{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WHS4MPFNXK63F5ROUAFUX6P2XZ","short_pith_number":"pith:WHS4MPFN","schema_version":"1.0","canonical_sha256":"b1e5c63cadbabdb2f62ea00b4bf9fabe4f87d1aa2ab4c68abdc2955d99aa6f8b","source":{"kind":"arxiv","id":"2006.12231","version":6},"attestation_state":"computed","paper":{"title":"Deep Network with Approximation Error Being Reciprocal of Width to Power of Square Root of Depth","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haizhao Yang, Shijun Zhang, Zuowei Shen","submitted_at":"2020-06-22T13:27:33Z","abstract_excerpt":"A new network with super approximation power is introduced. This network is built with Floor ($\\lfloor x\\rfloor$) or ReLU ($\\max\\{0,x\\}$) activation function in each neuron and hence we call such networks Floor-ReLU networks. For any hyper-parameters $N\\in\\mathbb{N}^+$ and $L\\in\\mathbb{N}^+$, it is shown that Floor-ReLU networks with width $\\max\\{d,\\, 5N+13\\}$ and depth $64dL+3$ can uniformly approximate a H\\\"older function $f$ on $[0,1]^d$ with an approximation error $3\\lambda d^{\\alpha/2}N^{-\\alpha\\sqrt{L}}$, where $\\alpha \\in(0,1]$ and $\\lambda$ are the H\\\"older order and constant, respecti"},"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":"2006.12231","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T13:27:33Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"c4f1d0c1448452d84a7f3f74314792d96aa4b567afe3cbc8585f5f924e50c7bd","abstract_canon_sha256":"a893c9b01bdc7de6931406f4aeafefea2251e1e050a5c06fea726ba894dc0dd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:48.624252Z","signature_b64":"qsgAX0y823/xUtMFGRbY0agKLVxj+9vx7fOsucOUe0rHHiTFaeVWcjMRS65LXEXdCGEUFNOAvsvhxSvymrXiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1e5c63cadbabdb2f62ea00b4bf9fabe4f87d1aa2ab4c68abdc2955d99aa6f8b","last_reissued_at":"2026-07-05T02:26:48.623769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:48.623769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Network with Approximation Error Being Reciprocal of Width to Power of Square Root of Depth","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haizhao Yang, Shijun Zhang, Zuowei Shen","submitted_at":"2020-06-22T13:27:33Z","abstract_excerpt":"A new network with super approximation power is introduced. This network is built with Floor ($\\lfloor x\\rfloor$) or ReLU ($\\max\\{0,x\\}$) activation function in each neuron and hence we call such networks Floor-ReLU networks. For any hyper-parameters $N\\in\\mathbb{N}^+$ and $L\\in\\mathbb{N}^+$, it is shown that Floor-ReLU networks with width $\\max\\{d,\\, 5N+13\\}$ and depth $64dL+3$ can uniformly approximate a H\\\"older function $f$ on $[0,1]^d$ with an approximation error $3\\lambda d^{\\alpha/2}N^{-\\alpha\\sqrt{L}}$, where $\\alpha \\in(0,1]$ and $\\lambda$ are the H\\\"older order and constant, respecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12231","kind":"arxiv","version":6},"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/2006.12231/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":"2006.12231","created_at":"2026-07-05T02:26:48.623827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12231v6","created_at":"2026-07-05T02:26:48.623827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12231","created_at":"2026-07-05T02:26:48.623827+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHS4MPFNXK63","created_at":"2026-07-05T02:26:48.623827+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHS4MPFNXK63F5RO","created_at":"2026-07-05T02:26:48.623827+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHS4MPFN","created_at":"2026-07-05T02:26:48.623827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01357","citing_title":"Do Neural Networks Really Beat the Curse of Dimensionality? A Bit-Complexity View","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ","json":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ.json","graph_json":"https://pith.science/api/pith-number/WHS4MPFNXK63F5ROUAFUX6P2XZ/graph.json","events_json":"https://pith.science/api/pith-number/WHS4MPFNXK63F5ROUAFUX6P2XZ/events.json","paper":"https://pith.science/paper/WHS4MPFN"},"agent_actions":{"view_html":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ","download_json":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ.json","view_paper":"https://pith.science/paper/WHS4MPFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12231&json=true","fetch_graph":"https://pith.science/api/pith-number/WHS4MPFNXK63F5ROUAFUX6P2XZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WHS4MPFNXK63F5ROUAFUX6P2XZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ/action/storage_attestation","attest_author":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ/action/author_attestation","sign_citation":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ/action/citation_signature","submit_replication":"https://pith.science/pith/WHS4MPFNXK63F5ROUAFUX6P2XZ/action/replication_record"}},"created_at":"2026-07-05T02:26:48.623827+00:00","updated_at":"2026-07-05T02:26:48.623827+00:00"}