{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B4UTJWISTDE6KMPY3CRW4RARVP","short_pith_number":"pith:B4UTJWIS","schema_version":"1.0","canonical_sha256":"0f2934d91298c9e531f8d8a36e4411abd84bd81ef9e1cc78dd3f6b6fe8fb75d3","source":{"kind":"arxiv","id":"2010.01458","version":1},"attestation_state":"computed","paper":{"title":"The Finite Neuron Method and Convergence Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Jinchao Xu","submitted_at":"2020-10-04T01:15:30Z","abstract_excerpt":"We study a family of $H^m$-conforming piecewise polynomials based on artificial neural network, named as the finite neuron method (FNM), for numerical solution of $2m$-th order partial differential equations in $\\mathbb{R}^d$ for any $m,d \\geq 1$ and then provide convergence analysis for this method. Given a general domain $\\Omega\\subset\\mathbb R^d$ and a partition $\\mathcal T_h$ of $\\Omega$, it is still an open problem in general how to construct conforming finite element subspace of $H^m(\\Omega)$ that have adequate approximation properties. By using techniques from artificial neural networks"},"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":"2010.01458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2020-10-04T01:15:30Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"af834d99451480a4fbf41bd803e98a2b74b98886de371120905a9912e0ac0ffe","abstract_canon_sha256":"06b905ec8d94804400cb1d811fdb877040550d8aab80c3093f383d07ca3fd0a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:45.872349Z","signature_b64":"1ANm9UNK67bjP6GxjLcqnl7sz++3n8eC1+sysN9nhM5rS3ogO+/gVUqVMk0SP4CLxRnQybl3o1TazMnLUpwdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f2934d91298c9e531f8d8a36e4411abd84bd81ef9e1cc78dd3f6b6fe8fb75d3","last_reissued_at":"2026-07-05T02:02:45.871938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:45.871938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Finite Neuron Method and Convergence Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Jinchao Xu","submitted_at":"2020-10-04T01:15:30Z","abstract_excerpt":"We study a family of $H^m$-conforming piecewise polynomials based on artificial neural network, named as the finite neuron method (FNM), for numerical solution of $2m$-th order partial differential equations in $\\mathbb{R}^d$ for any $m,d \\geq 1$ and then provide convergence analysis for this method. Given a general domain $\\Omega\\subset\\mathbb R^d$ and a partition $\\mathcal T_h$ of $\\Omega$, it is still an open problem in general how to construct conforming finite element subspace of $H^m(\\Omega)$ that have adequate approximation properties. By using techniques from artificial neural networks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01458","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/2010.01458/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":"2010.01458","created_at":"2026-07-05T02:02:45.871993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01458v1","created_at":"2026-07-05T02:02:45.871993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01458","created_at":"2026-07-05T02:02:45.871993+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4UTJWISTDE6","created_at":"2026-07-05T02:02:45.871993+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4UTJWISTDE6KMPY","created_at":"2026-07-05T02:02:45.871993+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4UTJWIS","created_at":"2026-07-05T02:02:45.871993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08869","citing_title":"Adaptive Randomized Neural Networks with Locally Activation Function: Theory and Algorithm for Solving PDEs","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP","json":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP.json","graph_json":"https://pith.science/api/pith-number/B4UTJWISTDE6KMPY3CRW4RARVP/graph.json","events_json":"https://pith.science/api/pith-number/B4UTJWISTDE6KMPY3CRW4RARVP/events.json","paper":"https://pith.science/paper/B4UTJWIS"},"agent_actions":{"view_html":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP","download_json":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP.json","view_paper":"https://pith.science/paper/B4UTJWIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01458&json=true","fetch_graph":"https://pith.science/api/pith-number/B4UTJWISTDE6KMPY3CRW4RARVP/graph.json","fetch_events":"https://pith.science/api/pith-number/B4UTJWISTDE6KMPY3CRW4RARVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP/action/storage_attestation","attest_author":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP/action/author_attestation","sign_citation":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP/action/citation_signature","submit_replication":"https://pith.science/pith/B4UTJWISTDE6KMPY3CRW4RARVP/action/replication_record"}},"created_at":"2026-07-05T02:02:45.871993+00:00","updated_at":"2026-07-05T02:02:45.871993+00:00"}