{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FS5P5IH4K67ST3PE4HIIQVJSHU","short_pith_number":"pith:FS5P5IH4","schema_version":"1.0","canonical_sha256":"2cbafea0fc57bf29ede4e1d08855323d0ca303c1d2f97e7241407ac67002823f","source":{"kind":"arxiv","id":"2201.07395","version":4},"attestation_state":"computed","paper":{"title":"Overview frequency principle/spectral bias in deep learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tao Luo, Yaoyu Zhang, Zhi-Qin John Xu","submitted_at":"2022-01-19T03:08:33Z","abstract_excerpt":"Understanding deep learning is increasingly emergent as it penetrates more and more into industry and science. In recent years, a research line from Fourier analysis sheds lights on this magical \"black box\" by showing a Frequency Principle (F-Principle or spectral bias) of the training behavior of deep neural networks (DNNs) -- DNNs often fit functions from low to high frequency during the training. The F-Principle is first demonstrated by onedimensional synthetic data followed by the verification in high-dimensional real datasets. A series of works subsequently enhance the validity of the F-P"},"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":"2201.07395","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-19T03:08:33Z","cross_cats_sorted":[],"title_canon_sha256":"54d1c6a3fe6344f65e41f9c9b6d30bc80542ec3cfff1b1ea3c15e33bc9586656","abstract_canon_sha256":"410510f67ea22a01e67f63f1aa30c29034731e21148597eef45626583717e005"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:08.053520Z","signature_b64":"bWTN+dNd4r/IBmLskVBP7NM/Roy3YtuSp85MdBqEdT+la7HSaeeeCzKf5eMwSQpvfhiBw1q93b1w6ANTuaB1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cbafea0fc57bf29ede4e1d08855323d0ca303c1d2f97e7241407ac67002823f","last_reissued_at":"2026-07-05T09:34:08.053040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:08.053040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overview frequency principle/spectral bias in deep learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tao Luo, Yaoyu Zhang, Zhi-Qin John Xu","submitted_at":"2022-01-19T03:08:33Z","abstract_excerpt":"Understanding deep learning is increasingly emergent as it penetrates more and more into industry and science. In recent years, a research line from Fourier analysis sheds lights on this magical \"black box\" by showing a Frequency Principle (F-Principle or spectral bias) of the training behavior of deep neural networks (DNNs) -- DNNs often fit functions from low to high frequency during the training. The F-Principle is first demonstrated by onedimensional synthetic data followed by the verification in high-dimensional real datasets. A series of works subsequently enhance the validity of the F-P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07395","kind":"arxiv","version":4},"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/2201.07395/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":"2201.07395","created_at":"2026-07-05T09:34:08.053097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.07395v4","created_at":"2026-07-05T09:34:08.053097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07395","created_at":"2026-07-05T09:34:08.053097+00:00"},{"alias_kind":"pith_short_12","alias_value":"FS5P5IH4K67S","created_at":"2026-07-05T09:34:08.053097+00:00"},{"alias_kind":"pith_short_16","alias_value":"FS5P5IH4K67ST3PE","created_at":"2026-07-05T09:34:08.053097+00:00"},{"alias_kind":"pith_short_8","alias_value":"FS5P5IH4","created_at":"2026-07-05T09:34:08.053097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12997","citing_title":"Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU","json":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU.json","graph_json":"https://pith.science/api/pith-number/FS5P5IH4K67ST3PE4HIIQVJSHU/graph.json","events_json":"https://pith.science/api/pith-number/FS5P5IH4K67ST3PE4HIIQVJSHU/events.json","paper":"https://pith.science/paper/FS5P5IH4"},"agent_actions":{"view_html":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU","download_json":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU.json","view_paper":"https://pith.science/paper/FS5P5IH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.07395&json=true","fetch_graph":"https://pith.science/api/pith-number/FS5P5IH4K67ST3PE4HIIQVJSHU/graph.json","fetch_events":"https://pith.science/api/pith-number/FS5P5IH4K67ST3PE4HIIQVJSHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU/action/storage_attestation","attest_author":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU/action/author_attestation","sign_citation":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU/action/citation_signature","submit_replication":"https://pith.science/pith/FS5P5IH4K67ST3PE4HIIQVJSHU/action/replication_record"}},"created_at":"2026-07-05T09:34:08.053097+00:00","updated_at":"2026-07-05T09:34:08.053097+00:00"}