{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GEBISPB5Z2UTVF62FFYT65WHC6","short_pith_number":"pith:GEBISPB5","schema_version":"1.0","canonical_sha256":"3102893c3dcea93a97da29713f76c717bd648d65497fe4028c6852cf2c07f121","source":{"kind":"arxiv","id":"2410.16105","version":1},"attestation_state":"computed","paper":{"title":"Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ronglong Fang, Yuesheng Xu","submitted_at":"2024-10-21T15:34:33Z","abstract_excerpt":"Deep neural networks (DNNs) suffer from the spectral bias, wherein DNNs typically exhibit a tendency to prioritize the learning of lower-frequency components of a function, struggling to capture its high-frequency features. This paper is to address this issue. Notice that a function having only low frequency components may be well-represented by a shallow neural network (SNN), a network having only a few layers. By observing that composition of low frequency functions can effectively approximate a high-frequency function, we propose to learn a function containing high-frequency components by c"},"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":"2410.16105","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-21T15:34:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78364b0932c8b6a73f9c4b284a54c9b8601e1f5f8523bb99add320ea4db713fc","abstract_canon_sha256":"daac5a969144e4d05bc6160683a08510a036bf3040953407405da9b2a5785dab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:29.391241Z","signature_b64":"7D8c66EhOXFbq/N3X+sikd6nfxCz6c7P9Cs0ZP6WWh3F73/kodEkyu19EsnYgTUr5s056Sq8WpVURszgf9D0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3102893c3dcea93a97da29713f76c717bd648d65497fe4028c6852cf2c07f121","last_reissued_at":"2026-07-05T09:23:29.390759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:29.390759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ronglong Fang, Yuesheng Xu","submitted_at":"2024-10-21T15:34:33Z","abstract_excerpt":"Deep neural networks (DNNs) suffer from the spectral bias, wherein DNNs typically exhibit a tendency to prioritize the learning of lower-frequency components of a function, struggling to capture its high-frequency features. This paper is to address this issue. Notice that a function having only low frequency components may be well-represented by a shallow neural network (SNN), a network having only a few layers. By observing that composition of low frequency functions can effectively approximate a high-frequency function, we propose to learn a function containing high-frequency components by c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16105","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/2410.16105/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":"2410.16105","created_at":"2026-07-05T09:23:29.390818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16105v1","created_at":"2026-07-05T09:23:29.390818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16105","created_at":"2026-07-05T09:23:29.390818+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEBISPB5Z2UT","created_at":"2026-07-05T09:23:29.390818+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEBISPB5Z2UTVF62","created_at":"2026-07-05T09:23:29.390818+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEBISPB5","created_at":"2026-07-05T09:23:29.390818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.11015","citing_title":"SUPER Module for Detail-Sensitive and Cost-Efficient U-Net Variant Decoders","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6","json":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6.json","graph_json":"https://pith.science/api/pith-number/GEBISPB5Z2UTVF62FFYT65WHC6/graph.json","events_json":"https://pith.science/api/pith-number/GEBISPB5Z2UTVF62FFYT65WHC6/events.json","paper":"https://pith.science/paper/GEBISPB5"},"agent_actions":{"view_html":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6","download_json":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6.json","view_paper":"https://pith.science/paper/GEBISPB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16105&json=true","fetch_graph":"https://pith.science/api/pith-number/GEBISPB5Z2UTVF62FFYT65WHC6/graph.json","fetch_events":"https://pith.science/api/pith-number/GEBISPB5Z2UTVF62FFYT65WHC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6/action/storage_attestation","attest_author":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6/action/author_attestation","sign_citation":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6/action/citation_signature","submit_replication":"https://pith.science/pith/GEBISPB5Z2UTVF62FFYT65WHC6/action/replication_record"}},"created_at":"2026-07-05T09:23:29.390818+00:00","updated_at":"2026-07-05T09:23:29.390818+00:00"}