{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:T6STN56F4MRKXJP2I26JPTQVPG","short_pith_number":"pith:T6STN56F","schema_version":"1.0","canonical_sha256":"9fa536f7c5e322aba5fa46bc97ce15798d584172b81280caf35749e60453510f","source":{"kind":"arxiv","id":"1911.05467","version":3},"attestation_state":"computed","paper":{"title":"ChebNet: Efficient and Stable Constructions of Deep Neural Networks with Rectified Power Units via Chebyshev Approximations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Bo Li, Haijun Yu, Shanshan Tang","submitted_at":"2019-11-07T06:30:47Z","abstract_excerpt":"In a previous study [B. Li, S. Tang and H. Yu, Commun. Comput. Phy. 27(2):379-411, 2020], it is shown that deep neural networks built with rectified power units (RePU) as activation functions can give better approximation for sufficient smooth functions than those built with rectified linear units, by converting polynomial approximations using power series into deep neural networks with optimal complexity and no approximation error. However, in practice, power series approximations are not easy to obtain due to the associated stability issue. In this paper, we propose a new and more stable way"},"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":"1911.05467","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2019-11-07T06:30:47Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"92c9bb618f0667db1b49fbb292d75709baad875b9fc6a6787532da1c6b162cac","abstract_canon_sha256":"172ee675baf59c334c0b4d01793c332b90a209f5c2ba463ed01796dfd5f39836"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:12.995452Z","signature_b64":"iysW5R893mO5XDxjP8EM60YgR1vArwgNwiFqZlQZZEEpI3A9BkE0ssRIdaCqZ2ra1V4nas7In/JJ1tqDziTTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fa536f7c5e322aba5fa46bc97ce15798d584172b81280caf35749e60453510f","last_reissued_at":"2026-05-20T00:00:12.994336Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:12.994336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChebNet: Efficient and Stable Constructions of Deep Neural Networks with Rectified Power Units via Chebyshev Approximations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Bo Li, Haijun Yu, Shanshan Tang","submitted_at":"2019-11-07T06:30:47Z","abstract_excerpt":"In a previous study [B. Li, S. Tang and H. Yu, Commun. Comput. Phy. 27(2):379-411, 2020], it is shown that deep neural networks built with rectified power units (RePU) as activation functions can give better approximation for sufficient smooth functions than those built with rectified linear units, by converting polynomial approximations using power series into deep neural networks with optimal complexity and no approximation error. However, in practice, power series approximations are not easy to obtain due to the associated stability issue. In this paper, we propose a new and more stable way"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05467","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/1911.05467/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":"1911.05467","created_at":"2026-05-20T00:00:12.994490+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05467v3","created_at":"2026-05-20T00:00:12.994490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05467","created_at":"2026-05-20T00:00:12.994490+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6STN56F4MRK","created_at":"2026-05-20T00:00:12.994490+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6STN56F4MRKXJP2","created_at":"2026-05-20T00:00:12.994490+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6STN56F","created_at":"2026-05-20T00:00:12.994490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18143","citing_title":"Distributional Off-Policy Evaluation with Deep Quantile Process Regression","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG","json":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG.json","graph_json":"https://pith.science/api/pith-number/T6STN56F4MRKXJP2I26JPTQVPG/graph.json","events_json":"https://pith.science/api/pith-number/T6STN56F4MRKXJP2I26JPTQVPG/events.json","paper":"https://pith.science/paper/T6STN56F"},"agent_actions":{"view_html":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG","download_json":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG.json","view_paper":"https://pith.science/paper/T6STN56F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05467&json=true","fetch_graph":"https://pith.science/api/pith-number/T6STN56F4MRKXJP2I26JPTQVPG/graph.json","fetch_events":"https://pith.science/api/pith-number/T6STN56F4MRKXJP2I26JPTQVPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG/action/storage_attestation","attest_author":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG/action/author_attestation","sign_citation":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG/action/citation_signature","submit_replication":"https://pith.science/pith/T6STN56F4MRKXJP2I26JPTQVPG/action/replication_record"}},"created_at":"2026-05-20T00:00:12.994490+00:00","updated_at":"2026-05-20T00:00:12.994490+00:00"}