{"as_of":"2026-08-10T18:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f7a27e63571394bea11a757bb974f3d322949d66edd724c688c5341859ce406d","coverage":[{"denominator":53,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":53,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T01:52:01.555713Z","state":"measured"},{"denominator":53,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":53,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.27767/citation-record","integrity":"/paper/2607.27767/integrity","json":"/paper/2607.27767/citation-record.json","paper":"/paper/2607.27767"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:52:01.305077Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.305077Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:fb7cb187200d39363bcbfbccbf2596849cb96dca425ed541c04dcf32f597d0a8","observation_id":"f9721aa0-c98c-4ef4-abf3-5a4c36e9ac20","resolution":{"observed_at":"2026-08-01T01:52:01.305077Z","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":"2026-08-01T01:52:01.310388Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.310388Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:bbf8572a58f22359b4b29bcb88f002e00283e1332cd14e3a9f956e9d94efa00d","observation_id":"621146b3-cc47-4adb-a358-39ce7ae3a314","resolution":{"observed_at":"2026-08-01T01:52:01.310388Z","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":"2026-08-01T01:52:01.315972Z","title":"From local structures to size generalization in graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.315972Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:1c7bfa8b2f559284b26f0ad9f27d292b12a08c6e9e4c5c732fb33b011199880d","observation_id":"49e12172-a298-4295-9302-a9784f9ca4ae","resolution":{"observed_at":"2026-08-01T01:52:01.315972Z","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":"2026-08-01T01:52:01.321651Z","title":"Graphon neural networks and the trans- ferability of graph neural networks.Advances in Neural Information Processing Systems, 33: 1702–1712, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.321651Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:123de8361fc681ae0642991091035956da055d90607ffe8aa22791d2fb3ba153","observation_id":"94a18a54-afdd-4d2c-901a-ce744dff72d3","resolution":{"observed_at":"2026-08-01T01:52:01.321651Z","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":"2026-08-01T01:52:01.326740Z","title":"The structure and function of complex networks.SIAM Review, 45(2): 167–256, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.326740Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:ea651f956ae6a925f61d0f7f7e103ecc24a61c348774310a98879e3d3ab17199","observation_id":"7ae78782-b450-424d-92b5-5a9aac3af211","resolution":{"observed_at":"2026-08-01T01:52:01.326740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.31315","last_updated":"2026-05-29T13:46:28Z","snapshot_observed_at":"2026-07-06T23:40:32.387598Z","submitted_at":"2026-05-29T13:46:28Z","title":"Graph Neural Networks Are Not Continuous Across Graph Resolutions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.31315","snapshot_observed_at":"2026-08-01T01:52:01.332001Z","title":"Graph neural networks are not continuous across graph resolutions.arXiv preprint arXiv:2605.31315, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.332001Z"},"links":{"cited_paper":"/paper/2605.31315","citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:47de9d1800b8a1487f15392d3f42ff7a205e0432e990e0144f8d040c9675f22f","observation_id":"5bd77990-75d0-41ab-ae74-e55ffedf6776","resolution":{"observed_at":"2026-08-01T01:52:01.332001Z","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":"2026-08-01T01:52:01.338539Z","title":"Graph reduction with spectral and cut guarantees.Journal of Machine Learning Research, 20(116):1–42, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.338539Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:d173afce7a05563cae86d7190fa78196ca99c5f34ed5053344cafbd8247e9376","observation_id":"47ed87e3-b655-4332-8004-9ebfd1011b85","resolution":{"observed_at":"2026-08-01T01:52:01.338539Z","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":"2026-08-01T01:52:01.343202Z","title":"Graph coarsening: from scientific computing to machine learning.SeMA Journal, 79(1):187–223, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.343202Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:f11794f392fb0dc54843e5ab7542f486cf83c8a5826079d7f7b38821a0eb73a7","observation_id":"e8ed0024-87d7-48fa-adaa-9611aa3784e4","resolution":{"observed_at":"2026-08-01T01:52:01.343202Z","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":"2026-08-01T01:52:01.348850Z","title":"Graph coarsening with message-passing guarantees.Ad- vances in Neural Information Processing Systems, 37:114902–114927, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.348850Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:165c70798511e6b18cf0c1ca233483ed0b4fdd7f51726878779db0ab7f3a2a49","observation_id":"985a3f3a-d549-40a4-8e90-9dc5918d91d3","resolution":{"observed_at":"2026-08-01T01:52:01.348850Z","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":"2026-08-01T01:52:01.353473Z","title":"Self-similarity of complex networks and hidden metric spaces.Physical Review Letters, 100(7):078701, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.353473Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:4b97df908763ae279a28b39e98b7a05189e3a20a27185330e91428b28158ecdb","observation_id":"3ba9aec7-23d8-49e5-9cd9-b9390e222e21","resolution":{"observed_at":"2026-08-01T01:52:01.353473Z","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":"2026-08-01T01:52:01.358017Z","title":"Network geometry.Nature Reviews Physics, 3(2):114–135, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.358017Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:edd09aa8260bf8f42e22fcaf40c04665de9eb047522bca833fdc2ba04174a0a7","observation_id":"fb024073-da9f-459c-b27e-8bbb83b9074c","resolution":{"observed_at":"2026-08-01T01:52:01.358017Z","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":"2026-08-01T01:52:01.363115Z","title":"Hyperbolic geometry of complex networks.Physical Review E—Statistical, Nonlinear , and Soft Matter Physics, 82(3):036106, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.363115Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:f22cee94d7637c98bd710eec919d4e1a95ce34c9826365f8c52b69cd426415bb","observation_id":"3cfe2fce-6a3d-442d-b300-b2e87c1e7267","resolution":{"observed_at":"2026-08-01T01:52:01.363115Z","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":"2026-08-01T01:52:01.367673Z","title":"Cambridge University Press, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.367673Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:2877881cb1f135fbd38a9342aecfa1146af2d3eb0d2d35e8e1730aef3fcd8bcc","observation_id":"71dcb843-3368-43e4-b0cb-b448e643d76b","resolution":{"observed_at":"2026-08-01T01:52:01.367673Z","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":"2026-08-01T01:52:01.372197Z","title":"Multiscale unfolding of real networks by geometric renormalization.Nature Physics, 14(6):583–589, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.372197Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:b393f30764b1bdf9403cf11c99f13b1aea00a4eabc119465fad0759ef7a0b0da","observation_id":"8ec9c9bb-e008-4920-a108-70980d073cbb","resolution":{"observed_at":"2026-08-01T01:52:01.372197Z","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":"2026-08-01T01:52:01.377551Z","title":"Similarity of neural network representations revisited","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.377551Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:41cdf3d007f11842344a8402b7fe8f0c26e4b9d5fedf1adef3a73504e28c75df","observation_id":"6baaffa8-5f83-41e1-b82f-ececb7589077","resolution":{"observed_at":"2026-08-01T01:52:01.377551Z","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":"2026-08-01T01:52:01.383646Z","title":"Ángeles Serrano, and Marián Boguñá","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.383646Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:be68ca2d14b6be1d08785b2ed6312aba6b957eb9e8eceecf9bc73da5bd4d3dde","observation_id":"98c7a10e-7067-4f06-ab83-8a4b8ed92341","resolution":{"observed_at":"2026-08-01T01:52:01.383646Z","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":"2026-08-01T01:52:01.387784Z","title":"Hierarchical graph representation learning with differentiable pooling.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.387784Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:f5a81fb368af5ba369268569c5a3e3b1f48624a5757f9075fd99950c723e72e6","observation_id":"5be63e6c-359d-4d19-8fb2-0a31a3bcb64b","resolution":{"observed_at":"2026-08-01T01:52:01.387784Z","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":"2026-08-01T01:52:01.392803Z","title":"Graph u-nets","venue":null,"work_id":null,"year":2083},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.392803Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:f8dee6cac332a77d971649e3a5df40504fea47560ee4011e94d92dac909e4c84","observation_id":"9e7b4d2f-3d0d-4be6-beb4-e7f2200fa01c","resolution":{"observed_at":"2026-08-01T01:52:01.392803Z","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":"2026-08-01T01:52:01.397298Z","title":"Understanding pooling in graph neural networks.IEEE transactions on neural networks and learning systems, 35(2):2708–2718, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.397298Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:8d27d5ec66804cd765afd985e686e285a4d12ea35e27f0eb866cb75d1f1500d7","observation_id":"c88a1942-fec7-4023-8394-23125e9a8a51","resolution":{"observed_at":"2026-08-01T01:52:01.397298Z","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":"2026-08-01T01:52:01.401548Z","title":"Geometry-aware edge pooling for graph neural networks.Advances in Neural Information Processing Systems, 38: 157770–157808, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.401548Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:c761733555156289b465442dfc1e1ea7d0edaf902874b347e1afcecb4884e12b","observation_id":"4d6dc0d8-3a8b-4523-be9e-f19e65d6a472","resolution":{"observed_at":"2026-08-01T01:52:01.401548Z","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":"2026-08-01T01:52:01.406339Z","title":"Graph pooling via ricci flow.Transactions on Machine Learning Research, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.406339Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:26db746931af817cdb2fba51d32a69e25576ba0509d6f0701950776a6d59b3f7","observation_id":"35384f2f-a0fa-4de1-b406-0e7544ea6207","resolution":{"observed_at":"2026-08-01T01:52:01.406339Z","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":"2026-08-01T01:52:01.411414Z","title":"Scaling up graph neural networks via graph coarsening","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.411414Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:27a95fbb3339c4daac6f06f15da1100522098b428da247e50a5e54361ad76ebe","observation_id":"2db517bb-2296-41fa-9c75-7ba35f719d21","resolution":{"observed_at":"2026-08-01T01:52:01.411414Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-01T01:52:01.415832Z","title":"Network renormalization.Nature Reviews Physics, 7(4):203–219, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.415832Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:f37f0e4caa649b4a24e3ac8699e6a3219d687f9bbab9c70c909e3f3b0cfabe39","observation_id":"0cc40695-df57-4095-ba69-5d8fbece646b","resolution":{"observed_at":"2026-08-01T01:52:01.415832Z","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":"2026-08-01T01:52:01.420083Z","title":"Self-similarity of complex networks","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.420083Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:301f9133dabb488f85ce528b622c9fc3c87d3c000d1be297064897397abb37c5","observation_id":"54d1af41-5412-4f57-bd92-002353e83dc5","resolution":{"observed_at":"2026-08-01T01:52:01.420083Z","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":"2026-08-01T01:52:01.424142Z","title":"Geometric renormalization unravels self-similarity of the multiscale human connectome","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.424142Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:15ac76e6fbc0ef99fdde6f7731dd1645caa3556f032ff8f9cc25d484e3f2b469","observation_id":"eef915c3-ea72-4cdc-aa37-5c45ee0d0ce9","resolution":{"observed_at":"2026-08-01T01:52:01.424142Z","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":"2026-08-01T01:52:01.428989Z","title":"Geometric renormalization of weighted networks.Communications Physics, 7(1):97, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.428989Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:9e3672505d8e4eb5dfa260fbdad03eaf93f24d8f3956d53292f74c9f918377bf","observation_id":"60c16cf4-16d2-428a-a44c-a2695d81d621","resolution":{"observed_at":"2026-08-01T01:52:01.428989Z","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":"2026-08-01T01:52:01.434468Z","title":"Laplacian renormaliza- tion group for heterogeneous networks.Nature Physics, 19(3):445–450, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.434468Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:5208949072d4ca39ac7b46723d6b74fce3a3f7564127ab02d40174d99779b705","observation_id":"d858c78f-97df-4588-aec1-41b01a457b3f","resolution":{"observed_at":"2026-08-01T01:52:01.434468Z","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":"2026-08-01T01:52:01.439762Z","title":"Higher-order laplacian renormalization.Nature Physics, 21(4):661–668, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.439762Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:f96cacedb2bca6d48c820597f0122f056f95c1429b2537bcc830f5b0a6d68c56","observation_id":"a6c8a8a8-52a9-4cfc-8fe0-9d4ef5bb6367","resolution":{"observed_at":"2026-08-01T01:52:01.439762Z","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":"2026-08-01T01:52:01.444504Z","title":"Multiscale network renormalization: Scale-invariance without geometry.Physical Review Research, 5(4):043101, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.444504Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:1a50fe1f6194977e976459fab1fe578dac8b0977ac31f75d1d602b31fcdf59e7","observation_id":"1282b0b9-18cf-429a-af62-26f5c72c488e","resolution":{"observed_at":"2026-08-01T01:52:01.444504Z","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":"2026-08-01T01:52:01.449174Z","title":"A metadata-driven approach to understand graph neural networks.Advances in Neural Information Processing Systems, 36:15320–15340, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.449174Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:f74bc4857acdfd05dbd4193c9dece0cf8e5f858e887ed7bf39b9a65da0dd0d87","observation_id":"f4327d55-ea55-46bb-ac2b-5679521fd8b7","resolution":{"observed_at":"2026-08-01T01:52:01.449174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.00547","last_updated":"2025-03-01T16:18:07Z","snapshot_observed_at":"2026-08-09T11:03:45.938629Z","submitted_at":"2025-03-01T16:18:07Z","title":"Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.00547","snapshot_observed_at":"2026-08-01T01:52:01.453583Z","title":"Performance heterogeneity in graph neural networks: Lessons for architecture design and preprocessing.arXiv preprint arXiv:2503.00547, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.453583Z"},"links":{"cited_paper":"/paper/2503.00547","citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:7665449868a4f650ab6fdb8008188a9d5f0a9f75eaf5289552bce483e888be57","observation_id":"e6cee50b-d093-4169-a714-124ae6d49acd","resolution":{"observed_at":"2026-08-01T01:52:01.453583Z","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":"2026-08-01T01:52:01.458796Z","title":"Transferability properties of graph neural networks.IEEE Transactions on Signal Processing, 71:3474–3489, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.458796Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:b34e20e5e73350beb2ba832ca799bb5913fbe8f2c43dea8cb06b32f72d011e8e","observation_id":"f4c767cf-a7cb-41aa-b608-3be64dd2b883","resolution":{"observed_at":"2026-08-01T01:52:01.458796Z","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":"2026-08-01T01:52:01.463308Z","title":"Mercator: uncovering faithful hyperbolic embeddings of complex networks.New Journal of Physics, 21 (12):123033, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.463308Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:b729e166756065180881bc1eba95c72ec02f2430858dd1369d1a27abb96167d7","observation_id":"4f77386d-7a2a-481c-8aac-4f33faeaa473","resolution":{"observed_at":"2026-08-01T01:52:01.463308Z","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":"2026-08-01T01:52:01.467643Z","title":"The d-mercator method for the multidimensional hyperbolic embedding of real networks.Nature Communica- tions, 14(1):7585, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.467643Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:d4b950c948beb2f9653b6e06e1340a177d87b86d1df389c31f7e70b50fe647fa","observation_id":"3f09dc18-6995-40e1-b62a-860fb7e6e0f9","resolution":{"observed_at":"2026-08-01T01:52:01.467643Z","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":"10.1103/physrevresearch.2.023040","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Ángeles Serrano","venue":"Physical Review Research","work_id":"bf765f98-80a9-4aed-bd8f-7e1bd712bb69","year":2020},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.472164Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:41e54534e42c9bae773991af1ff0115f71312503e136ff5987dc0a7ece5fd98b","observation_id":"4d474a2c-4e9f-4d9b-988e-8c27bd5d8f4e","resolution":{"observed_at":"2026-08-01T01:56:16.158956Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:52:01.477201Z","title":"Collective classification in network data.AI Magazine, 29(3):93–106, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.477201Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:8feafff55b1ea1da7822a01ac28fe07f8282b07d87d2924f312f8e7f2af30c2e","observation_id":"cef1f549-752a-4214-af3b-eef499f2c6da","resolution":{"observed_at":"2026-08-01T01:52:01.477201Z","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":"2026-08-01T01:52:01.481810Z","title":"Revisiting semi-supervised learning with graph embeddings","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.481810Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:4055195e4f970d068dc8426171287bb9a7facb89bbe54063a82d0290eeba8f1a","observation_id":"91cae729-8e12-49b7-b6b6-601b77d23af1","resolution":{"observed_at":"2026-08-01T01:52:01.481810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05868","last_updated":"2019-06-18T13:15:39Z","snapshot_observed_at":"2026-08-10T09:46:29.797564Z","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":"2026-08-01T01:52:01.486353Z","title":"Pitfalls of graph neural network evaluation.arXiv preprint arXiv:1811.05868, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.486353Z"},"links":{"cited_paper":"/paper/1811.05868","citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:aa1c0df3a2b3f2cdaec1e2bd37ef998b291716f6b728c95a2de4857819d56ede","observation_id":"c080f884-98f2-4c50-a7a8-c53487ed7999","resolution":{"observed_at":"2026-08-01T01:52:01.486353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.02901","last_updated":"2022-01-09T23:19:38Z","snapshot_observed_at":"2026-08-09T07:12:13.529182Z","submitted_at":"2020-07-06T17:25:47Z","title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.02901","snapshot_observed_at":"2026-08-01T01:52:01.491244Z","title":"Wiki-cs: A wikipedia-based benchmark for graph neural networks.arXiv preprint arXiv:2007.02901, 2020","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.491244Z"},"links":{"cited_paper":"/paper/2007.02901","citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:63613fcf2862f8690f0c5f134a91dad0214e40749a7202f0307eef7b3b11a956","observation_id":"4a4c427c-fea8-447d-8dba-434c0aae292a","resolution":{"observed_at":"2026-08-01T01:52:01.491244Z","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":"2026-08-01T01:52:01.495970Z","title":"GraphSAINT: Graph sampling based inductive learning method","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.495970Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:44e9e59297e693b5364c2e5d50de8777c5d9238ed49fb16bb8d28feea51aa106","observation_id":"9c9d3386-3cab-4498-9beb-21e526d50a53","resolution":{"observed_at":"2026-08-01T01:52:01.495970Z","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":"2026-08-01T01:52:01.500453Z","title":"Scale-free networks well done.Physical Review Research, 1(3):033034, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.500453Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:b3f1053174a61fea8aa660f8156180f2b571ebd0cf6b8588f561ac13a81ac30b","observation_id":"16b8eeed-7a9c-4696-bc43-ef7f31fcda58","resolution":{"observed_at":"2026-08-01T01:52:01.500453Z","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":"2026-08-01T01:52:01.504828Z","title":"Graph attention networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.504828Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:c0328e7938006d0caaa01585a2890a4d3d6968c0cc7ae828e67d4c8e20c441f2","observation_id":"3a160ccd-abf5-4df9-8bc4-74b2907de1e0","resolution":{"observed_at":"2026-08-01T01:52:01.504828Z","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":"2026-08-01T01:52:01.514251Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.514251Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:d7d58e43a201d3b9f5134757e20f539b491862b3880dd34393f6155b5f0f53b2","observation_id":"ca9f527a-6969-4f11-88c1-3956c72c4f0f","resolution":{"observed_at":"2026-08-01T01:52:01.514251Z","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":"2026-08-01T01:52:01.518990Z","title":"Algorithms for learning kernels based on centered alignment.The Journal of Machine Learning Research, 13:795–828, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.518990Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:24870f139370a66c62399647cc113736a0f44c4f50bec8ce8a6ee9846b4398ab","observation_id":"c42a4e2a-40db-4163-80d6-53f5c410bdea","resolution":{"observed_at":"2026-08-01T01:52:01.518990Z","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":"2026-08-01T01:52:01.523445Z","title":"On kernel-target alignment.Advances in neural information processing systems, 14, 2001","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.523445Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:210ec2d444eb7bb15e2741de5292aeaa0621c54262200ed7f7d84b86d598397e","observation_id":"05104a48-95d2-412e-9829-947b25c8341d","resolution":{"observed_at":"2026-08-01T01:52:01.523445Z","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":"2026-08-01T01:52:01.527948Z","title":"Grounding representation similarity through statistical testing.Advances in Neural Information Processing Systems, 34:1556–1568,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.527948Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:0f2adefbe3dd3da4b29058be3d10e2f8b65d88732b881f06d9180c45cc11f2a0","observation_id":"ffcbe010-b0b8-43a2-9d07-905f6045d6c6","resolution":{"observed_at":"2026-08-01T01:52:01.527948Z","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":"2026-08-01T01:52:01.532490Z","title":"Generalized shape metrics on neural representations.Advances in neural information processing systems, 34:4738–4750,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.532490Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:b8d7d02d97105b264cf22bd9bdc15a7a1e41ce44217373b96e71e3be36aac4e3","observation_id":"9d3388dd-9652-4b78-bbd5-5e753c3cf740","resolution":{"observed_at":"2026-08-01T01:52:01.532490Z","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":"2026-08-01T01:52:01.537094Z","title":"Spectral gap of random hyperbolic graphs and related param- eters.The Annals of Applied Probability, 28(2):941 – 989, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.537094Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:efc248b58817a1d527c03ffe46572ce27f169d14f663ce1279e7f7457352d837","observation_id":"3142721b-bf0d-4a3c-a44c-6efb9fbb33fc","resolution":{"observed_at":"2026-08-01T01:52:01.537094Z","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":"2026-08-01T01:52:01.541674Z","title":"Feature-aware ultra-low dimensional reduction of real networks.npj Complexity, 1(1):13, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.541674Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:976958f5bcb4040224dd4cfd4ab6d8a25fc6e1d6b0f6eca6092f63571485b57d","observation_id":"f70e7eae-d04e-43c0-b294-8d1e7d86ef41","resolution":{"observed_at":"2026-08-01T01:52:01.541674Z","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":"2026-08-01T01:52:01.546004Z","title":"Án- geles Serrano","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.546004Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:d055bbebc810e3d0bedfaaee44b1bbdc1caf274440f12831660ce5e6c5068226","observation_id":"7545fa6e-0afd-4e0f-9070-37aa8fc20b70","resolution":{"observed_at":"2026-08-01T01:52:01.546004Z","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":"2026-08-01T01:52:01.550742Z","title":"Detecting the ultra low dimensionality of real networks.Nature Communications, 13(1):6096, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.550742Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:5e2030992cd8b90221b23f3aa235009bdc2fd3cb0f3e497bd12d91709986229a","observation_id":"58982095-91de-49a6-9da8-1bd70a77c86f","resolution":{"observed_at":"2026-08-01T01:52:01.550742Z","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":"2026-08-01T01:52:01.555713Z","title":"Machine learning meets complex networks via coalescent embedding in the hyperbolic space.Nature Communications, 8(1):1615, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.555713Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:665953f6cbc723e90943f10dc3bd0816905a0bea40a8eed9a3d286002c2899a1","observation_id":"449d50f0-264c-49a1-bc0b-ecaf89047c09","resolution":{"observed_at":"2026-08-01T01:52:01.555713Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-01T01:52:01.509405Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-01T01:52:01.509405Z"},"links":{"citing_paper":"/paper/2607.27767"},"observation_digest":"sha256:7c644665dc1383eebdfcfa053d3ed8d0eac646b2de895f409b1e55c4a4f51312","observation_id":"e2253142-88b3-436e-a357-3d9a1009cc44","resolution":{"observed_at":"2026-08-01T01:52:01.509405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.27767","last_updated":"2026-07-30T07:03:23Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T07:13:58.516966Z","submitted_at":"2026-07-30T07:03:23Z","title":"Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization"},"reference_resolution":{"displayed":53,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":50,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":53},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 0 inbound Pith citation observations for arXiv:2607.27767."}