{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:37VL664E7OB6S5Q6FCYDD53QNQ","short_pith_number":"pith:37VL664E","schema_version":"1.0","canonical_sha256":"dfeabf7b84fb83e9761e28b031f7706c3bf8435c2d4b6e9c8716027e6736a808","source":{"kind":"arxiv","id":"2312.16483","version":2},"attestation_state":"computed","paper":{"title":"Expressivity and Approximation Properties of Deep Neural Networks with ReLU$^k$ Activation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","cs.NE","math.NA"],"primary_cat":"cs.LG","authors_text":"Jinchao Xu, Juncai He, Tong Mao","submitted_at":"2023-12-27T09:11:14Z","abstract_excerpt":"In this paper, we investigate the expressivity and approximation properties of deep neural networks employing the ReLU$^k$ activation function for $k \\geq 2$. Although deep ReLU networks can approximate polynomials effectively, deep ReLU$^k$ networks have the capability to represent higher-degree polynomials precisely. Our initial contribution is a comprehensive, constructive proof for polynomial representation using deep ReLU$^k$ networks. This allows us to establish an upper bound on both the size and count of network parameters. Consequently, we are able to demonstrate a suboptimal approxim"},"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":"2312.16483","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T09:11:14Z","cross_cats_sorted":["cs.NA","cs.NE","math.NA"],"title_canon_sha256":"c1eefb77c8db3dae8e36551b6b1a7123df917281ccb396efb03b4f604f339efb","abstract_canon_sha256":"89ce68ec9f70750f790c4b61cc740756e7ce519d988e8733808ee5d60a3166dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:26.307492Z","signature_b64":"t/Hm7PN8v30B1F0x/nb3eU3Sl3JO2lZX0nL7N4GdWVstqvLatkoEHiHxl2H4/wNRO8qcmzuWmHnqpRxjhLCTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfeabf7b84fb83e9761e28b031f7706c3bf8435c2d4b6e9c8716027e6736a808","last_reissued_at":"2026-07-05T07:32:26.307010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:26.307010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expressivity and Approximation Properties of Deep Neural Networks with ReLU$^k$ Activation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","cs.NE","math.NA"],"primary_cat":"cs.LG","authors_text":"Jinchao Xu, Juncai He, Tong Mao","submitted_at":"2023-12-27T09:11:14Z","abstract_excerpt":"In this paper, we investigate the expressivity and approximation properties of deep neural networks employing the ReLU$^k$ activation function for $k \\geq 2$. Although deep ReLU networks can approximate polynomials effectively, deep ReLU$^k$ networks have the capability to represent higher-degree polynomials precisely. Our initial contribution is a comprehensive, constructive proof for polynomial representation using deep ReLU$^k$ networks. This allows us to establish an upper bound on both the size and count of network parameters. Consequently, we are able to demonstrate a suboptimal approxim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16483","kind":"arxiv","version":2},"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/2312.16483/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":"2312.16483","created_at":"2026-07-05T07:32:26.307069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16483v2","created_at":"2026-07-05T07:32:26.307069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16483","created_at":"2026-07-05T07:32:26.307069+00:00"},{"alias_kind":"pith_short_12","alias_value":"37VL664E7OB6","created_at":"2026-07-05T07:32:26.307069+00:00"},{"alias_kind":"pith_short_16","alias_value":"37VL664E7OB6S5Q6","created_at":"2026-07-05T07:32:26.307069+00:00"},{"alias_kind":"pith_short_8","alias_value":"37VL664E","created_at":"2026-07-05T07:32:26.307069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18468","citing_title":"Shallow ReLU$^s$ Networks in $L^p$-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization","ref_index":3,"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":31,"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":127,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ","json":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ.json","graph_json":"https://pith.science/api/pith-number/37VL664E7OB6S5Q6FCYDD53QNQ/graph.json","events_json":"https://pith.science/api/pith-number/37VL664E7OB6S5Q6FCYDD53QNQ/events.json","paper":"https://pith.science/paper/37VL664E"},"agent_actions":{"view_html":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ","download_json":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ.json","view_paper":"https://pith.science/paper/37VL664E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16483&json=true","fetch_graph":"https://pith.science/api/pith-number/37VL664E7OB6S5Q6FCYDD53QNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/37VL664E7OB6S5Q6FCYDD53QNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ/action/storage_attestation","attest_author":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ/action/author_attestation","sign_citation":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ/action/citation_signature","submit_replication":"https://pith.science/pith/37VL664E7OB6S5Q6FCYDD53QNQ/action/replication_record"}},"created_at":"2026-07-05T07:32:26.307069+00:00","updated_at":"2026-07-05T07:32:26.307069+00:00"}