{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GI26RF4UBRZZ542ABXMZSY6XSV","short_pith_number":"pith:GI26RF4U","schema_version":"1.0","canonical_sha256":"3235e897940c739ef3400dd99963d7957f8b6a78544edbcaf16948656a222924","source":{"kind":"arxiv","id":"2305.00608","version":3},"attestation_state":"computed","paper":{"title":"Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guohao Shen, Jian Huang, Yuanyuan Lin, Yuling Jiao","submitted_at":"2023-05-01T00:09:48Z","abstract_excerpt":"We study the properties of differentiable neural networks activated by rectified power unit (RePU) functions. We show that the partial derivatives of RePU neural networks can be represented by RePUs mixed-activated networks and derive upper bounds for the complexity of the function class of derivatives of RePUs networks. We establish error bounds for simultaneously approximating $C^s$ smooth functions and their derivatives using RePU-activated deep neural networks. Furthermore, we derive improved approximation error bounds when data has an approximate low-dimensional support, demonstrating the"},"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":"2305.00608","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-01T00:09:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d9836529435b71ab5c99344b3fd616e4fa38323f1ef8729217d107b1f6d8ff9a","abstract_canon_sha256":"f71cdfa49dff437cabb431950081ebe286f8a43df10d80b782dccddabff41474"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:13.546514Z","signature_b64":"aFu6CgdN6Pix9w8Xljjjxx8CCYjhF+D9Szd2hzeElf68LzL1xXTR2fWTa9lZ/V3IY14SZN8FtKhz7zRUyI/bCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3235e897940c739ef3400dd99963d7957f8b6a78544edbcaf16948656a222924","last_reissued_at":"2026-07-05T08:10:13.546049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:13.546049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guohao Shen, Jian Huang, Yuanyuan Lin, Yuling Jiao","submitted_at":"2023-05-01T00:09:48Z","abstract_excerpt":"We study the properties of differentiable neural networks activated by rectified power unit (RePU) functions. We show that the partial derivatives of RePU neural networks can be represented by RePUs mixed-activated networks and derive upper bounds for the complexity of the function class of derivatives of RePUs networks. We establish error bounds for simultaneously approximating $C^s$ smooth functions and their derivatives using RePU-activated deep neural networks. Furthermore, we derive improved approximation error bounds when data has an approximate low-dimensional support, demonstrating the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00608","kind":"arxiv","version":3},"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/2305.00608/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":"2305.00608","created_at":"2026-07-05T08:10:13.546102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00608v3","created_at":"2026-07-05T08:10:13.546102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00608","created_at":"2026-07-05T08:10:13.546102+00:00"},{"alias_kind":"pith_short_12","alias_value":"GI26RF4UBRZZ","created_at":"2026-07-05T08:10:13.546102+00:00"},{"alias_kind":"pith_short_16","alias_value":"GI26RF4UBRZZ542A","created_at":"2026-07-05T08:10:13.546102+00:00"},{"alias_kind":"pith_short_8","alias_value":"GI26RF4U","created_at":"2026-07-05T08:10:13.546102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06781","citing_title":"On Explicit Super-Expressive Approximation for Neural Networks","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2606.05599","citing_title":"Mitigating the Curse of Dimensionality in Uniform Convergence of Deep Neural Networks via Smooth Activations","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18143","citing_title":"Distributional Off-Policy Evaluation with Deep Quantile Process Regression","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV","json":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV.json","graph_json":"https://pith.science/api/pith-number/GI26RF4UBRZZ542ABXMZSY6XSV/graph.json","events_json":"https://pith.science/api/pith-number/GI26RF4UBRZZ542ABXMZSY6XSV/events.json","paper":"https://pith.science/paper/GI26RF4U"},"agent_actions":{"view_html":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV","download_json":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV.json","view_paper":"https://pith.science/paper/GI26RF4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00608&json=true","fetch_graph":"https://pith.science/api/pith-number/GI26RF4UBRZZ542ABXMZSY6XSV/graph.json","fetch_events":"https://pith.science/api/pith-number/GI26RF4UBRZZ542ABXMZSY6XSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV/action/storage_attestation","attest_author":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV/action/author_attestation","sign_citation":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV/action/citation_signature","submit_replication":"https://pith.science/pith/GI26RF4UBRZZ542ABXMZSY6XSV/action/replication_record"}},"created_at":"2026-07-05T08:10:13.546102+00:00","updated_at":"2026-07-05T08:10:13.546102+00:00"}