{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AQYO4U5R4J2CEXFY67AMN62FPA","short_pith_number":"pith:AQYO4U5R","schema_version":"1.0","canonical_sha256":"0430ee53b1e274225cb8f7c0c6fb4578314792330cbe7917148e9f3956972f46","source":{"kind":"arxiv","id":"2207.05748","version":2},"attestation_state":"computed","paper":{"title":"Physics-Informed Deep Neural Operator Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Aniruddha Bora, George Em Karniadakis, Somdatta Goswami, Yue Yu","submitted_at":"2022-07-08T12:29:09Z","abstract_excerpt":"Standard neural networks can approximate general nonlinear operators, represented either explicitly by a combination of mathematical operators, e.g., in an advection-diffusion-reaction partial differential equation, or simply as a black box, e.g., a system-of-systems. The first neural operator was the Deep Operator Network (DeepONet), proposed in 2019 based on rigorous approximation theory. Since then, a few other less general operators have been published, e.g., based on graph neural networks or Fourier transforms. For black box systems, training of neural operators is data-driven only but if"},"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":"2207.05748","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-08T12:29:09Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"54c7587882df8e3b0b757aeb613be557144b4fdb59daba29acf75a688daf8f49","abstract_canon_sha256":"b8216830299a6847b30a0eb0574cd936492b7af02675fb2aec5dbccb61f1fe1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:55.529002Z","signature_b64":"NN5G+8HDTKQUuPnM4F70OyfYDw5YdfmNCpnH7ajUDpcjLMY9n9EiITKYGiocRslyQ4UWiT3Ye5oF1/NFWi1gCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0430ee53b1e274225cb8f7c0c6fb4578314792330cbe7917148e9f3956972f46","last_reissued_at":"2026-07-05T04:40:55.528509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:55.528509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physics-Informed Deep Neural Operator Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Aniruddha Bora, George Em Karniadakis, Somdatta Goswami, Yue Yu","submitted_at":"2022-07-08T12:29:09Z","abstract_excerpt":"Standard neural networks can approximate general nonlinear operators, represented either explicitly by a combination of mathematical operators, e.g., in an advection-diffusion-reaction partial differential equation, or simply as a black box, e.g., a system-of-systems. The first neural operator was the Deep Operator Network (DeepONet), proposed in 2019 based on rigorous approximation theory. Since then, a few other less general operators have been published, e.g., based on graph neural networks or Fourier transforms. For black box systems, training of neural operators is data-driven only but if"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05748","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/2207.05748/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":"2207.05748","created_at":"2026-07-05T04:40:55.528568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05748v2","created_at":"2026-07-05T04:40:55.528568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05748","created_at":"2026-07-05T04:40:55.528568+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQYO4U5R4J2C","created_at":"2026-07-05T04:40:55.528568+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQYO4U5R4J2CEXFY","created_at":"2026-07-05T04:40:55.528568+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQYO4U5R","created_at":"2026-07-05T04:40:55.528568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22150","citing_title":"Parameterized Representations via Implicit Stochastic Modulation for High-Dimensional and High-Order Neural PDE Solvers","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2407.17182","citing_title":"A DeepONet for inverting the Neumann-to-Dirichlet Operator in Electrical Impedance Tomography: An approximation theoretic perspective and numerical results","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05133","citing_title":"Learning Hidden Physics and System Parameters with Deep Operator Networks","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12344","citing_title":"FEDONet : Fourier-Embedded DeepONet for Spectrally Accurate Operator Learning","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA","json":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA.json","graph_json":"https://pith.science/api/pith-number/AQYO4U5R4J2CEXFY67AMN62FPA/graph.json","events_json":"https://pith.science/api/pith-number/AQYO4U5R4J2CEXFY67AMN62FPA/events.json","paper":"https://pith.science/paper/AQYO4U5R"},"agent_actions":{"view_html":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA","download_json":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA.json","view_paper":"https://pith.science/paper/AQYO4U5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05748&json=true","fetch_graph":"https://pith.science/api/pith-number/AQYO4U5R4J2CEXFY67AMN62FPA/graph.json","fetch_events":"https://pith.science/api/pith-number/AQYO4U5R4J2CEXFY67AMN62FPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA/action/storage_attestation","attest_author":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA/action/author_attestation","sign_citation":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA/action/citation_signature","submit_replication":"https://pith.science/pith/AQYO4U5R4J2CEXFY67AMN62FPA/action/replication_record"}},"created_at":"2026-07-05T04:40:55.528568+00:00","updated_at":"2026-07-05T04:40:55.528568+00:00"}