{"as_of":"2026-08-12T13:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5a2e73b6625921fcc07136ff726f8cc21b52d4311db0371850007984e15c99e3","coverage":[{"denominator":16,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T03:49:46.006008Z","state":"measured"},{"denominator":17,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":17,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-20T01:58:19.874612Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-10T12:15:01.137692Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"cited_work":{"arxiv_id":"2602.06842","doi":"10.48550/arxiv.2602.06842.url:http://arxiv.org/abs/2602.06842","metadata_source":"arxiv_reference","pith_arxiv_id":"2602.06842","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","venue":null,"work_id":"d1d1cc6c-ec3e-438e-a108-f3f8e33bc306","year":2026},"citing_paper":{"arxiv_id":"2605.19867","last_updated":"2026-05-19T13:58:31Z","snapshot_observed_at":"2026-07-06T23:30:30.141040Z","submitted_at":"2026-05-19T13:58:31Z","title":"When can a neural operator replace a coarse solve? Architectural principles for two-level preconditioning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-20T01:58:19.874612Z"},"links":{"cited_paper":"/paper/2602.06842","citing_paper":"/paper/2605.19867"},"observation_digest":"sha256:7da02dff17a672804254e26f045b7e8a28d71cc3f5a6cb4ed747aa803e8cfdab","observation_id":"54c9ffd7-aa1c-421c-bbb1-f0106b5de4de","resolution":{"observed_at":"2026-06-03T02:05:45.543805Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2602.06842/citation-record","integrity":"/paper/2602.06842/integrity","json":"/paper/2602.06842/citation-record.json","paper":"/paper/2602.06842"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:49:43.755283Z","title":"Number 13","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:43.755283Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:2bea2a1469ea7c77768b93b7dbf148afe5aefeeb16e85da3677b12e8cee7c473","observation_id":"397ca113-fb91-4443-8710-1b3353061f69","resolution":{"observed_at":"2026-08-03T03:49:43.755283Z","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":"2026-08-03T03:49:43.888193Z","title":"Preconditioning techniques for large linear systems: a survey.Journal of computational Physics, 182(2):418–477, 2002","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:43.888193Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:f8c08fcd1228ecc07a2f2e999cd02e891f1c6127dfc7958f670ad1217bf012c1","observation_id":"a26f6ecf-dbf0-49f4-9671-1af714b62be4","resolution":{"observed_at":"2026-08-03T03:49:43.888193Z","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":"2026-08-03T03:49:43.979060Z","title":"Oosterlee, and Anton Schuller.Multigrid","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:43.979060Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:688ee0f99b57439298a767359832aafb2b72328a4c38c38c4fa999d1349a1975","observation_id":"fff24c12-cd0a-4bc5-bd76-a61906684ca0","resolution":{"observed_at":"2026-08-03T03:49:43.979060Z","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":"2026-08-03T03:49:44.151983Z","title":"SIAM, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:44.151983Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:080355d70002c83acd5e8c73606a87ae6587a2280443c98f9d895d61ef5fc9ae","observation_id":"54600fb4-de8e-4c33-b09f-ee658732a905","resolution":{"observed_at":"2026-08-03T03:49:44.151983Z","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":"2026-08-03T03:49:44.349458Z","title":"Chebyshev semi-iterative methods, successive over- relaxation iterative methods, and second order Richardson iterative methods.Numerische Mathematik, 3(1):157–168, 1961","venue":null,"work_id":null,"year":1961},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:44.349458Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:95e1e2281c706337429f5a7403134224b0d0d1075b8fa27b73004171a4e1529c","observation_id":"cada1f90-d63a-464d-bf67-9deec3e7f15f","resolution":{"observed_at":"2026-08-03T03:49:44.349458Z","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":"2026-08-03T03:49:44.520058Z","title":"Anderson acceleration for fixed-point iterations.SIAM Journal on Numerical Analysis, 49(4):1715–1735, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:44.520058Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:dca104386b8b6ba5f714fd69271b226cd6608baa2b2fde755aa40139d9eed213","observation_id":"816377cd-780a-47f8-a1bd-156615520e38","resolution":{"observed_at":"2026-08-03T03:49:44.520058Z","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":"2026-08-03T03:49:44.698066Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:44.698066Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:6cc71e87b45dd465a210f3c24ef108eb3e3be4dd697fae368a31160efca00ec8","observation_id":"df19c1d3-e6bf-4a92-8504-593130f0942e","resolution":{"observed_at":"2026-08-03T03:49:44.698066Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.08895","last_updated":"2021-05-17T03:12:33Z","snapshot_observed_at":"2026-07-06T10:05:26.653366Z","submitted_at":"2020-10-18T00:34:21Z","title":"Fourier Neural Operator for Parametric Partial Differential Equations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.08895","snapshot_observed_at":"2026-08-03T03:49:44.826404Z","title":"Fourier neural operator for parametric partial differential equations.arXiv preprint arXiv:2010.08895, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:44.826404Z"},"links":{"cited_paper":"/paper/2010.08895","citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:b3dc52084603ab3f4a6120655dace0adaab0cdde511fbd491bd64b5c79d89535","observation_id":"5ff19f6c-6bae-4fc6-9548-b12200b8ec2f","resolution":{"observed_at":"2026-08-03T03:49:44.826404Z","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":"2026-08-03T03:49:44.974081Z","title":"Learn- ing nonlinear operators via DeepONet based on the universal approximation theorem of operators.Nature machine intelligence, 3(3):218–229, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:44.974081Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:8a3793d7c7be3a6c4bb75a417f5f4cbf8558093a5905ca366e4ad26e58c0521b","observation_id":"78bf22e1-b9a4-45e8-a809-f0fc281cc592","resolution":{"observed_at":"2026-08-03T03:49:44.974081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08734","last_updated":"2019-05-31T13:45:08Z","snapshot_observed_at":"2026-08-02T06:24:21.199176Z","submitted_at":"2018-06-22T15:39:05Z","title":"On the Spectral Bias of Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08734","snapshot_observed_at":"2026-08-03T03:49:45.123047Z","title":"Ham- precht, Yoshua Bengio, and Aaron Courville","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:45.123047Z"},"links":{"cited_paper":"/paper/1806.08734","citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:83b78262e5e7e257c2a20e6323bc0412ed5dca756ab3ab08253af6bbcfc30240","observation_id":"9442ea32-4eb9-461b-945b-7e442e0fc828","resolution":{"observed_at":"2026-08-03T03:49:45.123047Z","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":"2026-08-03T03:49:45.313012Z","title":"Blending neural operators and relaxation methods in PDE numerical solvers.Nature Machine Intelligence, pages 1–11, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:45.313012Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:35145bcd9a3b4d8c4b1e610cc4d09ceece1b7e55e4db819dec2bcf14558ccb68","observation_id":"6c597bef-cb79-4a2f-9cf0-165f92625067","resolution":{"observed_at":"2026-08-03T03:49:45.313012Z","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":"2026-08-03T03:49:45.418518Z","title":"A hybrid iterative method based on mionet for PDEs: Theory and numerical examples.Mathematics of Computation, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:45.418518Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:f9d32036f142d00baeaa30cee6e0953d059a71bc42ae784f1a0eb735926a7781","observation_id":"7b99d717-cd2c-46be-816d-6578ea55332c","resolution":{"observed_at":"2026-08-03T03:49:45.418518Z","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":"2026-08-03T03:49:45.557331Z","title":"MIONet: Learning multiple-input operators via tensor product.SIAM Journal on Scientific Computing, 44(6):A3490–A3514, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:45.557331Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:147d2cc69aa96ba9557ab44bc0791961784ea91b034134c849d9b1caff00077a","observation_id":"8933cd1f-786c-4d22-b42f-b6269ab53d60","resolution":{"observed_at":"2026-08-03T03:49:45.557331Z","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":"2026-08-03T03:49:45.719403Z","title":"Learning singularity-encoded Green’s functions with application to iterative methods.arXiv preprint arXiv:2509.11580, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:45.719403Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:ff4347b96c34727faf2f2d56b1346d8d44c27dfd1b841a763c2db750171267f8","observation_id":"ae7d1a6d-5f32-4390-a288-4b129be03a41","resolution":{"observed_at":"2026-08-03T03:49:45.719403Z","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":"2026-08-03T03:49:45.884202Z","title":"A hybrid iterative neural solver based on spectral analysis for parametric PDEs.Journal of Computational Physics, page 114165, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:45.884202Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:a5b954ce5df69d9ec70d78e71220a74694d441938bb33a57d65120141b9fe0c6","observation_id":"af7062b1-c9f1-400c-a0de-fd310c5ee7b7","resolution":{"observed_at":"2026-08-03T03:49:45.884202Z","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":"2026-08-03T03:49:46.006008Z","title":"Deeponet based preconditioning strate- gies for solving parametric linear systems of equations.SIAM Journal on Scientific Com- puting, 47(1):C151–C181, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:46.006008Z"},"links":{"citing_paper":"/paper/2602.06842"},"observation_digest":"sha256:1059b8b9172fab048e89af831ff9407fd05283d534bb5ee965d279e5b16ea6fb","observation_id":"f2f9c37b-0131-4c20-804d-ce9bb0a1cadd","resolution":{"observed_at":"2026-08-03T03:49:46.006008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.06842","last_updated":"2026-06-02T13:05:51Z","latest_version":2,"primary_category":"math.NA","snapshot_observed_at":"2026-08-03T03:49:43.172797Z","submitted_at":"2026-02-06T16:35:16Z","title":"Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter"},"reference_resolution":{"displayed":16,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":16},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 1 inbound Pith citation observation for arXiv:2602.06842."}