{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G7DRMAJTCU7OZCY2SU2JCWSVP4","short_pith_number":"pith:G7DRMAJT","schema_version":"1.0","canonical_sha256":"37c7160133153eec8b1a9534915a557f2ccc3881fa19e084511b6e54f69892e6","source":{"kind":"arxiv","id":"2312.14276","version":3},"attestation_state":"computed","paper":{"title":"Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Jinchao Xu, Juncai He","submitted_at":"2023-12-21T19:57:29Z","abstract_excerpt":"In this study, we establish that deep neural networks employing ReLU and ReLU$^2$ activation functions can effectively represent Lagrange finite element functions of any order on various simplicial meshes in arbitrary dimensions. We introduce two novel formulations for globally expressing the basis functions of Lagrange elements, tailored for both specific and arbitrary meshes. These formulations are based on a geometric decomposition of the elements, incorporating several insightful and essential properties of high-dimensional simplicial meshes, barycentric coordinate functions, and global ba"},"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":"2312.14276","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2023-12-21T19:57:29Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"e321f79b8045a40aef9d5d7622cb44652ceb63b563c2cb883d4a911fb67b2ebe","abstract_canon_sha256":"18c5cbda6e39b4d791f0edcb1238b15ac328194a21b6d902837c35c8b8e84f71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:45.313260Z","signature_b64":"smZoCvIrBFYEP6zb9dl3R1NfZsR2tEaPplxmTVffHz6BEbL1s4508LOoBYOPjrCNKj1SlIUUWTvMBmHG4yL7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37c7160133153eec8b1a9534915a557f2ccc3881fa19e084511b6e54f69892e6","last_reissued_at":"2026-07-05T07:32:45.312718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:45.312718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Jinchao Xu, Juncai He","submitted_at":"2023-12-21T19:57:29Z","abstract_excerpt":"In this study, we establish that deep neural networks employing ReLU and ReLU$^2$ activation functions can effectively represent Lagrange finite element functions of any order on various simplicial meshes in arbitrary dimensions. We introduce two novel formulations for globally expressing the basis functions of Lagrange elements, tailored for both specific and arbitrary meshes. These formulations are based on a geometric decomposition of the elements, incorporating several insightful and essential properties of high-dimensional simplicial meshes, barycentric coordinate functions, and global ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14276","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/2312.14276/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":"2312.14276","created_at":"2026-07-05T07:32:45.312791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14276v3","created_at":"2026-07-05T07:32:45.312791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14276","created_at":"2026-07-05T07:32:45.312791+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7DRMAJTCU7O","created_at":"2026-07-05T07:32:45.312791+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7DRMAJTCU7OZCY2","created_at":"2026-07-05T07:32:45.312791+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7DRMAJT","created_at":"2026-07-05T07:32:45.312791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22557","citing_title":"Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22557","citing_title":"Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2404.19756","citing_title":"KAN: Kolmogorov-Arnold Networks","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4","json":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4.json","graph_json":"https://pith.science/api/pith-number/G7DRMAJTCU7OZCY2SU2JCWSVP4/graph.json","events_json":"https://pith.science/api/pith-number/G7DRMAJTCU7OZCY2SU2JCWSVP4/events.json","paper":"https://pith.science/paper/G7DRMAJT"},"agent_actions":{"view_html":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4","download_json":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4.json","view_paper":"https://pith.science/paper/G7DRMAJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14276&json=true","fetch_graph":"https://pith.science/api/pith-number/G7DRMAJTCU7OZCY2SU2JCWSVP4/graph.json","fetch_events":"https://pith.science/api/pith-number/G7DRMAJTCU7OZCY2SU2JCWSVP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4/action/storage_attestation","attest_author":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4/action/author_attestation","sign_citation":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4/action/citation_signature","submit_replication":"https://pith.science/pith/G7DRMAJTCU7OZCY2SU2JCWSVP4/action/replication_record"}},"created_at":"2026-07-05T07:32:45.312791+00:00","updated_at":"2026-07-05T07:32:45.312791+00:00"}