{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5F2T6Z3ON5W2PYCN6L3AGRM2UZ","short_pith_number":"pith:5F2T6Z3O","schema_version":"1.0","canonical_sha256":"e9753f676e6f6da7e04df2f603459aa65a6b9a902d4ea9ae0f83a520950efaca","source":{"kind":"arxiv","id":"2207.08675","version":2},"attestation_state":"computed","paper":{"title":"Learning differentiable solvers for systems with hard constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditi S. Krishnapriyan, Geoffrey N\\'egiar, Michael W. Mahoney","submitted_at":"2022-07-18T15:11:43Z","abstract_excerpt":"We introduce a practical method to enforce partial differential equation (PDE) constraints for functions defined by neural networks (NNs), with a high degree of accuracy and up to a desired tolerance. We develop a differentiable PDE-constrained layer that can be incorporated into any NN architecture. Our method leverages differentiable optimization and the implicit function theorem to effectively enforce physical constraints. Inspired by dictionary learning, our model learns a family of functions, each of which defines a mapping from PDE parameters to PDE solutions. At inference time, the mode"},"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":"2207.08675","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-18T15:11:43Z","cross_cats_sorted":[],"title_canon_sha256":"6f43e451d5985cb7cfd09b8930dc44e19085d47f06f7174f7dacdc967bbabf7b","abstract_canon_sha256":"0c50ba928ac202e6a90f04f0c6c1db705a1ae4e6283769563bb604e29b1b4def"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:58.048180Z","signature_b64":"xhx7ZRGlneCWh3YJ00soaRit2jTBzY53G/oYz9/4Im9ZCaYrvzWE8uH2zoqp7lVrq3UiIYTy7GKlzcnT8AbyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9753f676e6f6da7e04df2f603459aa65a6b9a902d4ea9ae0f83a520950efaca","last_reissued_at":"2026-07-05T06:01:58.047780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:58.047780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning differentiable solvers for systems with hard constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditi S. Krishnapriyan, Geoffrey N\\'egiar, Michael W. Mahoney","submitted_at":"2022-07-18T15:11:43Z","abstract_excerpt":"We introduce a practical method to enforce partial differential equation (PDE) constraints for functions defined by neural networks (NNs), with a high degree of accuracy and up to a desired tolerance. We develop a differentiable PDE-constrained layer that can be incorporated into any NN architecture. Our method leverages differentiable optimization and the implicit function theorem to effectively enforce physical constraints. Inspired by dictionary learning, our model learns a family of functions, each of which defines a mapping from PDE parameters to PDE solutions. At inference time, the mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08675","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/2207.08675/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":"2207.08675","created_at":"2026-07-05T06:01:58.047836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.08675v2","created_at":"2026-07-05T06:01:58.047836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08675","created_at":"2026-07-05T06:01:58.047836+00:00"},{"alias_kind":"pith_short_12","alias_value":"5F2T6Z3ON5W2","created_at":"2026-07-05T06:01:58.047836+00:00"},{"alias_kind":"pith_short_16","alias_value":"5F2T6Z3ON5W2PYCN","created_at":"2026-07-05T06:01:58.047836+00:00"},{"alias_kind":"pith_short_8","alias_value":"5F2T6Z3O","created_at":"2026-07-05T06:01:58.047836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.00233","citing_title":"Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ","json":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ.json","graph_json":"https://pith.science/api/pith-number/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/graph.json","events_json":"https://pith.science/api/pith-number/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/events.json","paper":"https://pith.science/paper/5F2T6Z3O"},"agent_actions":{"view_html":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ","download_json":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ.json","view_paper":"https://pith.science/paper/5F2T6Z3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.08675&json=true","fetch_graph":"https://pith.science/api/pith-number/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/action/storage_attestation","attest_author":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/action/author_attestation","sign_citation":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/action/citation_signature","submit_replication":"https://pith.science/pith/5F2T6Z3ON5W2PYCN6L3AGRM2UZ/action/replication_record"}},"created_at":"2026-07-05T06:01:58.047836+00:00","updated_at":"2026-07-05T06:01:58.047836+00:00"}