{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:D6567CEBSYXIPM7E7XUEMVQWSC","short_pith_number":"pith:D6567CEB","schema_version":"1.0","canonical_sha256":"1fbbef8881962e87b3e4fde846561690bdeaa04fa5944abf7cd572edd73cdc12","source":{"kind":"arxiv","id":"1904.02311","version":7},"attestation_state":"computed","paper":{"title":"Approximation Rates for Neural Networks with General Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.CA","authors_text":"Jinchao Xu, Jonathan W. Siegel","submitted_at":"2019-04-04T02:18:08Z","abstract_excerpt":"We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer neural network with a polynomially-decaying non-sigmoidal activation function. We extend the dimension independent approximation rates previously obtained to this new class of activation functions. Our second result gives a weaker, but still dimension independent, approximation rate for a larger class of activation functions, removing the polynomial decay assumption. This result applies to any bounded, integrable ac"},"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":"1904.02311","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.CA","submitted_at":"2019-04-04T02:18:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2490c4c1492b19f69d5f382afd0e5b522bfcf4b6addd9fa7b264e1fceab04400","abstract_canon_sha256":"39870f4f7756edf9ddc30538750e4dbd02bafc57b2c1c4478247f8f877dca2f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:03.085147Z","signature_b64":"XB5Mrz3vdZgOVmcOM4uoFcAeLsM9QnkU1Y6qrL0oMxPlkJrPnAHhJ3tNuMDUFZZ7IvVRP2nsfKem8DkXFi8WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fbbef8881962e87b3e4fde846561690bdeaa04fa5944abf7cd572edd73cdc12","last_reissued_at":"2026-07-05T02:04:03.084745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:03.084745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation Rates for Neural Networks with General Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.CA","authors_text":"Jinchao Xu, Jonathan W. Siegel","submitted_at":"2019-04-04T02:18:08Z","abstract_excerpt":"We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer neural network with a polynomially-decaying non-sigmoidal activation function. We extend the dimension independent approximation rates previously obtained to this new class of activation functions. Our second result gives a weaker, but still dimension independent, approximation rate for a larger class of activation functions, removing the polynomial decay assumption. This result applies to any bounded, integrable ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02311","kind":"arxiv","version":7},"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/1904.02311/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":"1904.02311","created_at":"2026-07-05T02:04:03.084806+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02311v7","created_at":"2026-07-05T02:04:03.084806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02311","created_at":"2026-07-05T02:04:03.084806+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6567CEBSYXI","created_at":"2026-07-05T02:04:03.084806+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6567CEBSYXIPM7E","created_at":"2026-07-05T02:04:03.084806+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6567CEB","created_at":"2026-07-05T02:04:03.084806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC","json":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC.json","graph_json":"https://pith.science/api/pith-number/D6567CEBSYXIPM7E7XUEMVQWSC/graph.json","events_json":"https://pith.science/api/pith-number/D6567CEBSYXIPM7E7XUEMVQWSC/events.json","paper":"https://pith.science/paper/D6567CEB"},"agent_actions":{"view_html":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC","download_json":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC.json","view_paper":"https://pith.science/paper/D6567CEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02311&json=true","fetch_graph":"https://pith.science/api/pith-number/D6567CEBSYXIPM7E7XUEMVQWSC/graph.json","fetch_events":"https://pith.science/api/pith-number/D6567CEBSYXIPM7E7XUEMVQWSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC/action/storage_attestation","attest_author":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC/action/author_attestation","sign_citation":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC/action/citation_signature","submit_replication":"https://pith.science/pith/D6567CEBSYXIPM7E7XUEMVQWSC/action/replication_record"}},"created_at":"2026-07-05T02:04:03.084806+00:00","updated_at":"2026-07-05T02:04:03.084806+00:00"}