{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:USKTLROHE3NHTPBIGJT44XBBKH","short_pith_number":"pith:USKTLROH","canonical_record":{"source":{"id":"1906.06903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-17T08:49:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e21ac6e30085ddd87adf5c1b72064a907c1e501e038bffde016f6b0b2013145","abstract_canon_sha256":"b3fab74785c7b31cc60b44c40ffc76edeae394d55567e7d72c4f6164d6c56a28"},"schema_version":"1.0"},"canonical_sha256":"a49535c5c726da79bc283267ce5c2151f01d9bcbe87916041306a9bfd6899c81","source":{"kind":"arxiv","id":"1906.06903","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06903","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06903v2","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06903","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"pith_short_12","alias_value":"USKTLROHE3NH","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"USKTLROHE3NHTPBI","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"USKTLROH","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:USKTLROHE3NHTPBIGJT44XBBKH","target":"record","payload":{"canonical_record":{"source":{"id":"1906.06903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-17T08:49:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e21ac6e30085ddd87adf5c1b72064a907c1e501e038bffde016f6b0b2013145","abstract_canon_sha256":"b3fab74785c7b31cc60b44c40ffc76edeae394d55567e7d72c4f6164d6c56a28"},"schema_version":"1.0"},"canonical_sha256":"a49535c5c726da79bc283267ce5c2151f01d9bcbe87916041306a9bfd6899c81","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:53.529024Z","signature_b64":"QudxSnVCGBVpi7zlFjHWh3y3WkZ8wt8ShwCTVecrtR5sa5LfSaFAy/rQwHBVa91g2NOaWHjDW7Q1GJHQeNW1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a49535c5c726da79bc283267ce5c2151f01d9bcbe87916041306a9bfd6899c81","last_reissued_at":"2026-05-17T23:39:53.528595Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:53.528595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.06903","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z6tqe7EYbZtZ53CMTE8WCK9ZNSFQMUdOHCQ+rh5GlkywNIhrvSRdpG7x5LRIFXsp1QVw6JsnsEMjlGbOR251CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T22:39:30.291170Z"},"content_sha256":"409fb8a64f96958df11405d161cc8c34e1ad7717c28bedeecf4636ccc25929ca","schema_version":"1.0","event_id":"sha256:409fb8a64f96958df11405d161cc8c34e1ad7717c28bedeecf4636ccc25929ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:USKTLROHE3NHTPBIGJT44XBBKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smooth function approximation by deep neural networks with general activation functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ilsang Ohn, Yongdai Kim","submitted_at":"2019-06-17T08:49:21Z","abstract_excerpt":"There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation ability of deep neural networks with a broad class of activation functions. This class of activation functions includes most of frequently used activation functions. We derive the required depth, width and sparsity of a deep neural network to approximate any H\\\"older smooth function upto a given approximation error for the large class of activation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06903","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6QfVl/cFX5rCdEhaf6IS1uGhBg//PmD+xkLhzHGmoyhsqPf98qywzKYe+XOhhSUpS2EQqpanRQyPJjYWopKwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T22:39:30.291525Z"},"content_sha256":"4309327c26076f4b77d6861eaceb678a17ba5d35ad31e8f22d8f2f67a0822aef","schema_version":"1.0","event_id":"sha256:4309327c26076f4b77d6861eaceb678a17ba5d35ad31e8f22d8f2f67a0822aef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USKTLROHE3NHTPBIGJT44XBBKH/bundle.json","state_url":"https://pith.science/pith/USKTLROHE3NHTPBIGJT44XBBKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USKTLROHE3NHTPBIGJT44XBBKH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T22:39:30Z","links":{"resolver":"https://pith.science/pith/USKTLROHE3NHTPBIGJT44XBBKH","bundle":"https://pith.science/pith/USKTLROHE3NHTPBIGJT44XBBKH/bundle.json","state":"https://pith.science/pith/USKTLROHE3NHTPBIGJT44XBBKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USKTLROHE3NHTPBIGJT44XBBKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:USKTLROHE3NHTPBIGJT44XBBKH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b3fab74785c7b31cc60b44c40ffc76edeae394d55567e7d72c4f6164d6c56a28","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-17T08:49:21Z","title_canon_sha256":"0e21ac6e30085ddd87adf5c1b72064a907c1e501e038bffde016f6b0b2013145"},"schema_version":"1.0","source":{"id":"1906.06903","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06903","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06903v2","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06903","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"pith_short_12","alias_value":"USKTLROHE3NH","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"USKTLROHE3NHTPBI","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"USKTLROH","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:4309327c26076f4b77d6861eaceb678a17ba5d35ad31e8f22d8f2f67a0822aef","target":"graph","created_at":"2026-05-17T23:39:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation ability of deep neural networks with a broad class of activation functions. This class of activation functions includes most of frequently used activation functions. We derive the required depth, width and sparsity of a deep neural network to approximate any H\\\"older smooth function upto a given approximation error for the large class of activation ","authors_text":"Ilsang Ohn, Yongdai Kim","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-17T08:49:21Z","title":"Smooth function approximation by deep neural networks with general activation functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06903","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:409fb8a64f96958df11405d161cc8c34e1ad7717c28bedeecf4636ccc25929ca","target":"record","created_at":"2026-05-17T23:39:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b3fab74785c7b31cc60b44c40ffc76edeae394d55567e7d72c4f6164d6c56a28","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-17T08:49:21Z","title_canon_sha256":"0e21ac6e30085ddd87adf5c1b72064a907c1e501e038bffde016f6b0b2013145"},"schema_version":"1.0","source":{"id":"1906.06903","kind":"arxiv","version":2}},"canonical_sha256":"a49535c5c726da79bc283267ce5c2151f01d9bcbe87916041306a9bfd6899c81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a49535c5c726da79bc283267ce5c2151f01d9bcbe87916041306a9bfd6899c81","first_computed_at":"2026-05-17T23:39:53.528595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:53.528595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QudxSnVCGBVpi7zlFjHWh3y3WkZ8wt8ShwCTVecrtR5sa5LfSaFAy/rQwHBVa91g2NOaWHjDW7Q1GJHQeNW1DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:53.529024Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.06903","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:409fb8a64f96958df11405d161cc8c34e1ad7717c28bedeecf4636ccc25929ca","sha256:4309327c26076f4b77d6861eaceb678a17ba5d35ad31e8f22d8f2f67a0822aef"],"state_sha256":"66328a922479cc21897a6a51e2c743f58ab4cf6dc04c707c6d7da81487d13390"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g36nqYGRloN3XpmzuYEcOVTLtstEYJi5HahEt2spX0xFQMBw1Z66hMF2/xXT4KhlFXBiWGqP10E6eBUODB+RBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T22:39:30.293421Z","bundle_sha256":"5f784f3c04f7663484dee2ea5c4a598d20ea5225f4a12d7f63784ce1d8b92b62"}}