{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OALZLWN3FFT36BTVZV52EAUVLI","short_pith_number":"pith:OALZLWN3","schema_version":"1.0","canonical_sha256":"701795d9bb2967bf0675cd7ba202955a16285223e9d757f186c40c7fa851b72a","source":{"kind":"arxiv","id":"1906.05497","version":5},"attestation_state":"computed","paper":{"title":"Deep Network Approximation Characterized by Number of Neurons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Haizhao Yang, Shijun Zhang, Zuowei Shen","submitted_at":"2019-06-13T06:15:15Z","abstract_excerpt":"This paper quantitatively characterizes the approximation power of deep feed-forward neural networks (FNNs) in terms of the number of neurons. It is shown by construction that ReLU FNNs with width $\\mathcal{O}\\big(\\max\\{d\\lfloor N^{1/d}\\rfloor,\\, N+1\\}\\big)$ and depth $\\mathcal{O}(L)$ can approximate an arbitrary H\\\"older continuous function of order $\\alpha\\in (0,1]$ on $[0,1]^d$ with a nearly tight approximation rate $\\mathcal{O}\\big(\\sqrt{d} N^{-2\\alpha/d}L^{-2\\alpha/d}\\big)$ measured in $L^p$-norm for any $N,L\\in \\mathbb{N}^+$ and $p\\in[1,\\infty]$. More generally for an arbitrary continuou"},"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":"1906.05497","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2019-06-13T06:15:15Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"0b918275268b551fff572ce8f87f9250740adcb1794e96c630a25dd4961e6519","abstract_canon_sha256":"4259ff4e331f04e755dc54a9c46c7b3ccd26673a3cabfcb1f746cbc46ee6a588"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:47.473065Z","signature_b64":"GROXN4TneOgzEDjGw3hLSDwwrQpu/11M0izX3VE8vy2S5qXZEcORB8iU1hrJRphQ+Vf4qmeBYW0w1l24QzIwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"701795d9bb2967bf0675cd7ba202955a16285223e9d757f186c40c7fa851b72a","last_reissued_at":"2026-07-05T02:06:47.472675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:47.472675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Network Approximation Characterized by Number of Neurons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Haizhao Yang, Shijun Zhang, Zuowei Shen","submitted_at":"2019-06-13T06:15:15Z","abstract_excerpt":"This paper quantitatively characterizes the approximation power of deep feed-forward neural networks (FNNs) in terms of the number of neurons. It is shown by construction that ReLU FNNs with width $\\mathcal{O}\\big(\\max\\{d\\lfloor N^{1/d}\\rfloor,\\, N+1\\}\\big)$ and depth $\\mathcal{O}(L)$ can approximate an arbitrary H\\\"older continuous function of order $\\alpha\\in (0,1]$ on $[0,1]^d$ with a nearly tight approximation rate $\\mathcal{O}\\big(\\sqrt{d} N^{-2\\alpha/d}L^{-2\\alpha/d}\\big)$ measured in $L^p$-norm for any $N,L\\in \\mathbb{N}^+$ and $p\\in[1,\\infty]$. More generally for an arbitrary continuou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05497","kind":"arxiv","version":5},"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/1906.05497/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":"1906.05497","created_at":"2026-07-05T02:06:47.472730+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05497v5","created_at":"2026-07-05T02:06:47.472730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05497","created_at":"2026-07-05T02:06:47.472730+00:00"},{"alias_kind":"pith_short_12","alias_value":"OALZLWN3FFT3","created_at":"2026-07-05T02:06:47.472730+00:00"},{"alias_kind":"pith_short_16","alias_value":"OALZLWN3FFT36BTV","created_at":"2026-07-05T02:06:47.472730+00:00"},{"alias_kind":"pith_short_8","alias_value":"OALZLWN3","created_at":"2026-07-05T02:06:47.472730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"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":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25608","citing_title":"Learning Sparse Compositional Functions with Norm-Constrained Neural Networks","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2503.02129","citing_title":"Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon","ref_index":10,"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":166,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI","json":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI.json","graph_json":"https://pith.science/api/pith-number/OALZLWN3FFT36BTVZV52EAUVLI/graph.json","events_json":"https://pith.science/api/pith-number/OALZLWN3FFT36BTVZV52EAUVLI/events.json","paper":"https://pith.science/paper/OALZLWN3"},"agent_actions":{"view_html":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI","download_json":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI.json","view_paper":"https://pith.science/paper/OALZLWN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05497&json=true","fetch_graph":"https://pith.science/api/pith-number/OALZLWN3FFT36BTVZV52EAUVLI/graph.json","fetch_events":"https://pith.science/api/pith-number/OALZLWN3FFT36BTVZV52EAUVLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI/action/storage_attestation","attest_author":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI/action/author_attestation","sign_citation":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI/action/citation_signature","submit_replication":"https://pith.science/pith/OALZLWN3FFT36BTVZV52EAUVLI/action/replication_record"}},"created_at":"2026-07-05T02:06:47.472730+00:00","updated_at":"2026-07-05T02:06:47.472730+00:00"}