{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HDTJUBVU54T3HNU35I74BFQS3N","short_pith_number":"pith:HDTJUBVU","schema_version":"1.0","canonical_sha256":"38e69a06b4ef27b3b69bea3fc09612db55d415eb18198a6a0098a61d59f2d85a","source":{"kind":"arxiv","id":"2402.10680","version":1},"attestation_state":"computed","paper":{"title":"Gauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"math.OC","authors_text":"Anas Jnini, Flavio Vella, Marius Zeinhofer","submitted_at":"2024-02-16T13:34:28Z","abstract_excerpt":"We propose Gauss-Newton's method in function space for the solution of the Navier-Stokes equations in the physics-informed neural network (PINN) framework. Upon discretization, this yields a natural gradient method that provably mimics the function space dynamics. Our computational results demonstrate close to single-precision accuracy measured in relative $L^2$ norm on a number of benchmark problems. To the best of our knowledge, this constitutes the first contribution in the PINN literature that solves the Navier-Stokes equations to this degree of accuracy. Finally, we show that given a suit"},"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":"2402.10680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-02-16T13:34:28Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"f2c738f024cf6221c23eecbe3e5f9c0796236c2946443bf0dfec08cbf5fddaf6","abstract_canon_sha256":"f695517671486acfb29114aa19fd25d41e4bc37a216a095c7c32d7129d136e56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:59.258375Z","signature_b64":"p0VduOQUcPBlqBPXY41gnLSfdqO8u2pIdwfSNDKZW/BGD9WmedsJicvk/Ua2/RrTEnZyMJheP/UbvtAAjfm8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38e69a06b4ef27b3b69bea3fc09612db55d415eb18198a6a0098a61d59f2d85a","last_reissued_at":"2026-07-05T07:45:59.257871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:59.257871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"math.OC","authors_text":"Anas Jnini, Flavio Vella, Marius Zeinhofer","submitted_at":"2024-02-16T13:34:28Z","abstract_excerpt":"We propose Gauss-Newton's method in function space for the solution of the Navier-Stokes equations in the physics-informed neural network (PINN) framework. Upon discretization, this yields a natural gradient method that provably mimics the function space dynamics. Our computational results demonstrate close to single-precision accuracy measured in relative $L^2$ norm on a number of benchmark problems. To the best of our knowledge, this constitutes the first contribution in the PINN literature that solves the Navier-Stokes equations to this degree of accuracy. Finally, we show that given a suit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10680","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/2402.10680/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":"2402.10680","created_at":"2026-07-05T07:45:59.257930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10680v1","created_at":"2026-07-05T07:45:59.257930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10680","created_at":"2026-07-05T07:45:59.257930+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDTJUBVU54T3","created_at":"2026-07-05T07:45:59.257930+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDTJUBVU54T3HNU3","created_at":"2026-07-05T07:45:59.257930+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDTJUBVU","created_at":"2026-07-05T07:45:59.257930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02184","citing_title":"Neural-network methods for two-dimensional finite-source reflector design","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03162","citing_title":"On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15554","citing_title":"Natural gradient descent with momentum","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":182,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N","json":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N.json","graph_json":"https://pith.science/api/pith-number/HDTJUBVU54T3HNU35I74BFQS3N/graph.json","events_json":"https://pith.science/api/pith-number/HDTJUBVU54T3HNU35I74BFQS3N/events.json","paper":"https://pith.science/paper/HDTJUBVU"},"agent_actions":{"view_html":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N","download_json":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N.json","view_paper":"https://pith.science/paper/HDTJUBVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10680&json=true","fetch_graph":"https://pith.science/api/pith-number/HDTJUBVU54T3HNU35I74BFQS3N/graph.json","fetch_events":"https://pith.science/api/pith-number/HDTJUBVU54T3HNU35I74BFQS3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N/action/storage_attestation","attest_author":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N/action/author_attestation","sign_citation":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N/action/citation_signature","submit_replication":"https://pith.science/pith/HDTJUBVU54T3HNU35I74BFQS3N/action/replication_record"}},"created_at":"2026-07-05T07:45:59.257930+00:00","updated_at":"2026-07-05T07:45:59.257930+00:00"}