{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QABJ5TFLOTZT3DPWZ6KTF6XRY6","short_pith_number":"pith:QABJ5TFL","schema_version":"1.0","canonical_sha256":"80029eccab74f33d8df6cf9532faf1c78f807223102781e91604aa6005d4c43e","source":{"kind":"arxiv","id":"2501.06933","version":3},"attestation_state":"computed","paper":{"title":"Neural equilibria for long-term prediction of nonlinear conservation laws","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.comp-ph","physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Ivan Dokmani\\'c, J. Antonio Lara Benitez, Junyi Guo, Kareem Hegazy, Maarten V. de Hoop, Michael W. Mahoney","submitted_at":"2025-01-12T21:02:20Z","abstract_excerpt":"Nonlinear conservation laws govern a broad class of important physical systems in science and industry and are central to scientific machine learning (SciML). Large general-purpose models offer speed, but replacing the numerical and physical structure of solvers often compromises stability, accuracy, and physical faithfulness. Here, we aim to balance the general inductive bias of conservation with the flexibility and speed of neural networks through a conservation-aware SciML backbone, which we call Neural Discrete Equilibrium (NeurDE). NeurDE places machine learning inside a kinetic solver by"},"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":"2501.06933","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T21:02:20Z","cross_cats_sorted":["physics.comp-ph","physics.flu-dyn"],"title_canon_sha256":"21104ba6bf31eaea4e744517f46786010908bcf1298012e2c170fe0ce89534c7","abstract_canon_sha256":"05aa3843843d66a8d2e44b378b774d939fb443eba92be86b477c700e7f85ab84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:47.972617Z","signature_b64":"rw1a8jrUvbgTQAThBboBJqxMKUXuhIzclq5Jt4u6qm80WboS9BISZ/Wpqnio3pjyjur8GWyTdhruLnRDnfNvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80029eccab74f33d8df6cf9532faf1c78f807223102781e91604aa6005d4c43e","last_reissued_at":"2026-05-20T00:02:47.971750Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:47.971750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural equilibria for long-term prediction of nonlinear conservation laws","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.comp-ph","physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Ivan Dokmani\\'c, J. Antonio Lara Benitez, Junyi Guo, Kareem Hegazy, Maarten V. de Hoop, Michael W. Mahoney","submitted_at":"2025-01-12T21:02:20Z","abstract_excerpt":"Nonlinear conservation laws govern a broad class of important physical systems in science and industry and are central to scientific machine learning (SciML). Large general-purpose models offer speed, but replacing the numerical and physical structure of solvers often compromises stability, accuracy, and physical faithfulness. Here, we aim to balance the general inductive bias of conservation with the flexibility and speed of neural networks through a conservation-aware SciML backbone, which we call Neural Discrete Equilibrium (NeurDE). NeurDE places machine learning inside a kinetic solver by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06933","kind":"arxiv","version":3},"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/2501.06933/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":"2501.06933","created_at":"2026-05-20T00:02:47.971893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06933v3","created_at":"2026-05-20T00:02:47.971893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06933","created_at":"2026-05-20T00:02:47.971893+00:00"},{"alias_kind":"pith_short_12","alias_value":"QABJ5TFLOTZT","created_at":"2026-05-20T00:02:47.971893+00:00"},{"alias_kind":"pith_short_16","alias_value":"QABJ5TFLOTZT3DPW","created_at":"2026-05-20T00:02:47.971893+00:00"},{"alias_kind":"pith_short_8","alias_value":"QABJ5TFL","created_at":"2026-05-20T00:02:47.971893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2509.09936","citing_title":"SciML Agents: Write the Solver, Not the Solution","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6","json":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6.json","graph_json":"https://pith.science/api/pith-number/QABJ5TFLOTZT3DPWZ6KTF6XRY6/graph.json","events_json":"https://pith.science/api/pith-number/QABJ5TFLOTZT3DPWZ6KTF6XRY6/events.json","paper":"https://pith.science/paper/QABJ5TFL"},"agent_actions":{"view_html":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6","download_json":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6.json","view_paper":"https://pith.science/paper/QABJ5TFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06933&json=true","fetch_graph":"https://pith.science/api/pith-number/QABJ5TFLOTZT3DPWZ6KTF6XRY6/graph.json","fetch_events":"https://pith.science/api/pith-number/QABJ5TFLOTZT3DPWZ6KTF6XRY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6/action/storage_attestation","attest_author":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6/action/author_attestation","sign_citation":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6/action/citation_signature","submit_replication":"https://pith.science/pith/QABJ5TFLOTZT3DPWZ6KTF6XRY6/action/replication_record"}},"created_at":"2026-05-20T00:02:47.971893+00:00","updated_at":"2026-05-20T00:02:47.971893+00:00"}