{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:B7KD4I5G67CFIVXBXMXLUKBKM4","short_pith_number":"pith:B7KD4I5G","schema_version":"1.0","canonical_sha256":"0fd43e23a6f7c45456e1bb2eba282a67208c465f37df5b165c04591982c8d41b","source":{"kind":"arxiv","id":"1906.09477","version":2},"attestation_state":"computed","paper":{"title":"The phase diagram of approximation rates for deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Anton Zhevnerchuk, Dmitry Yarotsky","submitted_at":"2019-06-22T17:56:14Z","abstract_excerpt":"We explore the phase diagram of approximation rates for deep neural networks and prove several new theoretical results. In particular, we generalize the existing result on the existence of deep discontinuous phase in ReLU networks to functional classes of arbitrary positive smoothness, and identify the boundary between the feasible and infeasible rates. Moreover, we show that all networks with a piecewise polynomial activation function have the same phase diagram. Next, we demonstrate that standard fully-connected architectures with a fixed width independent of smoothness can adapt to smoothne"},"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":"1906.09477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-22T17:56:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b98c2f947a3b4be40856162298e13ef2e1210e555fee6557bdd79174b99a2127","abstract_canon_sha256":"7fabd3b177a15bbdb5f9d7500a5b20538c381224d271d818b0a474a84f149069"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:54.144534Z","signature_b64":"KRuqNRkIkWDC7BUg3MtZBVGbXHbffbyxQ4Uu7MDKNIC3ZAT6zuoRroNa1H7+lVHLPCX1SeMBG77O8+oHCzp0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fd43e23a6f7c45456e1bb2eba282a67208c465f37df5b165c04591982c8d41b","last_reissued_at":"2026-07-05T02:04:54.144105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:54.144105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The phase diagram of approximation rates for deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Anton Zhevnerchuk, Dmitry Yarotsky","submitted_at":"2019-06-22T17:56:14Z","abstract_excerpt":"We explore the phase diagram of approximation rates for deep neural networks and prove several new theoretical results. In particular, we generalize the existing result on the existence of deep discontinuous phase in ReLU networks to functional classes of arbitrary positive smoothness, and identify the boundary between the feasible and infeasible rates. Moreover, we show that all networks with a piecewise polynomial activation function have the same phase diagram. Next, we demonstrate that standard fully-connected architectures with a fixed width independent of smoothness can adapt to smoothne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09477","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/1906.09477/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":"1906.09477","created_at":"2026-07-05T02:04:54.144163+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09477v2","created_at":"2026-07-05T02:04:54.144163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09477","created_at":"2026-07-05T02:04:54.144163+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7KD4I5G67CF","created_at":"2026-07-05T02:04:54.144163+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7KD4I5G67CFIVXB","created_at":"2026-07-05T02:04:54.144163+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7KD4I5G","created_at":"2026-07-05T02:04:54.144163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03549","citing_title":"Fourier Residual Networks Achieve Spectral Accuracy for Discontinuous Functions","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4","json":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4.json","graph_json":"https://pith.science/api/pith-number/B7KD4I5G67CFIVXBXMXLUKBKM4/graph.json","events_json":"https://pith.science/api/pith-number/B7KD4I5G67CFIVXBXMXLUKBKM4/events.json","paper":"https://pith.science/paper/B7KD4I5G"},"agent_actions":{"view_html":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4","download_json":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4.json","view_paper":"https://pith.science/paper/B7KD4I5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09477&json=true","fetch_graph":"https://pith.science/api/pith-number/B7KD4I5G67CFIVXBXMXLUKBKM4/graph.json","fetch_events":"https://pith.science/api/pith-number/B7KD4I5G67CFIVXBXMXLUKBKM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4/action/storage_attestation","attest_author":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4/action/author_attestation","sign_citation":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4/action/citation_signature","submit_replication":"https://pith.science/pith/B7KD4I5G67CFIVXBXMXLUKBKM4/action/replication_record"}},"created_at":"2026-07-05T02:04:54.144163+00:00","updated_at":"2026-07-05T02:04:54.144163+00:00"}