{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TM23WTSCQ7CYG24YV6V3ONO477","short_pith_number":"pith:TM23WTSC","schema_version":"1.0","canonical_sha256":"9b35bb4e4287c5836b98afabb735dcffd33f1b638fdf4728f866b1ff0f83e71d","source":{"kind":"arxiv","id":"2106.07687","version":1},"attestation_state":"computed","paper":{"title":"Deep neural networks for geometric multigrid methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Christian Lessig, Nils Margenberg, Robert Jendersie, Thomas Richter","submitted_at":"2021-06-14T18:10:41Z","abstract_excerpt":"We investigate scaling and efficiency of the deep neural network multigrid method (DNN-MG).\n  DNN-MG is a novel neural network-based technique for the simulation of the Navier-Stokes equations that combines an adaptive geometric multigrid solver, i.e. a highly efficient\n  classical solution scheme, with a recurrent neural network with memory.\n  The neural network replaces in DNN-MG one or multiple finest multigrid layers and provides a correction for the classical solve in the next time step.\n  This leads to little degradation in the solution quality while substantially reducing the overall co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.07687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2021-06-14T18:10:41Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"58caa632cf1bead0c8a8819888a8f86ea22c2325ffa5bba4dbb8ef9ca9d51f4b","abstract_canon_sha256":"a4c5f0b874a6f8ff494c401a50e157fb328fa37278f11f5ddd7cf1fdca4e9d77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:32.798268Z","signature_b64":"OIdDQsaQskZeQ/HgIfoejma0eaQqNQlNaA4J1LI69YIKESk+tzMHqUkIaz6m3UnSS5L4cP1Bt65uETtFiqnxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b35bb4e4287c5836b98afabb735dcffd33f1b638fdf4728f866b1ff0f83e71d","last_reissued_at":"2026-07-05T02:49:32.797796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:32.797796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep neural networks for geometric multigrid methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Christian Lessig, Nils Margenberg, Robert Jendersie, Thomas Richter","submitted_at":"2021-06-14T18:10:41Z","abstract_excerpt":"We investigate scaling and efficiency of the deep neural network multigrid method (DNN-MG).\n  DNN-MG is a novel neural network-based technique for the simulation of the Navier-Stokes equations that combines an adaptive geometric multigrid solver, i.e. a highly efficient\n  classical solution scheme, with a recurrent neural network with memory.\n  The neural network replaces in DNN-MG one or multiple finest multigrid layers and provides a correction for the classical solve in the next time step.\n  This leads to little degradation in the solution quality while substantially reducing the overall co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07687","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.07687/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.07687","created_at":"2026-07-05T02:49:32.797858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.07687v1","created_at":"2026-07-05T02:49:32.797858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07687","created_at":"2026-07-05T02:49:32.797858+00:00"},{"alias_kind":"pith_short_12","alias_value":"TM23WTSCQ7CY","created_at":"2026-07-05T02:49:32.797858+00:00"},{"alias_kind":"pith_short_16","alias_value":"TM23WTSCQ7CYG24Y","created_at":"2026-07-05T02:49:32.797858+00:00"},{"alias_kind":"pith_short_8","alias_value":"TM23WTSC","created_at":"2026-07-05T02:49:32.797858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.16598","citing_title":"A robust and stable hybrid neural network/finite element method for 2D flows that generalizes to different geometries","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477","json":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477.json","graph_json":"https://pith.science/api/pith-number/TM23WTSCQ7CYG24YV6V3ONO477/graph.json","events_json":"https://pith.science/api/pith-number/TM23WTSCQ7CYG24YV6V3ONO477/events.json","paper":"https://pith.science/paper/TM23WTSC"},"agent_actions":{"view_html":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477","download_json":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477.json","view_paper":"https://pith.science/paper/TM23WTSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.07687&json=true","fetch_graph":"https://pith.science/api/pith-number/TM23WTSCQ7CYG24YV6V3ONO477/graph.json","fetch_events":"https://pith.science/api/pith-number/TM23WTSCQ7CYG24YV6V3ONO477/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477/action/storage_attestation","attest_author":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477/action/author_attestation","sign_citation":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477/action/citation_signature","submit_replication":"https://pith.science/pith/TM23WTSCQ7CYG24YV6V3ONO477/action/replication_record"}},"created_at":"2026-07-05T02:49:32.797858+00:00","updated_at":"2026-07-05T02:49:32.797858+00:00"}