{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GL7FK3RVC3ZECXFMUTQCBLZYKF","short_pith_number":"pith:GL7FK3RV","schema_version":"1.0","canonical_sha256":"32fe556e3516f2415caca4e020af385148aaa04016de451205f8400a83fb67b7","source":{"kind":"arxiv","id":"2409.02363","version":4},"attestation_state":"computed","paper":{"title":"Optimal Neural Network Approximation for High-Dimensional Continuous Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayan Maiti, Haizhao Yang, Michelle Michelle","submitted_at":"2024-09-04T01:18:55Z","abstract_excerpt":"Recently, the authors of \\cite{SYZ22} developed a neural network with width $36d(2d + 1)$ and depth $11$, which utilizes a special activation function called the elementary universal activation function, to achieve the super approximation property for functions in $C([a,b]^d)$. That is, the constructed network only requires a fixed number of neurons (and thus parameters) to approximate a $d$-variate continuous function on a $d$-dimensional hypercube with arbitrary accuracy. More specifically, only $\\mathcal{O}(d^2)$ neurons or parameters are used. One natural question is whether we can reduce "},"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":"2409.02363","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-04T01:18:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5e44ce02bafc17c9b712caea20167643808decbe64cadacc85fab03f9279becb","abstract_canon_sha256":"6f5d75e07b16551ac9d9884e8e97746f30518b41a2252bd24c7f050a55548455"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:14.680033Z","signature_b64":"dAW1LVgEQNvhL1cDGO7MtcVbHSeU0vl9OEZmSDy0djeiNBn9KxJzgpYmdWJbQxQz4Fc7mM1SvGMQy+brqlIhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32fe556e3516f2415caca4e020af385148aaa04016de451205f8400a83fb67b7","last_reissued_at":"2026-07-05T11:21:14.679551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:14.679551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Neural Network Approximation for High-Dimensional Continuous Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayan Maiti, Haizhao Yang, Michelle Michelle","submitted_at":"2024-09-04T01:18:55Z","abstract_excerpt":"Recently, the authors of \\cite{SYZ22} developed a neural network with width $36d(2d + 1)$ and depth $11$, which utilizes a special activation function called the elementary universal activation function, to achieve the super approximation property for functions in $C([a,b]^d)$. That is, the constructed network only requires a fixed number of neurons (and thus parameters) to approximate a $d$-variate continuous function on a $d$-dimensional hypercube with arbitrary accuracy. More specifically, only $\\mathcal{O}(d^2)$ neurons or parameters are used. One natural question is whether we can reduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02363","kind":"arxiv","version":4},"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/2409.02363/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":"2409.02363","created_at":"2026-07-05T11:21:14.679607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02363v4","created_at":"2026-07-05T11:21:14.679607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02363","created_at":"2026-07-05T11:21:14.679607+00:00"},{"alias_kind":"pith_short_12","alias_value":"GL7FK3RVC3ZE","created_at":"2026-07-05T11:21:14.679607+00:00"},{"alias_kind":"pith_short_16","alias_value":"GL7FK3RVC3ZECXFM","created_at":"2026-07-05T11:21:14.679607+00:00"},{"alias_kind":"pith_short_8","alias_value":"GL7FK3RV","created_at":"2026-07-05T11:21:14.679607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06781","citing_title":"On Explicit Super-Expressive Approximation for Neural Networks","ref_index":97,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27779","citing_title":"Global Convergence and Error Propagation in Neural Gradient Flows: A Riemannian Optimization Framework","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF","json":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF.json","graph_json":"https://pith.science/api/pith-number/GL7FK3RVC3ZECXFMUTQCBLZYKF/graph.json","events_json":"https://pith.science/api/pith-number/GL7FK3RVC3ZECXFMUTQCBLZYKF/events.json","paper":"https://pith.science/paper/GL7FK3RV"},"agent_actions":{"view_html":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF","download_json":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF.json","view_paper":"https://pith.science/paper/GL7FK3RV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02363&json=true","fetch_graph":"https://pith.science/api/pith-number/GL7FK3RVC3ZECXFMUTQCBLZYKF/graph.json","fetch_events":"https://pith.science/api/pith-number/GL7FK3RVC3ZECXFMUTQCBLZYKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF/action/storage_attestation","attest_author":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF/action/author_attestation","sign_citation":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF/action/citation_signature","submit_replication":"https://pith.science/pith/GL7FK3RVC3ZECXFMUTQCBLZYKF/action/replication_record"}},"created_at":"2026-07-05T11:21:14.679607+00:00","updated_at":"2026-07-05T11:21:14.679607+00:00"}