{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ECD66J35UTUZHF4MV6G4XS76RR","short_pith_number":"pith:ECD66J35","schema_version":"1.0","canonical_sha256":"2087ef277da4e993978caf8dcbcbfe8c5d9df1b54831500e3f5e70bbc90123a5","source":{"kind":"arxiv","id":"2410.17445","version":1},"attestation_state":"computed","paper":{"title":"Guaranteeing Conservation Laws with Projection in Physics-Informed Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Baez, Lam M. Nguyen, Luca Daniel, Subhro Das, Wang Zhang, Ziwen Ma","submitted_at":"2024-10-22T21:46:55Z","abstract_excerpt":"Physics-informed neural networks (PINNs) incorporate physical laws into their training to efficiently solve partial differential equations (PDEs) with minimal data. However, PINNs fail to guarantee adherence to conservation laws, which are also important to consider in modeling physical systems. To address this, we proposed PINN-Proj, a PINN-based model that uses a novel projection method to enforce conservation laws. We found that PINN-Proj substantially outperformed PINN in conserving momentum and lowered prediction error by three to four orders of magnitude from the best benchmark tested. P"},"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":"2410.17445","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T21:46:55Z","cross_cats_sorted":[],"title_canon_sha256":"dc12c3d241e80b6b9ae940b534871f2e3e7327e7df406a8ceed1ebb9521da751","abstract_canon_sha256":"bebbd2c1ef6f8b88d20ad7cca7aeb8c57e26af18c1f0123e3a52591b5a51f200"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:22.693703Z","signature_b64":"IyHja0z7RbpwsCSQTO5Gj78fuad9vz3m8rhIY4J3qMIYWGDml4bbzKBwcLTqk1fJ5i4iBiYmD5UcertVeQp7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2087ef277da4e993978caf8dcbcbfe8c5d9df1b54831500e3f5e70bbc90123a5","last_reissued_at":"2026-07-05T09:24:22.693247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:22.693247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guaranteeing Conservation Laws with Projection in Physics-Informed Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Baez, Lam M. Nguyen, Luca Daniel, Subhro Das, Wang Zhang, Ziwen Ma","submitted_at":"2024-10-22T21:46:55Z","abstract_excerpt":"Physics-informed neural networks (PINNs) incorporate physical laws into their training to efficiently solve partial differential equations (PDEs) with minimal data. However, PINNs fail to guarantee adherence to conservation laws, which are also important to consider in modeling physical systems. To address this, we proposed PINN-Proj, a PINN-based model that uses a novel projection method to enforce conservation laws. We found that PINN-Proj substantially outperformed PINN in conserving momentum and lowered prediction error by three to four orders of magnitude from the best benchmark tested. P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17445","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/2410.17445/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":"2410.17445","created_at":"2026-07-05T09:24:22.693324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17445v1","created_at":"2026-07-05T09:24:22.693324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17445","created_at":"2026-07-05T09:24:22.693324+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECD66J35UTUZ","created_at":"2026-07-05T09:24:22.693324+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECD66J35UTUZHF4M","created_at":"2026-07-05T09:24:22.693324+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECD66J35","created_at":"2026-07-05T09:24:22.693324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07681","citing_title":"PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention","ref_index":94,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR","json":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR.json","graph_json":"https://pith.science/api/pith-number/ECD66J35UTUZHF4MV6G4XS76RR/graph.json","events_json":"https://pith.science/api/pith-number/ECD66J35UTUZHF4MV6G4XS76RR/events.json","paper":"https://pith.science/paper/ECD66J35"},"agent_actions":{"view_html":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR","download_json":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR.json","view_paper":"https://pith.science/paper/ECD66J35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17445&json=true","fetch_graph":"https://pith.science/api/pith-number/ECD66J35UTUZHF4MV6G4XS76RR/graph.json","fetch_events":"https://pith.science/api/pith-number/ECD66J35UTUZHF4MV6G4XS76RR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR/action/storage_attestation","attest_author":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR/action/author_attestation","sign_citation":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR/action/citation_signature","submit_replication":"https://pith.science/pith/ECD66J35UTUZHF4MV6G4XS76RR/action/replication_record"}},"created_at":"2026-07-05T09:24:22.693324+00:00","updated_at":"2026-07-05T09:24:22.693324+00:00"}