{"as_of":"2026-08-08T23:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cf0043c4b4f415a70b19ffd41f42908bcc26d3381e94c8d2daba3433d63f3201","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T06:09:02.680956Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2607.22004/citation-record","integrity":"/paper/2607.22004/integrity","json":"/paper/2607.22004/citation-record.json","paper":"/paper/2607.22004"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2006.02409","last_updated":"2020-06-09T08:58:08Z","snapshot_observed_at":"2026-07-06T09:25:47.539137Z","submitted_at":"2020-06-03T17:35:54Z","title":"On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.02409","snapshot_observed_at":"2026-08-01T06:09:01.509015Z","title":"On the promise of the stochastic generalized gauss-newton method for training dnns.arXiv preprint arXiv:2006.02409,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.509015Z"},"links":{"cited_paper":"/paper/2006.02409","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:c1e4eb9c4080fb2c2fc101fa19801d16ad48c602370b3b1e013350ab4070b41e","observation_id":"1869e1e6-8cd3-41db-a885-8f262af4c360","resolution":{"observed_at":"2026-08-01T06:09:01.509015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.04466","last_updated":"2023-03-24T17:51:27Z","snapshot_observed_at":"2026-08-07T08:21:35.608697Z","submitted_at":"2021-07-09T14:32:02Z","title":"Greedy Training Algorithms for Neural Networks and Applications to PDEs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.04466","snapshot_observed_at":"2026-08-01T06:09:01.596181Z","title":"An efficient greedy training algorithm for neural networks and applications in PDEs.arXiv preprint arXiv:2107.04466,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.596181Z"},"links":{"cited_paper":"/paper/2107.04466","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:c212497104466305de317fb0756c140b8a63358e3867e7b81a7fbc4261105fe7","observation_id":"0a726314-6133-47c7-a9b2-d03222323f11","resolution":{"observed_at":"2026-08-01T06:09:01.596181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10680","last_updated":"2024-02-16T13:34:28Z","snapshot_observed_at":"2026-08-04T07:36:24.904902Z","submitted_at":"2024-02-16T13:34:28Z","title":"Gauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10680","snapshot_observed_at":"2026-08-01T06:09:01.657091Z","title":"Gauss-Newton natural gradient descent for physics-informed computational fluid dynamics.arXiv preprint arXiv:2402.10680,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.657091Z"},"links":{"cited_paper":"/paper/2402.10680","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:42aedc2a297125b13089421af17a5897c69600f8d3561aadfe4fff5f735c7949","observation_id":"1bc946e1-0e5c-449e-9bd5-5daf4353a5f4","resolution":{"observed_at":"2026-08-01T06:09:01.657091Z","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":"10.1007/s41884-018-0015-3","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zongyi Li, Nikola Borislavov Kovachki, Kamyar Azizzadenesheli, Burigede liu, Kaushik Bhat- tacharya, Andrew Stuart, and Anima Anandkumar","venue":"Information Geometry","work_id":"bd57ba9b-a206-4c7e-b435-57c3116b1e50","year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.937407Z"},"links":{"citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:1794d56c3723ebcfb1ccd765e761809d688ae80f0262326d01c426496e27e942","observation_id":"d96393df-bfcd-4b91-8e9f-fdfd67b063a9","resolution":{"observed_at":"2026-08-01T06:14:25.207842Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-01T06:09:02.167737Z","title":"Johannes M¨ uller and Marius Zeinhofer","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.167737Z"},"links":{"citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:ae54b4a6ef3439ed0b7c04ca9d3f082b5e1be540f3fc982e69517189ec982dad","observation_id":"40d4027c-a72b-4e83-a772-71ce23753718","resolution":{"observed_at":"2026-08-01T06:09:02.167737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.06236","last_updated":"2023-01-11T10:55:25Z","snapshot_observed_at":"2026-07-06T12:37:13.576647Z","submitted_at":"2022-02-13T07:32:17Z","title":"Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.06236","snapshot_observed_at":"2026-08-01T06:09:02.323721Z","title":"Efficient natural gradient descent methods for large-scale optimization problems.arXiv:2202.06236,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.323721Z"},"links":{"cited_paper":"/paper/2202.06236","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:ceca89c160d6ed2ef2100d317b972544ec362784c9a60f6047e8914246b3525c","observation_id":"e768f406-bd75-4471-b4c1-54b743fac6c2","resolution":{"observed_at":"2026-08-01T06:09:02.323721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.02353","last_updated":"2019-06-05T23:13:42Z","snapshot_observed_at":"2026-07-06T07:58:21.319675Z","submitted_at":"2019-06-05T23:13:42Z","title":"Efficient Subsampled Gauss-Newton and Natural Gradient Methods for Training Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.02353","snapshot_observed_at":"2026-08-01T06:09:02.401966Z","title":"Efficient subsampled gauss-newton and natural gradient methods for training neural networks.arXiv preprint arXiv:1906.02353,","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.401966Z"},"links":{"cited_paper":"/paper/1906.02353","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:16bf6118abb6e6d6108996927b7b740a4ef8db170917f3ea7611fa67a2d5990a","observation_id":"b8bf84bf-13b7-467c-9f02-48e9ac52c085","resolution":{"observed_at":"2026-08-01T06:09:02.401966Z","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":"2026-08-01T06:09:02.489927Z","title":"¨Uber eine neue Methode zur L¨ osung gewisser Variationsprobleme der mathe- matischen Physik.Journal f¨ ur die reine und angewandte Mathematik (Crelles Journal), 1909(135):1–61,","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.489927Z"},"links":{"citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:e17c3993e6ea79e26d719eabc288c11ed7d2c6d1a04dbe88a0c59f0cec075e84","observation_id":"f9c82938-2943-4c69-ab02-517b5662fcd0","resolution":{"observed_at":"2026-08-01T06:09:02.489927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.07404","last_updated":"2022-03-14T18:08:18Z","snapshot_observed_at":"2026-07-06T12:47:48.418460Z","submitted_at":"2022-03-14T18:08:18Z","title":"Respecting causality is all you need for training physics-informed neural networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.07404","snapshot_observed_at":"2026-08-01T06:09:02.605898Z","title":"Respecting causality is all you need for training physics-informed neural networks.arXiv preprint arXiv:2203.07404, 2022a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.605898Z"},"links":{"cited_paper":"/paper/2203.07404","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:cc9634668d043aaba30262ff6173b22d1c83701f090ea6c154133afc0ad522e6","observation_id":"6b0f9da8-f10f-4acb-8625-0f9d99d8a8c7","resolution":{"observed_at":"2026-08-01T06:09:02.605898Z","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":"2026-08-01T06:09:02.680956Z","title":"Competitive physics informed networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.680956Z"},"links":{"citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:9172a3b1a1123f69c8354c52e85e31d116f87767adb6fb99e7b7feb6582e8d7f","observation_id":"5b5fcd9a-26d3-4b70-9a8e-24fb2975490c","resolution":{"observed_at":"2026-08-01T06:09:02.680956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.08481","last_updated":"2024-05-02T17:19:54Z","snapshot_observed_at":"2026-07-06T11:39:29.892520Z","submitted_at":"2021-08-19T03:56:49Z","title":"Neural Operator: Learning Maps Between Function Spaces","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.08481","snapshot_observed_at":"2026-08-01T06:09:01.761928Z","title":"Neural operator: Learning maps between function spaces.arXiv preprint arXiv:2108.08481,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2001,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.761928Z"},"links":{"cited_paper":"/paper/2108.08481","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:d87686e99311c747ab2ef47bebd8d71414ad625655140fff839f4e80d42376cd","observation_id":"eeb4939a-a03e-4a91-aa8c-d7e2a6accdfa","resolution":{"observed_at":"2026-08-01T06:09:01.761928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08069","last_updated":"2016-06-26T19:01:09Z","snapshot_observed_at":"2026-08-01T16:02:14.350035Z","submitted_at":"2016-06-26T19:01:09Z","title":"An iteration count estimate for a mesh-dependent steepest descent method based on finite elements and Riesz inner product representation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08069","snapshot_observed_at":"2026-08-01T06:09:02.550455Z","title":"An iteration count estimate for a mesh-dependent steepest descent method based on finite elements and Riesz inner product representation.arXiv preprint arXiv:1606.08069,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2002,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.550455Z"},"links":{"cited_paper":"/paper/1606.08069","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:5a2f57915f4ad9cd708a9b6f55877291184333cab0576043e582ece93d7afc3a","observation_id":"d68738c7-759e-4b46-9d55-77616d0e2c07","resolution":{"observed_at":"2026-08-01T06:09:02.550455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.12348","last_updated":"2022-11-18T16:37:37Z","snapshot_observed_at":"2026-07-06T10:27:04.232722Z","submitted_at":"2020-12-22T20:48:20Z","title":"An overview on deep learning-based approximation methods for partial differential equations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.12348","snapshot_observed_at":"2026-08-01T06:09:00.997699Z","title":"An overview on deep learning-based approximation methods for partial differential equations.arXiv preprint arXiv:2012.12348,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2003,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:00.997699Z"},"links":{"cited_paper":"/paper/2012.12348","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:42b277629bae53224d940b131c439b5c7388ac5c94b7af581324d5f6c7f79c2b","observation_id":"64ca3141-9710-4dcb-80be-feb831c82555","resolution":{"observed_at":"2026-08-01T06:09:00.997699Z","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":"2026-08-01T06:09:02.071860Z","title":"Geometry and convergence of natural policy gradi- ents.MPI MiS Preprint 31/2022,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.071860Z"},"links":{"citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:2dab6cb5545fa49ffd72dd2442deb14ef54c9dc080f5c4ce39011bb6c77413eb","observation_id":"66bc3707-0610-4b1b-8068-108d49cb21bc","resolution":{"observed_at":"2026-08-01T06:09:02.071860Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11675","last_updated":"2019-09-25T15:28:33Z","snapshot_observed_at":"2026-07-06T07:56:03.252728Z","submitted_at":"2019-05-28T08:30:24Z","title":"Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11675","snapshot_observed_at":"2026-08-01T06:09:01.051615Z","title":"Tianle Cai, Ruiqi Gao, Jikai Hou, Siyu Chen, Dong Wang, Di He, Zhihua Zhang, and Liwei Wang","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.051615Z"},"links":{"cited_paper":"/paper/1905.11675","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:abe191ff04fae3f873d79626ed5b2f6d3d7be9a42346606c2472ce7519a2b7cc","observation_id":"c68d25f1-5815-4713-9477-ebfe1b02c012","resolution":{"observed_at":"2026-08-01T06:09:01.051615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.01941","last_updated":"2025-07-02T00:05:00Z","snapshot_observed_at":"2026-08-04T07:14:22.288540Z","submitted_at":"2023-02-03T19:00:03Z","title":"Empowering deep neural quantum states through efficient optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.01941","snapshot_observed_at":"2026-08-01T06:09:01.120423Z","title":"Efficient optimization of deep neural quantum states toward machine precision.arXiv preprint arXiv:2302.01941,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.120423Z"},"links":{"cited_paper":"/paper/2302.01941","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:745ddd319a8871df839c565aec24922f550482aa28653eb217e85e03590894e2","observation_id":"8fa8b88c-7da8-402f-8607-8aeaa20cbc6f","resolution":{"observed_at":"2026-08-01T06:09:01.120423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.14933","last_updated":"2026-05-14T15:09:23Z","snapshot_observed_at":"2026-08-04T06:10:56.186365Z","submitted_at":"2026-05-14T15:09:23Z","title":"Nystr\\\"om Approximation on Manifolds","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.14933","snapshot_observed_at":"2026-08-01T06:09:02.240209Z","title":"Nystr¨ om approximation on manifolds.arXiv preprint arXiv:2605.14933,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:02.240209Z"},"links":{"cited_paper":"/paper/2605.14933","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:e24c964b25a857218861aad561702a287c351eb373e834f139a47f24df02c805","observation_id":"663aed9b-9146-48be-8aed-cef216736b9a","resolution":{"observed_at":"2026-08-01T06:09:02.240209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.02338","last_updated":"2023-06-07T20:19:38Z","snapshot_observed_at":"2026-08-08T23:04:29.627079Z","submitted_at":"2022-07-05T22:09:40Z","title":"Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.02338","snapshot_observed_at":"2026-08-01T06:09:01.431933Z","title":"Rethinking the impor- tance of sampling in physics-informed neural networks.arXiv preprint arXiv:2207.02338,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.431933Z"},"links":{"cited_paper":"/paper/2207.02338","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:d4d3ff46785aabde607282eb0b8f3cdb3b834008673a2cd69f528d23775859e2","observation_id":"ce1ab534-97b7-478d-9d79-127345d03b71","resolution":{"observed_at":"2026-08-01T06:09:01.431933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15603","last_updated":"2024-10-30T15:53:30Z","snapshot_observed_at":"2026-07-31T01:15:27.345200Z","submitted_at":"2024-05-24T14:36:02Z","title":"Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15603","snapshot_observed_at":"2026-08-01T06:09:01.226078Z","title":"Kronecker-factored approximate curvature for physics-informed neural networks.arXiv preprint arXiv:2405.15603,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.226078Z"},"links":{"cited_paper":"/paper/2405.15603","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:eb0c56b8e6eea86f5ab230cc5edb54f15663e19ca70d3fa629047dc08641d77e","observation_id":"dfe00422-fe04-461a-8cac-1d2351d2024f","resolution":{"observed_at":"2026-08-01T06:09:01.226078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.01943","last_updated":"2022-10-20T22:23:25Z","snapshot_observed_at":"2026-07-06T12:34:21.166418Z","submitted_at":"2022-02-04T02:21:31Z","title":"PSO-PINN: Physics-Informed Neural Networks Trained with Particle Swarm Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01943","snapshot_observed_at":"2026-08-01T06:09:01.344971Z","title":"Pso-pinn: Physics-informed neural networks trained with particle swarm optimization.arXiv preprint arXiv:2202.01943,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-01T06:09:01.344971Z"},"links":{"cited_paper":"/paper/2202.01943","citing_paper":"/paper/2607.22004"},"observation_digest":"sha256:db089d10ef3360e968e794b19f705a9fadd8925329df7078537e52ef2088163e","observation_id":"be03a5c2-b598-46b2-8ba8-9fd89a12b5ef","resolution":{"observed_at":"2026-08-01T06:09:01.344971Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.22004","last_updated":"2026-07-24T06:07:14Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T14:04:39.357267Z","submitted_at":"2026-07-24T06:07:14Z","title":"Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":20},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2607.22004."}