{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PTKLTGGIOM2AURDJAWWVPPN5FJ","short_pith_number":"pith:PTKLTGGI","canonical_record":{"source":{"id":"1909.05136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T05:21:49Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"b6f26f1f40014f746f19ecbdcf3cd992b31133e03d39bb1071c91dc28e01aeb0","abstract_canon_sha256":"ef4482d50bd56818cd3e8a70c5743da59a1114f373af1cdc6c3d27bac1a1ee41"},"schema_version":"1.0"},"canonical_sha256":"7cd4b998c873340a446905ad57bdbd2a58185f1fffb700b2becd4fcd62e1e0af","source":{"kind":"arxiv","id":"1909.05136","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.05136","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"arxiv_version","alias_value":"1909.05136v1","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05136","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"pith_short_12","alias_value":"PTKLTGGIOM2A","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"pith_short_16","alias_value":"PTKLTGGIOM2AURDJ","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"pith_short_8","alias_value":"PTKLTGGI","created_at":"2026-07-05T01:56:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PTKLTGGIOM2AURDJAWWVPPN5FJ","target":"record","payload":{"canonical_record":{"source":{"id":"1909.05136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T05:21:49Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"b6f26f1f40014f746f19ecbdcf3cd992b31133e03d39bb1071c91dc28e01aeb0","abstract_canon_sha256":"ef4482d50bd56818cd3e8a70c5743da59a1114f373af1cdc6c3d27bac1a1ee41"},"schema_version":"1.0"},"canonical_sha256":"7cd4b998c873340a446905ad57bdbd2a58185f1fffb700b2becd4fcd62e1e0af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:28.072999Z","signature_b64":"B0XFrwXikORigrxFS8AhDeeAwgGTqkqjLk6eqKjaaZG9HVOAEmO+aIWptHE0gd9eU2qqeacn2YcB2by7ZWurBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cd4b998c873340a446905ad57bdbd2a58185f1fffb700b2becd4fcd62e1e0af","last_reissued_at":"2026-07-05T01:56:28.072661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:28.072661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.05136","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:56:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lzlY6+v0NDs8L/VostsBnmZit3zCxPITG0dQf1vuOWL+D7OmxxsWlaDS8LKnrLj7mgYRI5EAHS0xQAEOBFetDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:36:34.798117Z"},"content_sha256":"027db5d0ec0ac0438c01349b19ab8eb48155261b6db2f0bfdd35a0b89bbda0c7","schema_version":"1.0","event_id":"sha256:027db5d0ec0ac0438c01349b19ab8eb48155261b6db2f0bfdd35a0b89bbda0c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PTKLTGGIOM2AURDJAWWVPPN5FJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Bo Li, Haijun Yu, Shanshan Tang","submitted_at":"2019-09-09T05:21:49Z","abstract_excerpt":"Deep neural network with rectified linear units (ReLU) is getting more and more popular recently. However, the derivatives of the function represented by a ReLU network are not continuous, which limit the usage of ReLU network to situations only when smoothness is not required. In this paper, we construct deep neural networks with rectified power units (RePU), which can give better approximations for smooth functions. Optimal algorithms are proposed to explicitly build neural networks with sparsely connected RePUs, which we call PowerNets, to represent polynomials with no approximation error. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05136","kind":"arxiv","version":1},"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/1909.05136/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:56:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e6tloSdA0O2sUGOb7wHkrdol+wm/Yx3rMwvBDiPDBD0sZSsmcpG068dcV2kh9wAZqLhd1AgPDZ4DZyMsxZijBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:36:34.798617Z"},"content_sha256":"6fe903cb4178c7fa23cfabd77729320c969491d45da8e5d4af5f44313a764ff0","schema_version":"1.0","event_id":"sha256:6fe903cb4178c7fa23cfabd77729320c969491d45da8e5d4af5f44313a764ff0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTKLTGGIOM2AURDJAWWVPPN5FJ/bundle.json","state_url":"https://pith.science/pith/PTKLTGGIOM2AURDJAWWVPPN5FJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTKLTGGIOM2AURDJAWWVPPN5FJ/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":"2026-08-22T11:36:34Z","links":{"resolver":"https://pith.science/pith/PTKLTGGIOM2AURDJAWWVPPN5FJ","bundle":"https://pith.science/pith/PTKLTGGIOM2AURDJAWWVPPN5FJ/bundle.json","state":"https://pith.science/pith/PTKLTGGIOM2AURDJAWWVPPN5FJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTKLTGGIOM2AURDJAWWVPPN5FJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PTKLTGGIOM2AURDJAWWVPPN5FJ","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":"ef4482d50bd56818cd3e8a70c5743da59a1114f373af1cdc6c3d27bac1a1ee41","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T05:21:49Z","title_canon_sha256":"b6f26f1f40014f746f19ecbdcf3cd992b31133e03d39bb1071c91dc28e01aeb0"},"schema_version":"1.0","source":{"id":"1909.05136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.05136","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"arxiv_version","alias_value":"1909.05136v1","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05136","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"pith_short_12","alias_value":"PTKLTGGIOM2A","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"pith_short_16","alias_value":"PTKLTGGIOM2AURDJ","created_at":"2026-07-05T01:56:28Z"},{"alias_kind":"pith_short_8","alias_value":"PTKLTGGI","created_at":"2026-07-05T01:56:28Z"}],"graph_snapshots":[{"event_id":"sha256:6fe903cb4178c7fa23cfabd77729320c969491d45da8e5d4af5f44313a764ff0","target":"graph","created_at":"2026-07-05T01:56:28Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.05136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural network with rectified linear units (ReLU) is getting more and more popular recently. However, the derivatives of the function represented by a ReLU network are not continuous, which limit the usage of ReLU network to situations only when smoothness is not required. In this paper, we construct deep neural networks with rectified power units (RePU), which can give better approximations for smooth functions. Optimal algorithms are proposed to explicitly build neural networks with sparsely connected RePUs, which we call PowerNets, to represent polynomials with no approximation error. ","authors_text":"Bo Li, Haijun Yu, Shanshan Tang","cross_cats":["cs.NA","math.NA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T05:21:49Z","title":"PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05136","kind":"arxiv","version":1},"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":"sha256:027db5d0ec0ac0438c01349b19ab8eb48155261b6db2f0bfdd35a0b89bbda0c7","target":"record","created_at":"2026-07-05T01:56:28Z","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":"ef4482d50bd56818cd3e8a70c5743da59a1114f373af1cdc6c3d27bac1a1ee41","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T05:21:49Z","title_canon_sha256":"b6f26f1f40014f746f19ecbdcf3cd992b31133e03d39bb1071c91dc28e01aeb0"},"schema_version":"1.0","source":{"id":"1909.05136","kind":"arxiv","version":1}},"canonical_sha256":"7cd4b998c873340a446905ad57bdbd2a58185f1fffb700b2becd4fcd62e1e0af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cd4b998c873340a446905ad57bdbd2a58185f1fffb700b2becd4fcd62e1e0af","first_computed_at":"2026-07-05T01:56:28.072661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:28.072661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B0XFrwXikORigrxFS8AhDeeAwgGTqkqjLk6eqKjaaZG9HVOAEmO+aIWptHE0gd9eU2qqeacn2YcB2by7ZWurBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:28.072999Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.05136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:027db5d0ec0ac0438c01349b19ab8eb48155261b6db2f0bfdd35a0b89bbda0c7","sha256:6fe903cb4178c7fa23cfabd77729320c969491d45da8e5d4af5f44313a764ff0"],"state_sha256":"d3e0ec4da85ae72f0cbe7d5b50b93d8637412ae631387b237c2d86391e9628fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUOY/CdBqrjvUoiCilAfLFznH+K1cNzxE627P5EDJDcZkZAxS5maJEQpjO05IPkAozcE+z2iXC3TRlAtO/BADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T11:36:34.803080Z","bundle_sha256":"f5243d32ef3deae7d707f47fc5783f5d52c9715a92ebed7d7f2a490411f76f8c"}}