{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RKEVPVULOUGWSFEH5KLG4ZTN7L","short_pith_number":"pith:RKEVPVUL","schema_version":"1.0","canonical_sha256":"8a8957d68b750d691487ea966e666dfacf12c6e71280bd04ada096d295d9ab3c","source":{"kind":"arxiv","id":"2303.16110","version":2},"attestation_state":"computed","paper":{"title":"Invariant preservation in machine learned PDE solvers via error correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","physics.comp-ph"],"primary_cat":"math.NA","authors_text":"Ammar Hakim, Nick McGreivy","submitted_at":"2023-03-28T16:26:37Z","abstract_excerpt":"Machine learned partial differential equation (PDE) solvers trade the reliability of standard numerical methods for potential gains in accuracy and/or speed. The only way for a solver to guarantee that it outputs the exact solution is to use a convergent method in the limit that the grid spacing $\\Delta x$ and timestep $\\Delta t$ approach zero. Machine learned solvers, which learn to update the solution at large $\\Delta x$ and/or $\\Delta t$, can never guarantee perfect accuracy. Some amount of error is inevitable, so the question becomes: how do we constrain machine learned solvers to give us "},"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":"2303.16110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2023-03-28T16:26:37Z","cross_cats_sorted":["cs.LG","cs.NA","physics.comp-ph"],"title_canon_sha256":"4ae1d1f7a23b52fcc7b046bd8a1d06ab4276fda14ebd2ab923e79d6770988d75","abstract_canon_sha256":"eebae653ca3a6303d7b7ced6d3f204ed23d90b2d2f37189d0182b75726942b79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:04.409454Z","signature_b64":"bTAcGWl1nVZ/bghze0bFqRBS4CfuqJtMI/DMtrQUoXSVMuJ2EkAg4sDgiFBaFv+YAyz3gtYeOezejrP1wfayCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a8957d68b750d691487ea966e666dfacf12c6e71280bd04ada096d295d9ab3c","last_reissued_at":"2026-07-05T05:56:04.408959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:04.408959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invariant preservation in machine learned PDE solvers via error correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","physics.comp-ph"],"primary_cat":"math.NA","authors_text":"Ammar Hakim, Nick McGreivy","submitted_at":"2023-03-28T16:26:37Z","abstract_excerpt":"Machine learned partial differential equation (PDE) solvers trade the reliability of standard numerical methods for potential gains in accuracy and/or speed. The only way for a solver to guarantee that it outputs the exact solution is to use a convergent method in the limit that the grid spacing $\\Delta x$ and timestep $\\Delta t$ approach zero. Machine learned solvers, which learn to update the solution at large $\\Delta x$ and/or $\\Delta t$, can never guarantee perfect accuracy. Some amount of error is inevitable, so the question becomes: how do we constrain machine learned solvers to give us "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16110","kind":"arxiv","version":2},"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/2303.16110/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":"2303.16110","created_at":"2026-07-05T05:56:04.409019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16110v2","created_at":"2026-07-05T05:56:04.409019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16110","created_at":"2026-07-05T05:56:04.409019+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKEVPVULOUGW","created_at":"2026-07-05T05:56:04.409019+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKEVPVULOUGWSFEH","created_at":"2026-07-05T05:56:04.409019+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKEVPVUL","created_at":"2026-07-05T05:56:04.409019+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L","json":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L.json","graph_json":"https://pith.science/api/pith-number/RKEVPVULOUGWSFEH5KLG4ZTN7L/graph.json","events_json":"https://pith.science/api/pith-number/RKEVPVULOUGWSFEH5KLG4ZTN7L/events.json","paper":"https://pith.science/paper/RKEVPVUL"},"agent_actions":{"view_html":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L","download_json":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L.json","view_paper":"https://pith.science/paper/RKEVPVUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16110&json=true","fetch_graph":"https://pith.science/api/pith-number/RKEVPVULOUGWSFEH5KLG4ZTN7L/graph.json","fetch_events":"https://pith.science/api/pith-number/RKEVPVULOUGWSFEH5KLG4ZTN7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L/action/storage_attestation","attest_author":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L/action/author_attestation","sign_citation":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L/action/citation_signature","submit_replication":"https://pith.science/pith/RKEVPVULOUGWSFEH5KLG4ZTN7L/action/replication_record"}},"created_at":"2026-07-05T05:56:04.409019+00:00","updated_at":"2026-07-05T05:56:04.409019+00:00"}