{"as_of":"2026-08-21T19:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:535c2d0eba1edb13518355e9f33038d1277f5dcff7a89c1c8a492fc84548ad8a","coverage":[{"denominator":81,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":81,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T05:00:16.525227Z","state":"measured"},{"denominator":81,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":81,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2607.22381/citation-record","integrity":"/paper/2607.22381/integrity","json":"/paper/2607.22381/citation-record.json","paper":"/paper/2607.22381"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T05:00:11.165976Z","title":"Which graph shift operator? a spectral answer to an empirical question","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.165976Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:9b2f1aac1d73c1be27cb78d8aa5960abe7e2e0d396ddcc5de8003fb6281d810b","observation_id":"ad21a69c-e908-4d69-9d29-b5a1a93a5f1a","resolution":{"observed_at":"2026-08-01T05:00:11.165976Z","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":"2026-08-01T05:00:11.195266Z","title":"Statistical mechanics of complex networks.Reviews of modern physics, 74(1):47, 2002","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.195266Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:426501a401e845035f484aa536d90edefdb052a23967189dd8248d34191cfe8c","observation_id":"df294380-e60f-467b-848e-049e9292b110","resolution":{"observed_at":"2026-08-01T05:00:11.195266Z","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":"2026-08-01T05:00:11.250766Z","title":"Beyond weisfeiler– lehman with local ego-network encodings.Machine Learning and Knowledge Extraction, 5(4):1234–1265, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.250766Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:4558ed3ad2904f8f93a1d9c57ce2094eb58e0d74f87142a1462453801d395f23","observation_id":"fbf0bbc5-87cc-405a-9951-f121154b7d0f","resolution":{"observed_at":"2026-08-01T05:00:11.250766Z","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":"2026-08-01T05:00:11.288021Z","title":"Spectra of cayley graphs.Journal of Combinatorial Theory, Series B, 27(2):180– 189, 1979","venue":null,"work_id":null,"year":1979},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.288021Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:db6b52a2e08f61fd88047e3daf5ee2895c1f00a12b1895535e85310578647091","observation_id":"66522bc4-0736-4f79-80d1-c041b0ecba06","resolution":{"observed_at":"2026-08-01T05:00:11.288021Z","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":"2026-08-01T05:00:11.341855Z","title":"Constant curvature graph convo- lutional networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.341855Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:ce484996edbb7c51f50dc8020c8f91bd025379dfed105d63508eed499544651d","observation_id":"63db0253-a883-4874-8860-c66538d3fe9c","resolution":{"observed_at":"2026-08-01T05:00:11.341855Z","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":"2026-08-01T05:00:11.392541Z","title":"Diffusions hypercontractives","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.392541Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:b2b8eb6805df911c758dbfbd2673b15ddcf42ca8fe82096e55c9352ec9996a8a","observation_id":"459f45ca-348c-4c86-9bf6-5cef19abfa3b","resolution":{"observed_at":"2026-08-01T05:00:11.392541Z","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":"2026-08-01T05:00:11.445840Z","title":"Bauer, B","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.445840Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:678923cee0fbecd31f23f0edecfb7d1c37809fa318371046e21b6dd44284d470","observation_id":"01c18b00-82c9-43f1-bd46-d3f291734756","resolution":{"observed_at":"2026-08-01T05:00:11.445840Z","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":"2026-08-01T05:00:11.480503Z","title":"Bauer, B","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.480503Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:e3679b5ce9cd7392cf8130e282643154070af479fc6d649a2a2ea34c3bbe0af9","observation_id":"8f8b1feb-fbfd-41f8-8869-1e0e8520a7e9","resolution":{"observed_at":"2026-08-01T05:00:11.480503Z","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":"2026-08-01T05:00:11.516464Z","title":"Bauer, Y","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.516464Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:c4e2e08af6bd7590009f1a4b6cc34feb46e8069ab4713eafe5b1d0615b66c2b2","observation_id":"518678f0-4e7b-4d91-b72d-109752029638","resolution":{"observed_at":"2026-08-01T05:00:11.516464Z","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":"2026-08-01T05:00:11.539703Z","title":"Laplacian eigenmaps for dimensionality reduction and data representation.Neural computation, 15(6):1373–1396, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.539703Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:17871160a89efa1b2bcf770faba07d25c96388c70660357190d22e5a19b1d740","observation_id":"024724fd-764f-4154-8235-28987b2dd693","resolution":{"observed_at":"2026-08-01T05:00:11.539703Z","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":"2026-08-01T05:00:11.573501Z","title":"A computational fluid mechanics solution to the monge-kantorovich mass transfer problem.Numerische Mathematik, 84(3):375–393, 2000","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.573501Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:839a811c556e3640234bda10992d86da4e6ef7c6a44f36a8e5e829b1c7835876","observation_id":"61fec448-713f-480c-9542-341933fe860c","resolution":{"observed_at":"2026-08-01T05:00:11.573501Z","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":"2026-08-01T05:00:11.607935Z","title":"Unimodular random trees.Ergodic Theory Dynam","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.607935Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:0684488c81b57097ddd9c4417512b05ec53c56cb5e92552e78339493aad356bc","observation_id":"c6ad3e9c-c8ed-4492-9807-780c6430210d","resolution":{"observed_at":"2026-08-01T05:00:11.607935Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00110","last_updated":"2024-07-31T18:37:19Z","snapshot_observed_at":"2026-08-20T01:29:13.400578Z","submitted_at":"2024-07-31T18:37:19Z","title":"The Aldous--Lyons Conjecture I: Subgroup Tests","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00110","snapshot_observed_at":"2026-08-01T05:00:11.651744Z","title":"The aldous–lyons conjecture i: Subgroup tests.arXiv preprint arXiv:2408.00110, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.651744Z"},"links":{"cited_paper":"/paper/2408.00110","citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:5ae49ee99126db45412433146953673d8a0339dc725bfbd117c210a5bb03e97f","observation_id":"4d465d5f-3ed2-4f0a-a966-8c7d610c900d","resolution":{"observed_at":"2026-08-01T05:00:11.651744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.13318","last_updated":"2020-06-23T20:36:56Z","snapshot_observed_at":"2026-08-14T09:35:00.453149Z","submitted_at":"2020-06-23T20:36:56Z","title":"A Note on Over-Smoothing for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.13318","snapshot_observed_at":"2026-08-01T05:00:11.704197Z","title":"A note on over-smoothing for graph neural networks.arXiv preprint arXiv:2006.13318, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.704197Z"},"links":{"cited_paper":"/paper/2006.13318","citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:1c9dea9bea11c5b70906119208e0fc86a754c62fbb7de56b521c46825635a893","observation_id":"c40c02ee-b0aa-4b7a-855a-543092a66d82","resolution":{"observed_at":"2026-08-01T05:00:11.704197Z","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":"2026-08-01T05:00:11.735487Z","title":"Graph neural ricci flow: Evolving feature from a curvature perspective","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.735487Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:165fff2ebcfec0d4188ce842c1a90ed4cf65b4182bb0fcedad9bb41bd0e1c082","observation_id":"ab7cb6df-4f2c-45de-8575-895ad0a338ee","resolution":{"observed_at":"2026-08-01T05:00:11.735487Z","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":"2026-08-01T05:00:11.769896Z","title":"Chung, Y","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.769896Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:7adee1097a36974fd1daef7d151b812f19f0e7be1f1a8ac716839f6d88c4c6e2","observation_id":"11876de1-6660-4b15-a84d-811f0844daaf","resolution":{"observed_at":"2026-08-01T05:00:11.769896Z","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":"2026-08-01T05:00:11.810738Z","title":"Chung and S.-T","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.810738Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:02c9b17c1776c0795de2ad1d6e9f6f993d56186565cb188d6ba98240971d44ab","observation_id":"7af64e36-5551-4d16-9c85-e707faf17abc","resolution":{"observed_at":"2026-08-01T05:00:11.810738Z","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":"2026-08-01T05:00:11.868980Z","title":"American Mathematical Soc., 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.868980Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:db77c9f3d48b76ea9b9053307d82ba37e86e4b562d72fee12568f2c7bdbc954e","observation_id":"510cbca8-fa94-49d5-a947-a93f79694808","resolution":{"observed_at":"2026-08-01T05:00:11.868980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.09366","last_updated":"2019-02-25T15:30:11Z","snapshot_observed_at":"2026-08-14T17:11:40.924754Z","submitted_at":"2019-02-25T15:30:11Z","title":"Liouville properties","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.09366","snapshot_observed_at":"2026-08-01T05:00:11.889729Z","title":"Liouville properties.arXiv preprint arXiv:1902.09366, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.889729Z"},"links":{"cited_paper":"/paper/1902.09366","citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:b89c915eafa4e6deaf7d0e59a17a54be12334ce85baed1a82f52d117055b8ae8","observation_id":"cf169a7d-90e2-43c4-9733-1ef59d55be8f","resolution":{"observed_at":"2026-08-01T05:00:11.889729Z","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":"2026-08-01T05:00:11.917767Z","title":"A riemannian interpolation inequality à la borell, brascamp and lieb.Inventiones mathematicae, 146(2):219– 257, 2001","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.917767Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:6c7e67493e0f061a5dd9ba1a46ce0a79e02c7ee2565f86f20639cd160b116899","observation_id":"10d17e7f-474d-45e8-97d1-c64eb852fe62","resolution":{"observed_at":"2026-08-01T05:00:11.917767Z","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":"2026-08-01T05:00:11.953534Z","title":"Learning parametrised graph shift operators","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.953534Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:fbc61515e1ad0730414365f45460bb53514c0f8f8869733afad05d1697318018","observation_id":"fe78bb61-71e4-4e00-ba48-0eeeaaa2d74c","resolution":{"observed_at":"2026-08-01T05:00:11.953534Z","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":"2026-08-01T05:00:11.999425Z","title":"Springer, 1992","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:11.999425Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:108b3546463b9d5b9f6c8ce35dc8fe4709ab62403816ef682d38fe60fa5c095b","observation_id":"a8a45c6d-40d9-469b-89e4-00225293c7ae","resolution":{"observed_at":"2026-08-01T05:00:11.999425Z","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":"2026-08-01T05:00:12.052002Z","title":"Graph anisotropic diffusion for molecules","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.052002Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:5caed3c46f60a3d12ba70d746fe1873bf04871bd8116de60cfdbd45bad8c6ef4","observation_id":"63dfe760-3096-4ada-8c61-56f966c57309","resolution":{"observed_at":"2026-08-01T05:00:12.052002Z","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":"2026-08-01T05:00:12.097644Z","title":"Graph positional encoding via random feature propagation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.097644Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:131df102208a92870bccb309c0c4392e2b120457d216caf9837ce39e850b7941","observation_id":"81cec3c9-bafb-43ea-b175-85b6fa6d1639","resolution":{"observed_at":"2026-08-01T05:00:12.097644Z","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":"2026-08-01T05:00:12.147216Z","title":"Über die verteilung der wurzeln bei gewissen algebraischen gleichungen mit ganzzahligen koeffizienten.Mathematische Zeitschrift, 17(1):228–249, 1923","venue":null,"work_id":null,"year":1923},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.147216Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:2610e62009547571a4daca034cff6284dd79f73fb63a0001071aa5833a385d8f","observation_id":"470bbf62-0d25-4917-b93b-08c285e9f8ff","resolution":{"observed_at":"2026-08-01T05:00:12.147216Z","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":"2026-08-01T05:00:12.191071Z","title":"How powerful are k-hop message passing graph neural networks.Advances in Neural Information Processing Systems, 35:4776–4790, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.191071Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:918b1f61b6eac14f1bcda85531396af65717325e73a2ba1933eb5df82fefa3f1","observation_id":"bf0a4b1e-04d8-4c86-a398-91131605f05c","resolution":{"observed_at":"2026-08-01T05:00:12.191071Z","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":"2026-08-01T05:00:12.234374Z","title":"Effective structural encodings via local curvature profiles","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.234374Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:c0a5ed67fbed7acb689e9a35e7eaf1d7ed62348f215195bf2460e1841510700d","observation_id":"b653e357-8f46-4910-a916-f3e2116b490b","resolution":{"observed_at":"2026-08-01T05:00:12.234374Z","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":"2026-08-01T05:00:12.273887Z","title":"Mitigating over-smoothing and over-squashing using aug- mentations of forman-ricci curvature","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.273887Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:8014be3e3ca66fb199d396ea6e35eb7bd3bfe3278a8f2d5608c41a597e0cd289","observation_id":"c46c99a6-9f49-4746-a2fc-3c8634aae41b","resolution":{"observed_at":"2026-08-01T05:00:12.273887Z","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":"2026-08-01T05:00:12.312470Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.312470Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:e344b8ceec44c448e1ce7978e3aabeb89dff9649b19157cd6afb759a282b84ca","observation_id":"23c89bab-4277-4fe4-9b59-26e7efca196a","resolution":{"observed_at":"2026-08-01T05:00:12.312470Z","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":"2026-08-01T05:00:12.354945Z","title":"Bochner’s method for cell complexes and combinatorial ricci curvature.Discrete & Computational Geometry, 29:323–374, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.354945Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:4592b464c7c1d7706f56058c97556d112ea60d0103e3fcb837a740df699b3d2e","observation_id":"0b391194-2b36-4ea2-bc65-5ef8b7821a4c","resolution":{"observed_at":"2026-08-01T05:00:12.354945Z","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":"2026-08-01T05:00:12.397520Z","title":"Bochner’s Method for Cell Complexes and Combinatorial Ricci Curvature","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.397520Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:33515a010da9398d3c75d17e6a74259964723a6e826657f3a322a4b32c0ac687","observation_id":"a366165a-94f3-41ad-855b-855343647ecf","resolution":{"observed_at":"2026-08-01T05:00:12.397520Z","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":"2026-08-01T05:00:12.443621Z","title":"Configuring random graph models with fixed degree sequences.Siam Review, 60(2):315–355, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.443621Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:bfb8a899a214e552e9430ceab878811463468d52bf70bfa958c8d3439f3247c5","observation_id":"99b4cd27-c333-4579-a6ea-da27f0bbea84","resolution":{"observed_at":"2026-08-01T05:00:12.443621Z","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":"2026-08-01T05:00:12.515376Z","title":"Spectra of expansion graphs.The Electronic Journal of Linear Algebra, 6:2–10, 1999","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.515376Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:431328564b44aa4f9436f72c2c707b36363ce29c88aa14f95cc0035756e3529a","observation_id":"446a0d77-36e4-4ac0-ae8f-ea2077b6755b","resolution":{"observed_at":"2026-08-01T05:00:12.515376Z","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":"2026-08-01T05:00:12.594519Z","title":"On the shift operator, graph frequency, and optimal filtering in graph signal processing.IEEE Transactions on Signal Processing, 65(23):6303–6318, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.594519Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:0930271f9dee84db42032917dd1baaf2eb90c6b10610476a5d9c36b4bf776af9","observation_id":"3b7e67de-66e0-49cd-a3e8-993b6211368c","resolution":{"observed_at":"2026-08-01T05:00:12.594519Z","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":"2026-08-01T05:00:12.678812Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.678812Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:730596217ff6ef455071b5d466446489d2051b71a476b2de53dd039b224eb169","observation_id":"45670224-013a-4c42-8711-cb88014775cb","resolution":{"observed_at":"2026-08-01T05:00:12.678812Z","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":"2026-08-01T05:00:12.725827Z","title":"Stochastic blockmodels: First steps.Social networks, 5(2):109–137, 1983","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.725827Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:ca6e5442f821dd56974b00c715efa0c603c0b22aae9f5ddac495b1adeceb1c8c","observation_id":"4f4cb22f-d6e9-42b4-ba29-1e1f51643968","resolution":{"observed_at":"2026-08-01T05:00:12.725827Z","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":"2026-08-01T05:00:12.802052Z","title":"Ollivier’s ricci curvature, local clustering and curvature-dimension inequalities on graphs.Discrete & Computational Geometry, 51(2):300–322, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.802052Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:c1b4df848854ebcede8b58fdfcfa5102eb52f06922c9295045c2d12b76c10aed","observation_id":"0b778e4c-39ef-4cc0-8918-0f1bb2e577f7","resolution":{"observed_at":"2026-08-01T05:00:12.802052Z","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":"2026-08-01T05:00:12.874125Z","title":"FoSR: First-order spectral rewiring for addressing oversquashing in GNNs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.874125Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:b797b254b4257bba140871d2d53eb605e97d64b1f723dbdeaa62d33afdac5233","observation_id":"ad3e6e87-08d8-471f-a641-61e9d868608f","resolution":{"observed_at":"2026-08-01T05:00:12.874125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-01T05:00:12.937055Z","title":"Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:12.937055Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:c20d0898ed8cfe6f031b0f022f761567e9e5688ba24ce25322a95e0962c9367a","observation_id":"725b2355-ac3e-425a-8a63-c377b58c940b","resolution":{"observed_at":"2026-08-01T05:00:12.937055Z","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":"2026-08-01T05:00:13.047188Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.047188Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:a81af4f92002dae1bcade37da8c987a0f3b098c5cdf61fee51b19f08b387563b","observation_id":"c7f5d5ef-536b-4562-8c9d-17c8d4b2c926","resolution":{"observed_at":"2026-08-01T05:00:13.047188Z","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":"2026-08-01T05:00:13.101986Z","title":"John Wiley & Sons, 1996","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.101986Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:f342ed99795d1756bb5713ea5d4aa53de7396f2e986d770d6c7ccc127095ef61","observation_id":"67e0b809-5519-444d-92e4-6935527c39cf","resolution":{"observed_at":"2026-08-01T05:00:13.101986Z","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":"2026-08-01T05:00:13.187580Z","title":"Curvature graph neural network.Information Sciences, 592:50–66, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.187580Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:c8e3c58ebfac123d57727d0c5c91d71a5abed57a950c934212e9c5a841bc696c","observation_id":"787ea663-c4c5-43cf-94d7-0a2884e56e1d","resolution":{"observed_at":"2026-08-01T05:00:13.187580Z","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":"2026-08-01T05:00:13.272286Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.272286Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:5baf71f1ec934abf7c7066c91dd9f589457eb3823316a04f29a41d315f52c66f","observation_id":"7bb1424e-df7d-48be-9c70-4e347470b0ab","resolution":{"observed_at":"2026-08-01T05:00:13.272286Z","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":"2026-08-01T05:00:13.464492Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.464492Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:b303bd4a02260a73c5fd4ded67f99f4294e4aff3a2b32cd3369fa975fa3bde61","observation_id":"b5a8793a-ed2f-4000-9fb6-3d1e2a854cce","resolution":{"observed_at":"2026-08-01T05:00:13.464492Z","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":"2026-08-01T05:00:13.591858Z","title":"Lin and S.-T","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.591858Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:988c148f36863f5647130c848b1fd3ac6c77f5ec01230254fe5b707b2c36f25c","observation_id":"fc957f48-2c50-4674-8384-e7f6554bb9bd","resolution":{"observed_at":"2026-08-01T05:00:13.591858Z","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":"2026-08-01T05:00:13.680449Z","title":"Lott and C","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.680449Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:98b7e4f52b9846d6f11e2bbc79c2cd68399251204b58b7d30644d530ceecdcda","observation_id":"2d93d6c1-503f-42e8-aaf2-3d004ffe51d6","resolution":{"observed_at":"2026-08-01T05:00:13.680449Z","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":"2026-08-01T05:00:13.796056Z","title":"Curvature-based clustering on graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.796056Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:f9970b1e101c396d4478c392351c92b1b83b2717de2c48ccc18281d9f9c9e5d5","observation_id":"c82deab9-59ba-4215-b188-8b27bc8ead30","resolution":{"observed_at":"2026-08-01T05:00:13.796056Z","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":"2026-08-01T05:00:13.917148Z","title":null,"venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:13.917148Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:163f544bfb7b5402037b8191b1ca49c418b44106488f978cb24b4305da66048c","observation_id":"76dcada2-7708-4f9a-8ce7-415f95d22e52","resolution":{"observed_at":"2026-08-01T05:00:13.917148Z","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":"2026-08-01T05:00:14.026724Z","title":null,"venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.026724Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:8e31997e4d9a45b45085865be78cda2be554c902136d27de8d6ab25dd06c4aaf","observation_id":"cbaa3fef-ec30-450c-8fb0-27988a546ae1","resolution":{"observed_at":"2026-08-01T05:00:14.026724Z","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":"2026-08-01T05:00:14.167593Z","title":"TUDataset: A collection of benchmark datasets for learning with graphs.ICML 2020 GRL+ Workshop, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.167593Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:edea7519d420f82de4ada13f130925a42c46a652b5a848a876dc01d78cbdf8e7","observation_id":"24b4e888-dc74-472f-b129-33bd2241a46b","resolution":{"observed_at":"2026-08-01T05:00:14.167593Z","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":"2026-08-01T05:00:14.244233Z","title":"Maxima for graphs and a new proof of a theorem of turán.Canadian Journal of Mathematics, 17:533–540, 1965","venue":null,"work_id":null,"year":1965},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.244233Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:35f6b6df7833685635952ddaf1365130b3d08b29492f4db7b2c476c2f5885340","observation_id":"20509005-97d8-4e5b-8b99-abbf567a2343","resolution":{"observed_at":"2026-08-01T05:00:14.244233Z","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":"2026-08-01T05:00:14.307282Z","title":"Revisiting over-smoothing and over-squashing using ollivier-ricci curvature","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.307282Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:7857b08cdac22ae1ef6b102f36804922d99d405d707528206e6fcefd8e4ccf13","observation_id":"b4faf2c6-fafb-4a05-814a-7e65d3000384","resolution":{"observed_at":"2026-08-01T05:00:14.307282Z","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":"2026-08-01T05:00:14.364094Z","title":"Community detection on networks with ricci flow.Scientific reports, 9(1):9984, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.364094Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:af21b0c6636ebf418e1e28e51470d1e6037b473b4bc7e6b619c156b43962d4e6","observation_id":"2819f22a-f8a3-488b-9a48-63e96fdc489c","resolution":{"observed_at":"2026-08-01T05:00:14.364094Z","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":"2026-08-01T05:00:14.445624Z","title":"Springer, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.445624Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:488dceb9f6f87a9601ad984f5c323d3914cf0e86fe7153cb3035037b3cacc2de","observation_id":"2ab25dce-e219-4383-a1c4-6c0611537ac6","resolution":{"observed_at":"2026-08-01T05:00:14.445624Z","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":"2026-08-01T05:00:14.504615Z","title":"Ricci curvature of markov chains on metric spaces.Journal of Functional Analysis, 256(3):810–864, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.504615Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:d4c63e8c27c238281d237a5914e7e3abe170fd17e4102e043fbea2f0afa963dc","observation_id":"5e7eb09c-b565-4f00-b348-20117ce14c53","resolution":{"observed_at":"2026-08-01T05:00:14.504615Z","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":"2026-08-01T05:00:14.579707Z","title":"Otto and C","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.579707Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:4d1578d6d8321bd50695f711d26a003b1e243488e61ada178846aca1fc6b5dc5","observation_id":"17edb093-1409-4c12-8108-5b6916bf3ad1","resolution":{"observed_at":"2026-08-01T05:00:14.579707Z","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":"2026-08-01T05:00:14.646958Z","title":"Master stability functions for synchronized coupled systems.Physical review letters, 80(10):2109, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.646958Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:45e3fbb8b15ac1c4e23a7b4e20ebb374a7e44faeda19430fe2270bba9544c528","observation_id":"4918024f-04b0-41d6-bd30-51bed1ba5074","resolution":{"observed_at":"2026-08-01T05:00:14.646958Z","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":"2026-08-01T05:00:14.718380Z","title":"Geom-gcn: Geometric graph convolutional networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.718380Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:d0397fcd343078ea2ebe535441e78258d7888232da7717a193860f1b2a2b50b1","observation_id":"e88c407e-5e73-4863-93d4-ff6312e10b50","resolution":{"observed_at":"2026-08-01T05:00:14.718380Z","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":"2026-08-01T05:00:14.769410Z","title":"OUP Oxford, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.769410Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:d0a44878bb3f800c9c6e010d3b11a118662d4b55a4f79bd939cf89cdb8d873c2","observation_id":"fb1cbd92-27cd-439a-b343-dbaa2a451e8a","resolution":{"observed_at":"2026-08-01T05:00:14.769410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15874","last_updated":"2024-06-28T10:20:12Z","snapshot_observed_at":"2026-08-16T15:44:45.692150Z","submitted_at":"2023-03-28T10:31:36Z","title":"Criteria for entropic curvature on graph spaces","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15874","snapshot_observed_at":"2026-08-01T05:00:14.827089Z","title":"Criteria for entropic curvature on graph spaces.ArXiv preprint: 2303.15874, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.827089Z"},"links":{"cited_paper":"/paper/2303.15874","citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:49b14b5131d5381e8d900fb9519a071ab2c9cfee7a937bfe57ee2d4b64dab408","observation_id":"83c1daf1-582d-45db-89b9-78d0f0c30aeb","resolution":{"observed_at":"2026-08-01T05:00:14.827089Z","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":"2026-08-01T05:00:14.901027Z","title":"V on Renesse and K.-Th","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.901027Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:ffb84e356769a576a9b69d8ca665dc9308aeea62ec9f114610c5adf441f6ab62","observation_id":"61eec418-14fd-4ade-b9cb-a5253a004c50","resolution":{"observed_at":"2026-08-01T05:00:14.901027Z","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":"2026-08-01T05:00:14.959525Z","title":"Sparse expanders have negative curvature.Geom","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:14.959525Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:ece562418a0dfc73b2545dcd0289634e5fc78eed695010167ef3f64c11e45f75","observation_id":"90f45dc2-dd61-4e7e-9bdc-624c827dc79b","resolution":{"observed_at":"2026-08-01T05:00:14.959525Z","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":"2026-08-01T05:00:15.014948Z","title":"Entropic curvature on graphs along schrödinger bridges at zero temperature","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.014948Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:8cd2cba9ee1c12d17bdf2786c466133e77e49fcb52ec18932704763fedf3c797","observation_id":"e063386e-d65d-46fe-87d9-aeb8d0574dcb","resolution":{"observed_at":"2026-08-01T05:00:15.014948Z","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":"2026-08-01T05:00:15.080506Z","title":"Algorithms, graph theory, and linear equations in laplacian matrices","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.080506Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:b1341f6f32857b05ddbf03fe4ff8d2177a0e86fa55ff1e82b335372e66da0937","observation_id":"6e251b1d-5ccb-4417-88cc-075c498ff4de","resolution":{"observed_at":"2026-08-01T05:00:15.080506Z","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":"2026-08-01T05:00:15.145030Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.145030Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:ae557ac0b29fc8f134ac7e89164903fc6e3da61bc6309b04dc22d698c0184c19","observation_id":"254ee897-2671-41d6-a66a-31d3d1ee77c0","resolution":{"observed_at":"2026-08-01T05:00:15.145030Z","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":"2026-08-01T05:00:15.202392Z","title":"Towards understanding generalization of graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.202392Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:8df8884e3b6098eac54e0d8e6d9c088daf32eee532353d8df9261396d5dcebe1","observation_id":"62dc2a1b-3c8a-4ad9-a741-3968c7ff0a1c","resolution":{"observed_at":"2026-08-01T05:00:15.202392Z","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":"2026-08-01T05:00:15.247686Z","title":"Bronstein","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.247686Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:9e90cf4a9df7fdcfe6c34c4a0848fae61f5eb1e8c709643960c0b5585df51346","observation_id":"9983eba9-1755-4e7f-b216-d291bb453d94","resolution":{"observed_at":"2026-08-01T05:00:15.247686Z","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":"2026-08-01T05:00:15.306449Z","title":"The effectiveness of curvature-based rewiring and the role of hyperparameters in gnns revisited","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.306449Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:1f2cd30802647b1cd0d560d2bfbe80d6a074cd6689b67febadfbaafce0eb4217","observation_id":"f758b15c-fe44-426e-8d67-0bccc1608679","resolution":{"observed_at":"2026-08-01T05:00:15.306449Z","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":"2026-08-01T05:00:15.364176Z","title":"Scipy 1.0: fundamental algorithms for scientific computing in python.Nature methods, 17(3):261–272, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.364176Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:5d53465e04d6015d83d7ac281843a6a4e6b9b72c3e8ca80bd2b1bb588b70e70e","observation_id":"880fceb9-43ea-41a3-95a0-1f1f0d3543c0","resolution":{"observed_at":"2026-08-01T05:00:15.364176Z","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":"2026-08-01T05:00:15.424025Z","title":"A manifold perspective on the statistical generalization of graph neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.424025Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:f9a568af510a8523a0665b548c1762b85541dd2bdab3b4727e88b3c96a05e3ee","observation_id":"9d14e4c2-79ac-43c1-8549-dd3e4aaf11dc","resolution":{"observed_at":"2026-08-01T05:00:15.424025Z","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":"2026-08-01T05:00:15.515757Z","title":"The effect of watts-strogatz and barabási-albert graphs on memory formation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.515757Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:b51685267ac548082a1eb45c3856cce8c9d0f7f0b8689bcfae98dd224e8ad537","observation_id":"5e6cb62e-96eb-413d-822b-5e37698ed610","resolution":{"observed_at":"2026-08-01T05:00:15.515757Z","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":"2026-08-01T05:00:15.644008Z","title":"Revisiting semi-supervised learning with graph embeddings","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.644008Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:0021c701ba0991e3398469af99c267b71563f8b6d42e38f018a8edf51eee834f","observation_id":"dd9a18a1-039f-4b0d-83bb-d451264e0d9f","resolution":{"observed_at":"2026-08-01T05:00:15.644008Z","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":"2026-08-01T05:00:15.732158Z","title":"•SBM:Stochastic Block Models representing community-structured networks [36]","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.732158Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:9529aa94205fbfb9f4cd896b817b343b1793d3a8799ea3fee04e49e2c4c19b72","observation_id":"9e2104c3-679d-4dac-83c8-ee8e174741ac","resolution":{"observed_at":"2026-08-01T05:00:15.732158Z","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":"2026-08-01T05:00:15.817578Z","title":"reasonable","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.817578Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:35739eacf21fa68ec760dfbeffcaf83e711dfd4d17db6f3de1ff7c4b6f90ee2b","observation_id":"cf550f3f-dfd7-4fec-a2dc-ba2b0592dc90","resolution":{"observed_at":"2026-08-01T05:00:15.817578Z","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":"2026-08-01T05:00:15.875725Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.875725Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:7f2c9312b664262ac4611cd5ed780722ecf5dab4ccee38588ebe8f4b8bbd7b0f","observation_id":"0b1c0be9-2559-49a4-9aef-5937e41bbfc1","resolution":{"observed_at":"2026-08-01T05:00:15.875725Z","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":"2026-08-01T05:00:15.919279Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.919279Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:d6c22952813d7b24a2b07a1c0678f251c67ed64ad6e4adf0568beb28f4530ef0","observation_id":"3c6edc6c-7dbb-4a34-bfd3-ed578e1fe07f","resolution":{"observed_at":"2026-08-01T05:00:15.919279Z","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":"2026-08-01T05:00:15.983623Z","title":"fast-decay","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:15.983623Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:8031169a39109a9a9f18ce64a6a60c91605c15dc135903f506e43485b6fce0e2","observation_id":"4c58d9c2-11d8-42d7-8cf1-5cdfa8227245","resolution":{"observed_at":"2026-08-01T05:00:15.983623Z","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":"2026-08-01T05:00:16.099895Z","title":"• Computation:We compute the exact ORC for every edge (u, v)in the graph using the GraphRicciCurvature library","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:16.099895Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:0a0e4d348416531a57fc20f7aea1f069e3b120fe41c349d1df3ea6c915c9f984","observation_id":"ac9ce5f9-9346-4398-9431-c64aeaff05c3","resolution":{"observed_at":"2026-08-01T05:00:16.099895Z","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":"2026-08-01T05:00:16.201929Z","title":"The positional encoding is formed by the k smallest non-trivial eigenvectors of L","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:16.201929Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:2ea7f9b9d9bfeb8a7f8e5373d57d7b97464ea4f66752ce8e286b23e3fe372efa","observation_id":"7f52f60c-dd68-489c-afe8-79b4009ee365","resolution":{"observed_at":"2026-08-01T05:00:16.201929Z","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":"2026-08-01T05:00:16.365871Z","title":"The encoding pRWPE u ∈R k is defined by the diagonal entries of the random walk diffusion matrix at various steps: pRWPE u = P1 uu,P 2 uu,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:16.365871Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:8c441ef49f67b2baf7b57bbd166fd0eb80c5ce78fdcefb35e5a4413ac19ebb5a","observation_id":"5ec91f44-c648-4e64-a303-3031a127ad79","resolution":{"observed_at":"2026-08-01T05:00:16.365871Z","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":"2026-08-01T05:00:16.525227Z","title":null,"venue":null,"work_id":null,"year":1948},"citing_paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-01T05:00:16.525227Z"},"links":{"citing_paper":"/paper/2607.22381"},"observation_digest":"sha256:436e4e7ddc923a5568e8654504967f605b05bf12bae01673ffa17fb0d8956c75","observation_id":"06ce8db6-3fd7-4d8c-b26e-fe8ad7d1f92b","resolution":{"observed_at":"2026-08-01T05:00:16.525227Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.22381","last_updated":"2026-07-24T15:07:37Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T22:11:45.247048Z","submitted_at":"2026-07-24T15:07:37Z","title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature"},"reference_resolution":{"displayed":81,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":80,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":81},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 81 of 81 outbound references and 0 inbound Pith citation observations for arXiv:2607.22381."}