{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XNTKRQMXRB3RLQXNW5TMHWB3CD","short_pith_number":"pith:XNTKRQMX","schema_version":"1.0","canonical_sha256":"bb66a8c197887715c2edb766c3d83b10e73dad1fc91f14281770adcc88592814","source":{"kind":"arxiv","id":"1810.04374","version":3},"attestation_state":"computed","paper":{"title":"On the Approximation Properties of Random ReLU Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ambuj Tewari, Anna Gilbert, Yitong Sun","submitted_at":"2018-10-10T04:58:45Z","abstract_excerpt":"We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS). We first prove a universality theorem for the RKHS induced by random features whose feature maps are of the form of nodes in neural networks. The universality result implies that the random ReLU features method is a universally consistent learning algorithm. We prove that despite the universality of the RKHS induced by the random ReLU features, composition of functions in it generates substantially more complicated functions that are harder to approximate than those functions si"},"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":"1810.04374","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-10T04:58:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ac2c9ac746ec671ac22dda4bd042f4e583368821029d5b29ee3a2e79181b160","abstract_canon_sha256":"253e1f3ae5cc917350bf0058689747f83a9f829e78ad9e16de55fefc6e07cff9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:57:49.054305Z","signature_b64":"bqGVaTJl7WfkLZpgm0HqDUA5dfjSvI9N+10BIO4IkICnPeHKIt54XnBpiBAksjvy4JtM+F1Nc27KpAZf4aCkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb66a8c197887715c2edb766c3d83b10e73dad1fc91f14281770adcc88592814","last_reissued_at":"2026-07-04T23:57:49.053924Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:57:49.053924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Approximation Properties of Random ReLU Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ambuj Tewari, Anna Gilbert, Yitong Sun","submitted_at":"2018-10-10T04:58:45Z","abstract_excerpt":"We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS). We first prove a universality theorem for the RKHS induced by random features whose feature maps are of the form of nodes in neural networks. The universality result implies that the random ReLU features method is a universally consistent learning algorithm. We prove that despite the universality of the RKHS induced by the random ReLU features, composition of functions in it generates substantially more complicated functions that are harder to approximate than those functions si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04374","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/1810.04374/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":"1810.04374","created_at":"2026-07-04T23:57:49.053989+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.04374v3","created_at":"2026-07-04T23:57:49.053989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04374","created_at":"2026-07-04T23:57:49.053989+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNTKRQMXRB3R","created_at":"2026-07-04T23:57:49.053989+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNTKRQMXRB3RLQXN","created_at":"2026-07-04T23:57:49.053989+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNTKRQMX","created_at":"2026-07-04T23:57:49.053989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25057","citing_title":"Random Neural Network Expressivity for Non-Linear Partial Differential Equations","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14567","citing_title":"Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22208","citing_title":"Finite Expression Method with TranNet-based Function Learning for High-Dimensional Partial Differential Equations","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06519","citing_title":"Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD","json":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD.json","graph_json":"https://pith.science/api/pith-number/XNTKRQMXRB3RLQXNW5TMHWB3CD/graph.json","events_json":"https://pith.science/api/pith-number/XNTKRQMXRB3RLQXNW5TMHWB3CD/events.json","paper":"https://pith.science/paper/XNTKRQMX"},"agent_actions":{"view_html":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD","download_json":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD.json","view_paper":"https://pith.science/paper/XNTKRQMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.04374&json=true","fetch_graph":"https://pith.science/api/pith-number/XNTKRQMXRB3RLQXNW5TMHWB3CD/graph.json","fetch_events":"https://pith.science/api/pith-number/XNTKRQMXRB3RLQXNW5TMHWB3CD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD/action/storage_attestation","attest_author":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD/action/author_attestation","sign_citation":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD/action/citation_signature","submit_replication":"https://pith.science/pith/XNTKRQMXRB3RLQXNW5TMHWB3CD/action/replication_record"}},"created_at":"2026-07-04T23:57:49.053989+00:00","updated_at":"2026-07-04T23:57:49.053989+00:00"}