{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:75QT7FKQ7AQ3B4OC7XE2ZOSQ35","short_pith_number":"pith:75QT7FKQ","schema_version":"1.0","canonical_sha256":"ff613f9550f821b0f1c2fdc9acba50df56fb9eb527ae57d0be1bc3865652a2ea","source":{"kind":"arxiv","id":"2307.15285","version":3},"attestation_state":"computed","paper":{"title":"Optimal Approximation of Zonoids and Uniform Approximation by Shallow Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Jonathan W. Siegel","submitted_at":"2023-07-28T03:43:17Z","abstract_excerpt":"We study the following two related problems. The first is to determine to what error an arbitrary zonoid in $\\mathbb{R}^{d+1}$ can be approximated in the Hausdorff distance by a sum of $n$ line segments. The second is to determine optimal approximation rates in the uniform norm for shallow ReLU$^k$ neural networks on their variation spaces. The first of these problems has been solved for $d\\neq 2,3$, but when $d=2,3$ a logarithmic gap between the best upper and lower bounds remains. We close this gap, which completes the solution in all dimensions. For the second problem, our techniques signif"},"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":"2307.15285","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-07-28T03:43:17Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"872f7cc2fb7fa135f2ea27c901b6d5d4dadc43c16f95114dd727ce5103e2354c","abstract_canon_sha256":"c25e60f7ccbf7c5171886454979a0f5e8e9fba67b294af05aff799d68ff6077f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:19.495957Z","signature_b64":"jFlGew/423F8JpyUAivz+0jQdxir0PAPBzQt7aTmZCBhHmBbiwAweQylHdiV5McKjYWVvtNdj2lSraSFxt3SAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff613f9550f821b0f1c2fdc9acba50df56fb9eb527ae57d0be1bc3865652a2ea","last_reissued_at":"2026-07-05T10:38:19.495456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:19.495456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Approximation of Zonoids and Uniform Approximation by Shallow Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Jonathan W. Siegel","submitted_at":"2023-07-28T03:43:17Z","abstract_excerpt":"We study the following two related problems. The first is to determine to what error an arbitrary zonoid in $\\mathbb{R}^{d+1}$ can be approximated in the Hausdorff distance by a sum of $n$ line segments. The second is to determine optimal approximation rates in the uniform norm for shallow ReLU$^k$ neural networks on their variation spaces. The first of these problems has been solved for $d\\neq 2,3$, but when $d=2,3$ a logarithmic gap between the best upper and lower bounds remains. We close this gap, which completes the solution in all dimensions. For the second problem, our techniques signif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15285","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/2307.15285/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":"2307.15285","created_at":"2026-07-05T10:38:19.495521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15285v3","created_at":"2026-07-05T10:38:19.495521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15285","created_at":"2026-07-05T10:38:19.495521+00:00"},{"alias_kind":"pith_short_12","alias_value":"75QT7FKQ7AQ3","created_at":"2026-07-05T10:38:19.495521+00:00"},{"alias_kind":"pith_short_16","alias_value":"75QT7FKQ7AQ3B4OC","created_at":"2026-07-05T10:38:19.495521+00:00"},{"alias_kind":"pith_short_8","alias_value":"75QT7FKQ","created_at":"2026-07-05T10:38:19.495521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06789","citing_title":"Sharp uniform approximation for spectral Barron functions by deep neural networks","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35","json":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35.json","graph_json":"https://pith.science/api/pith-number/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/graph.json","events_json":"https://pith.science/api/pith-number/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/events.json","paper":"https://pith.science/paper/75QT7FKQ"},"agent_actions":{"view_html":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35","download_json":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35.json","view_paper":"https://pith.science/paper/75QT7FKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15285&json=true","fetch_graph":"https://pith.science/api/pith-number/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/graph.json","fetch_events":"https://pith.science/api/pith-number/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/action/storage_attestation","attest_author":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/action/author_attestation","sign_citation":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/action/citation_signature","submit_replication":"https://pith.science/pith/75QT7FKQ7AQ3B4OC7XE2ZOSQ35/action/replication_record"}},"created_at":"2026-07-05T10:38:19.495521+00:00","updated_at":"2026-07-05T10:38:19.495521+00:00"}