{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XLTAPJ3T7LOZKX5OCWLYB7Q6YJ","short_pith_number":"pith:XLTAPJ3T","schema_version":"1.0","canonical_sha256":"bae607a773fadd955fae159780fe1ec2622a9d38cc02c18427ea89bb4c852f5e","source":{"kind":"arxiv","id":"2102.04626","version":1},"attestation_state":"computed","paper":{"title":"Physics-informed neural networks with hard constraints for inverse design","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.comp-ph","authors_text":"Francesc Verdugo, Lu Lu, Raphael Pestourie, Steven G. Johnson, Wenjie Yao, Zhicheng Wang","submitted_at":"2021-02-09T03:18:15Z","abstract_excerpt":"Inverse design arises in a variety of areas in engineering such as acoustic, mechanics, thermal/electronic transport, electromagnetism, and optics. Topology optimization is a major form of inverse design, where we optimize a designed geometry to achieve targeted properties and the geometry is parameterized by a density function. This optimization is challenging, because it has a very high dimensionality and is usually constrained by partial differential equations (PDEs) and additional inequalities. Here, we propose a new deep learning method -- physics-informed neural networks with hard constr"},"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":"2102.04626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2021-02-09T03:18:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"236c68bd2d7ec324cf45ffbc92e066ca36cfa1e3f2f089165fe2b1e9303ef418","abstract_canon_sha256":"205f98f1b80e10def08b27f3a529506e3627ab774c419f86df2b0485f6685d0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:39.356911Z","signature_b64":"I1Ekdc/bpw8JJ0ykd0KPGUG9XSLKpCfyHQ0HeZgbvb9CFqd7Lg62JUGdnUl0f++mKamq56tVbAYaDeNbRBelBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bae607a773fadd955fae159780fe1ec2622a9d38cc02c18427ea89bb4c852f5e","last_reissued_at":"2026-07-05T03:48:39.356488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:39.356488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physics-informed neural networks with hard constraints for inverse design","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.comp-ph","authors_text":"Francesc Verdugo, Lu Lu, Raphael Pestourie, Steven G. Johnson, Wenjie Yao, Zhicheng Wang","submitted_at":"2021-02-09T03:18:15Z","abstract_excerpt":"Inverse design arises in a variety of areas in engineering such as acoustic, mechanics, thermal/electronic transport, electromagnetism, and optics. Topology optimization is a major form of inverse design, where we optimize a designed geometry to achieve targeted properties and the geometry is parameterized by a density function. This optimization is challenging, because it has a very high dimensionality and is usually constrained by partial differential equations (PDEs) and additional inequalities. Here, we propose a new deep learning method -- physics-informed neural networks with hard constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04626","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/2102.04626/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":"2102.04626","created_at":"2026-07-05T03:48:39.356544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04626v1","created_at":"2026-07-05T03:48:39.356544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04626","created_at":"2026-07-05T03:48:39.356544+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLTAPJ3T7LOZ","created_at":"2026-07-05T03:48:39.356544+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLTAPJ3T7LOZKX5O","created_at":"2026-07-05T03:48:39.356544+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLTAPJ3T","created_at":"2026-07-05T03:48:39.356544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21945","citing_title":"Beyond Data-Driven: How Physics-Informed Neural Networks are Reshaping Multi-Physics Design and Discovery","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02779","citing_title":"Comparison of Trefftz-Based PINNs and Standard PINNs Focusing on Structure Preservation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08408","citing_title":"AdamFLIP: Adaptive Momentum Feedback Linearization Optimization for Hard Constrained PINN Training","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ","json":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ.json","graph_json":"https://pith.science/api/pith-number/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/graph.json","events_json":"https://pith.science/api/pith-number/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/events.json","paper":"https://pith.science/paper/XLTAPJ3T"},"agent_actions":{"view_html":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ","download_json":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ.json","view_paper":"https://pith.science/paper/XLTAPJ3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04626&json=true","fetch_graph":"https://pith.science/api/pith-number/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/action/storage_attestation","attest_author":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/action/author_attestation","sign_citation":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/action/citation_signature","submit_replication":"https://pith.science/pith/XLTAPJ3T7LOZKX5OCWLYB7Q6YJ/action/replication_record"}},"created_at":"2026-07-05T03:48:39.356544+00:00","updated_at":"2026-07-05T03:48:39.356544+00:00"}