":"da3c1c6d-73f9-4700-afdd-cadd78f9ee03","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.244751Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:fb89894a7f52414344825bc3bfbb12a945d1d3afb17bf2dae6a8720f85659640","observation_id":"246dad70-d6e2-4a10-9032-1b8080b567e2","resolution":{"observed_at":"2026-08-14T04:24:47.054746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.11198","last_updated":"2020-11-03T19:20:22Z","snapshot_observed_at":"2026-08-13T22:55:24.578021Z","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":"2026-08-14T04:24:42.259239Z","title":"Bronstein, and Federico Monti","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.259239Z"},"links":{"cited_paper":"/paper/2004.11198","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:4ae8faec8d0a2c17315e2c52742d9c7e43c15b19a7cb136b0d39ce32db56345e","observation_id":"3dfbbbf5-8e7e-464a-ade6-e034112ab562","resolution":{"observed_at":"2026-08-14T04:24:42.259239Z","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":"2026-08-14T04:24:46.741691Z","title":"Predict then propagate: Graph neural networks meet personalized PageRank","venue":null,"work_id":"7e95855d-c40c-42f9-8bd7-2de0033327a2","year":2019},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.269495Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:db03804131a1232ff79a3289897297efd72be76ec21a5ec34a712e8901a194a1","observation_id":"c58a9052-cdca-4038-889c-5dcc95a5a28a","resolution":{"observed_at":"2026-08-14T04:24:46.794842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:46.666840Z","title":"Schoenholz, Patrick F","venue":null,"work_id":"11d45929-0a3a-4c1e-b728-a51e5a1065a0","year":2017},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.278723Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:95209aeadcda76248a6240a9b58c405447234547c2e1007fb85b623c26c0064c","observation_id":"e480bea8-87d4-42aa-8c47-89772386e18f","resolution":{"observed_at":"2026-08-14T04:24:46.675388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:46.569192Z","title":"Mamba: Linear-time sequence modeling with selective state spaces","venue":null,"work_id":"4d037957-6be8-47e0-bf06-8fe1840b6d07","year":2024},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.291292Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:2194c05cd827455c6d88e4652c26f5dc057e0a1049e4582e79e2bd909296ca1f","observation_id":"8c6f2fcb-5ed5-4f04-941c-ba8e7a5b56e5","resolution":{"observed_at":"2026-08-14T04:24:46.604866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.00396","last_updated":"2022-08-05T17:54:38Z","snapshot_observed_at":"2026-08-14T01:02:41.198730Z","submitted_at":"2021-10-31T03:32:18Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.00396","snapshot_observed_at":"2026-08-14T04:24:42.308748Z","title":"Efficiently modeling long sequences with structured state spaces.arXiv preprint arXiv:2111.00396, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.308748Z"},"links":{"cited_paper":"/paper/2111.00396","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:b2c0224cffdc14a39883a9dedad385199fe622388972aea6193b114b1d20bcde","observation_id":"1ebb6082-6b6a-4c8d-8db2-a8833a376bcc","resolution":{"observed_at":"2026-08-14T04:24:42.308748Z","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":"2026-08-14T04:24:46.515131Z","title":"Bronstein, and Francesco Di Giovanni","venue":null,"work_id":"5417fb4b-cc54-4ac1-83c8-30283f330252","year":2023},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.316825Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:9ca2764aabd46c7f59a7025d172197dbcdecaa05711dcef1709f2c5cbcdbc329","observation_id":"eab1f8ad-ff3c-4b64-a5a9-cf3b92d477cc","resolution":{"observed_at":"2026-08-14T04:24:46.538156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:46.417019Z","title":"Dai, and Quoc V","venue":null,"work_id":"f5420d64-2e99-44ee-82b3-2d31e39ba4c8","year":2017},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.323426Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:adddc0e0a1129fae045d4e6baf69bc89ea957bae92ccfdc9683b8e349808b3df","observation_id":"20c604f8-7d0e-4b21-b93f-0b51d0b7541c","resolution":{"observed_at":"2026-08-14T04:24:46.436470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:46.343319Z","title":"Hamilton, Rex Ying, and Jure Leskovec","venue":null,"work_id":"0d098eaf-517b-429d-84ad-818e9d626aac","year":2017},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.354762Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:e575b12fb288026381dce32c0b73ae59750c3abc8a8ace3e270e50f9b9d3f4ec","observation_id":"53a55628-748c-483e-8951-7e37b6e8f4ec","resolution":{"observed_at":"2026-08-14T04:24:46.380595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:46.282887Z","title":"Zeta functions of finite graphs and representations of p-adic groups","venue":null,"work_id":"e6d8bb2a-62c2-4ae8-adbd-b80fe50e48ae","year":1989},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.404754Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:e5258aae2c4a6e9c9001f0ecfe8b66f9e69d2548d7803d461e0821ff47955fd9","observation_id":"6a15d453-344d-488b-9c45-7eca142b4c92","resolution":{"observed_at":"2026-08-14T04:24:46.290732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:46.200471Z","title":"BernNet: Learning arbitrary graph spectral filters via bernstein approximation","venue":null,"work_id":"e3620f0d-0214-4f12-86d7-12158a4328b5","year":2021},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.431615Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:3c706faaef8ecffc73bb93a69695d900123d11335fd64d83ede9df87f3e830f5","observation_id":"a5d3366d-41c8-4e45-84d4-78f3fd4b9a6a","resolution":{"observed_at":"2026-08-14T04:24:46.216956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05815","last_updated":"2024-10-04T08:46:03Z","snapshot_observed_at":"2026-08-12T23:46:58.105397Z","submitted_at":"2024-06-09T15:03:36Z","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.05815","snapshot_observed_at":"2026-08-14T04:24:42.436353Z","title":"What can we learn from state space models for machine learning on graphs?arXiv preprint arXiv:2406.05815, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.436353Z"},"links":{"cited_paper":"/paper/2406.05815","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:463048a19b9893c7eca355a9ded957904bbafcf99fbf871d245748c0b70c71b8","observation_id":"61e09ef5-7158-45fd-b487-58bd3a2c3f8b","resolution":{"observed_at":"2026-08-14T04:24:42.436353Z","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":"2026-08-14T04:24:46.152445Z","title":"Banerjee, and Guido Montúfar","venue":null,"work_id":"4526ac48-5a6f-4f1d-9f40-4662bdbdda68","year":2023},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.453170Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:f1383cccd2a371611595787d1eb9ce2a4f9e2b32dbf7b0ae4338c431ca5aaede","observation_id":"aa0d0ea1-a203-4b8c-b136-6b39591e9b6c","resolution":{"observed_at":"2026-08-14T04:24:46.158235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01214","last_updated":"2025-03-05T07:02:28Z","snapshot_observed_at":"2026-08-12T23:31:21.441388Z","submitted_at":"2024-07-01T11:59:59Z","title":"Revisiting Random Walks for Learning on Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01214","snapshot_observed_at":"2026-08-14T04:24:42.494754Z","title":"Revisiting random walks for learning on graphs.arXiv preprint arXiv:2407.01214, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.494754Z"},"links":{"cited_paper":"/paper/2407.01214","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:d6ca08058ca22139528737806656bcb74ca6889c2f053a2a791d4ec78edca966","observation_id":"bf43c3da-9435-461a-9269-ca7842d15a35","resolution":{"observed_at":"2026-08-14T04:24:42.494754Z","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":"2026-08-14T04:24:46.046913Z","title":"Kipf and Max Welling","venue":null,"work_id":"f31f558e-d5b8-42d3-b372-eba882f8a3ae","year":2017},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.542329Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:41795d424612f18df5a9b6a26ef43838c0d2a6be980dc3f07e845321712b5594","observation_id":"ff3b7279-e67e-4807-acbc-7aecfcd1ef82","resolution":{"observed_at":"2026-08-14T04:24:46.070261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:46.005578Z","title":"Diffusion im- proves graph learning","venue":null,"work_id":"27c832cd-62c2-4e2e-a3af-767a455e860a","year":2019},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.591531Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:7abeb3cdd1d192a206f85bb9116fe6547849d7c995b4acd7713fa136a733f6d2","observation_id":"200ac0de-4b80-4780-b1af-3e364065eb0d","resolution":{"observed_at":"2026-08-14T04:24:46.034773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.897258Z","title":"Hamilton, Vincent Létourneau, and Prudencio Tossou","venue":null,"work_id":"57ab7f2f-cc85-4a12-ac4c-4dab4b69421a","year":2021},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.644759Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:6f7471d17fec451fc445e955ec3e78271dd396b1a5a336744cf173dcfb61ac71","observation_id":"58c6dfc1-c92c-4952-a4da-fe38e5ad97e9","resolution":{"observed_at":"2026-08-14T04:24:45.932074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:42.688966Z","title":"Spectral redemption in clustering sparse networks.Proceedings of the National Academy of Sciences, 110(52):20935–20940, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.688966Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:3d6e54262ac3b8769c3e953bdad7007f22fea77345a2462e8d6353d91e35239d","observation_id":"a37dd2e5-5680-463e-a779-66a21e18092f","resolution":{"observed_at":"2026-08-14T04:24:42.688966Z","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":"2026-08-14T04:24:45.844746Z","title":"Kosiorek, Seungjin Choi, and Yee Whye Teh","venue":null,"work_id":"c03da15c-195b-44f4-988d-6c008672dcfb","year":2019},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.724759Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:5d7d7f1f5292164bf3a91ee016396d96d35dc325a31470c55d3a3fa2c6624cb1","observation_id":"35eea304-dc35-4819-8e1e-83106a85ecec","resolution":{"observed_at":"2026-08-14T04:24:45.851176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.768762Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":"ee04fa71-b9dc-4020-987e-cdddff65de12","year":2018},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.752694Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:50dc0bb9e5820c9fef63e1f7b14c96daee4def0dab8999b78a65a047d078ab0e","observation_id":"5e4007ec-5628-418f-a170-5c97432e855d","resolution":{"observed_at":"2026-08-14T04:24:45.779411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:42.777207Z","title":"Towards deeper graph neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.777207Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:f42eaa7f02b2c9893fcea178d6c9efa0ef52703b00da3ec961e53d955439f8b3","observation_id":"e9eb827b-dbef-4fb0-8a16-b901186650d6","resolution":{"observed_at":"2026-08-14T04:24:42.777207Z","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":"2026-08-14T04:24:45.722458Z","title":"LRIM: a physics-based benchmark for provably evaluating long-range capabilities in graph learning","venue":null,"work_id":"266377c9-0242-4a43-b251-3c76fd2d8a30","year":2026},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.794748Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:a1cfbf0da112a0436da8a67f9613d3c274306f2ddd8ed5d5d2e30ff63d5dd49f","observation_id":"bf4b673b-250a-4cc3-857e-4e435ae70367","resolution":{"observed_at":"2026-08-14T04:24:45.737725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2605.12358","last_updated":"2026-05-12T16:32:04Z","snapshot_observed_at":"2026-08-14T07:26:33.142110Z","submitted_at":"2026-05-12T16:32:04Z","title":"From Message-Passing to Linearized Graph Sequence Models","version":1},"cited_work":{"arxiv_id":"2605.12358","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.12358","snapshot_observed_at":"2026-08-14T04:24:43.554744Z","title":"From Message-Passing to Linearized Graph Sequence Models","venue":"cs.LG","work_id":"a352fa00-969d-43e1-8953-358345ee1de2","year":2026},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.802996Z"},"links":{"cited_paper":"/paper/2605.12358","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:61f6bbd5e80932597f01974b17fdd8b75631283faa691483b9bc16fb2246a085","observation_id":"4fed509e-f62d-495c-a5fa-23c79ac0b869","resolution":{"observed_at":"2026-08-14T04:24:43.567650Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.685921Z","title":"Can you hear me now? a benchmark for long-range graph propagation","venue":null,"work_id":"2deed0c5-0c1a-4787-a43b-ff8214c086e6","year":2026},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.814773Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:bfdeb74f4862816c941259ac35516ee425c2f200e57d8020e9eb9f457095ffd5","observation_id":"1f0c5b6d-6897-489b-a459-b19d8bf4d4f9","resolution":{"observed_at":"2026-08-14T04:24:45.691410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.651577Z","title":"Graph neural networks exponentially lose expressive power for node classification","venue":null,"work_id":"ad42d432-c90b-416a-a5ef-1cb46dc1f11c","year":2020},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.834670Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:00f72784ef63ce2867fb5ecae4b2c726e8a65e67a7cb0cb02b98e4bc76ab5e94","observation_id":"a66c108d-7088-4db3-89b6-3cc219b8083c","resolution":{"observed_at":"2026-08-14T04:24:45.660221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.594589Z","title":"Smith, Albert Gu, Anushan Fernando, Ça˘glar Gülçehre, Razvan Pascanu, and Soham De","venue":null,"work_id":"82fece1b-13dd-4c6e-b42f-9e7d41a926b4","year":2023},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.848218Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:6ef5c19132a0ad82a136e90e0775d11fe16731bf566a2fe29bf6115276281d06","observation_id":"ee55a82b-5d7f-4030-a32a-d454e50f20a3","resolution":{"observed_at":"2026-08-14T04:24:45.621550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.552161Z","title":"Recipe for a general, powerful, scalable graph trans- former","venue":null,"work_id":"d0dc64aa-a175-43cf-a2c7-b94a3ed17a25","year":2022},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.864353Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:80cd5988e73a3824cf4d358c77b2b5652648a1c4178c7c3a4615983bf94d46da","observation_id":"87c2ad3b-16c3-4d8e-8ffe-34a5fff5996e","resolution":{"observed_at":"2026-08-14T04:24:45.568308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.448801Z","title":"DropEdge: Towards deep graph convolutional networks on node classification","venue":null,"work_id":"d285c5ed-eeb1-442e-ac55-7b92b177c376","year":2020},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.899830Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:23569e80b0f1a288b8bcff9ac9bfc6ba90df75e2e95ef42dbcf84285b84067fa","observation_id":"d6051e9b-0b0f-4672-8b21-54b48fd62ff4","resolution":{"observed_at":"2026-08-14T04:24:45.465690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10993","last_updated":"2023-03-20T10:21:29Z","snapshot_observed_at":"2026-08-13T12:20:52.753435Z","submitted_at":"2023-03-20T10:21:29Z","title":"A Survey on Oversmoothing in Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10993","snapshot_observed_at":"2026-08-14T04:24:42.934757Z","title":"A survey on oversmoothing in graph neural networks.arXiv preprint arXiv:2303.10993, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.934757Z"},"links":{"cited_paper":"/paper/2303.10993","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:9f880b75aed4944d9df9b9c5e588c4cfb56f0c34f9dd4a4acb1563a2204b373c","observation_id":"abc547b7-1c55-4891-83da-dc44ab0ee184","resolution":{"observed_at":"2026-08-14T04:24:42.934757Z","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":"2026-08-14T04:24:45.390535Z","title":"Sutherland, and Ali Kemal Sinop","venue":null,"work_id":"bbab0808-9542-426e-b8cd-e5357bc50525","year":2023},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.967723Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:d2b7f13a9004cfc4c143d87723ca2c6ce1a3ea0da8c412fee8e97768430be738","observation_id":"2f0a197e-50a1-4d6a-8870-9541b84c4248","resolution":{"observed_at":"2026-08-14T04:24:45.406074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.342912Z","title":"Walking out of the weisfeiler leman hierarchy: Graph learning beyond message passing.Transactions on Machine Learning Research, 2023","venue":null,"work_id":"da803cc7-a15e-47e2-a9bb-ca568fa8c4b6","year":2023},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.977166Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:4f1bdf40fa229be884d8ee8a25e41feb8ba833cee75a2473dbe3f94ae34c5f40","observation_id":"8c1c9254-c640-49b1-b041-5fc9554f5628","resolution":{"observed_at":"2026-08-14T04:24:45.360936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.254865Z","title":"Bronstein","venue":null,"work_id":"7907bd44-ff8c-4af2-8311-82b08ba535b4","year":2022},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.998343Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:6e2f525a4a46bac908228f0a0df3ea9f86b9bf9997e20fed0240944aa4441760","observation_id":"5b318b0b-a49e-4525-b602-576d3e86748b","resolution":{"observed_at":"2026-08-14T04:24:45.284531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.204241Z","title":"Gomez, Łukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":"e6ee4e63-06e8-48b1-81ff-00a2836aed29","year":2017},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.022935Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:ba4b1d5366c69193688a373aa34a25e952fd1a4d0d7d956fee11c461c8cedcaa","observation_id":"94592e62-177f-41d0-92bd-df767cd90834","resolution":{"observed_at":"2026-08-14T04:24:45.222044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.125225Z","title":"Graph attention networks","venue":null,"work_id":"7ccf5840-0eae-4a9e-b2b0-c2eaaeacadfe","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.037597Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:3b8721b2baa3c89ff4e5fc9c73f0ae184340c1fbab2c2bbaddb740d194506358","observation_id":"5d89bbfd-ecf9-4388-a9bf-7d53d7acdcb1","resolution":{"observed_at":"2026-08-14T04:24:45.154757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00789","last_updated":"2024-02-01T17:21:53Z","snapshot_observed_at":"2026-08-13T04:29:03.289216Z","submitted_at":"2024-02-01T17:21:53Z","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00789","snapshot_observed_at":"2026-08-14T04:24:43.093771Z","title":"Graph-mamba: Towards long-range graph sequence modeling with selective state spaces.arXiv preprint arXiv:2402.00789, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.093771Z"},"links":{"cited_paper":"/paper/2402.00789","citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:4fc26e10ba049d922db9ce14b455726a081739e1197e29a377d34fae2d9b96ed","observation_id":"3391a199-f846-41f5-8e95-42c4628dc3cc","resolution":{"observed_at":"2026-08-14T04:24:43.093771Z","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":"2026-08-14T04:24:44.954761Z","title":"Representation learning on graphs with jumping knowledge networks","venue":null,"work_id":"23b5375d-8731-40d7-a08e-f2b767b41bcc","year":2018},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.100516Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:4a4fc631f796b6a58d8592fcb6b0e3142a3eb909413ec71e1b564eca5c971468","observation_id":"ff848bfe-d93f-40c5-b01d-ea00fb651e2e","resolution":{"observed_at":"2026-08-14T04:24:44.975322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:44.845013Z","title":"How powerful are graph neural networks? InInternational Conference on Learning Representations, 2019","venue":null,"work_id":"063c3785-613b-467a-9e1d-b4451d148f21","year":2019},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.107197Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:a64045c423245c12c2816419347ff00dfc7a04fe23e6c7771d86b46266e49376","observation_id":"461edc02-b373-45f8-ab5e-e24be5e80108","resolution":{"observed_at":"2026-08-14T04:24:44.880500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:44.693831Z","title":"Do transformers really perform badly for graph repre- sentation? InAdvances in Neural Information Processing Systems, volume 34, pp","venue":null,"work_id":"0dc6ecdd-1803-46e8-a3f5-dcfcd4ebb204","year":2021},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.117188Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:c1f5de14da097b546ce6d2e45c8aac0a510cf4769d924ae4c67a5c0ca11ac6f6","observation_id":"2911e4f3-3bbc-4a1d-bab0-0b8f442c89a9","resolution":{"observed_at":"2026-08-14T04:24:44.726883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:44.185188Z","title":null,"venue":null,"work_id":"d218aaac-9319-4390-810f-b5163dce4f7f","year":2017},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.127753Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:d7bd52a336465ef7bb4a8b9e08f5f39a4541ae3e6769cc766c4ce30bbd80d1bf","observation_id":"761ca390-9118-4010-a2fa-e4f14b2b9ad4","resolution":{"observed_at":"2026-08-14T04:24:44.605931Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:44.161690Z","title":"Adaptive diffusion in graph neural networks","venue":null,"work_id":"17ef7a49-b467-43da-838d-69bc12a500d7","year":2021},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.148114Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:287749cee77f988cb63c02e9b2c60171521ee64cd9a2a9b7759cfa46e8696892","observation_id":"841424d4-7f64-48e0-9447-6a3b46d468b0","resolution":{"observed_at":"2026-08-14T04:24:44.166919Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:44.133579Z","title":"PairNorm: Tackling oversmoothing in GNNs","venue":null,"work_id":"5c80fa04-05f6-42bb-b118-d31e07c25846","year":2020},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.153757Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:494f7fe01feb33ed118c2a9de7ab5b4e248ebace20c0a4b3d703d729525407d1","observation_id":"c1eb8a51-8302-4645-a75c-d7179d665de7","resolution":{"observed_at":"2026-08-14T04:24:44.138530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:44.100367Z","title":"In particular,∥∂[T r(S)H]u/∂Hv∥2 = 2r−1|[Sr]uv|, whereas standard power propagation satisfies ∥∂[SrH]u/∂Hv∥2 =|[S r]uv|","venue":null,"work_id":"561d5e5b-c44d-43b7-814f-0b427ba34bb0","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.173985Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:dd769bb580f07344c6ae5fe79a5270e004868bd094146ec29529b93259e886b0","observation_id":"d1c35821-a6b5-465b-8a40-bfc0e88e481c","resolution":{"observed_at":"2026-08-14T04:24:44.112349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:44.041292Z","title":"This proves the result","venue":null,"work_id":"544e696d-fdfd-436d-becf-73858b619e12","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.215903Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:ce121604888ee40b54ef0e507baa02c110adfc9c4ba27752d5bc200def264bcf","observation_id":"a4f1bdaa-fa79-47fc-8828-6c8ed0fb31db","resolution":{"observed_at":"2026-08-14T04:24:44.057436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:45.042342Z","title":null,"venue":null,"work_id":"c8d6ed82-983a-4681-ad98-9243f4fa4fdd","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:43.074825Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:248745c375ca014a8b7ae52939810c8579f0f195ac034786e8018b6a2e3ab9d4","observation_id":"45c34b46-9b7c-4437-ae19-5be9cb4a00f8","resolution":{"observed_at":"2026-08-14T04:24:45.074823Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.642598Z","title":null,"venue":null,"work_id":"08541011-a007-4132-8015-f834faff43e4","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.095736Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:d0cbd40eb1f6434460d39f498b3baa1e976c93cb88c64737120f3de26274c232","observation_id":"9fef965b-0bb0-4832-a31b-92bca6998348","resolution":{"observed_at":"2026-08-14T04:24:47.665746Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:47.385340Z","title":null,"venue":null,"work_id":"c8e7eab6-368a-4593-8a28-ebf37c951e9f","year":null},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.122490Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:0a32d2e98961dd35bbc66037b1895c1deee0c2319cdec74d8236bff369b6cbac","observation_id":"f4e13a0f-3cb7-4079-b792-ad42853ad706","resolution":{"observed_at":"2026-08-14T04:24:47.435079Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:24:46.934749Z","title":null,"venue":null,"work_id":"970c5945-9b1b-4109-b7fc-4fadb90423ae","year":2022},"citing_paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-14T04:24:42.251152Z"},"links":{"citing_paper":"/paper/2608.09031"},"observation_digest":"sha256:2e412d522f3930336a075bc90e39ef7f7f82d06d2ff45919fb877119ec78e19b","observation_id":"ac4e6f8d-bb46-4996-9c4c-bdb4a9fd2692","resolution":{"observed_at":"2026-08-14T04:24:46.958955Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.09031","last_updated":"2026-08-10T02:31:46Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T04:29:58.911039Z","submitted_at":"2026-08-10T02:31:46Z","title":"HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":2,"verified_fuzzy":44},"total_outbound_references":61},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2608.09031."}