{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6ZTQJG7KSNFFLY3TDZ4AMSMKW5","short_pith_number":"pith:6ZTQJG7K","schema_version":"1.0","canonical_sha256":"f667049bea934a55e3731e7806498ab75fe689b65cd1b7a0f2471cf23eb43bfd","source":{"kind":"arxiv","id":"1906.09235","version":2},"attestation_state":"computed","paper":{"title":"Theory of the Frequency Principle for General Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tao Luo, Yaoyu Zhang, Zheng Ma, Zhi-Qin John Xu","submitted_at":"2019-06-21T16:46:04Z","abstract_excerpt":"Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, some empirical studies of DNNs reported a universal phenomenon of Frequency Principle (F-Principle): a DNN tends to learn a target function from low to high frequencies during the training. The F-Principle has been very useful in providing both qualitative and quantitative understandings of DNNs. In this paper, we rigorously investigate the F-Principle for the training dynamics of a general DNN at three stages: initial stage, intermediate stage, and final stage. For each stage, a theorem is provide"},"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":"1906.09235","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T16:46:04Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"61d645102792e881594b04fdc11e0dcc33014ded13e658811775052ccc93f9a0","abstract_canon_sha256":"4b46f3bba0ef873ae0a15819f17d45d475fc9b5a5927917a656a91756d77d5bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:41.726238Z","signature_b64":"47s++KDmTT6OrugUIeUEHcrSRdAjh6Nn6r7X85/ajaZytXotry9Vm7emibJi+IraKEmiFB7Gu9Hp2d4/RSAgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f667049bea934a55e3731e7806498ab75fe689b65cd1b7a0f2471cf23eb43bfd","last_reissued_at":"2026-05-17T23:41:41.725764Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:41.725764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theory of the Frequency Principle for General Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tao Luo, Yaoyu Zhang, Zheng Ma, Zhi-Qin John Xu","submitted_at":"2019-06-21T16:46:04Z","abstract_excerpt":"Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, some empirical studies of DNNs reported a universal phenomenon of Frequency Principle (F-Principle): a DNN tends to learn a target function from low to high frequencies during the training. The F-Principle has been very useful in providing both qualitative and quantitative understandings of DNNs. In this paper, we rigorously investigate the F-Principle for the training dynamics of a general DNN at three stages: initial stage, intermediate stage, and final stage. For each stage, a theorem is provide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09235","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1906.09235","created_at":"2026-05-17T23:41:41.725831+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09235v2","created_at":"2026-05-17T23:41:41.725831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09235","created_at":"2026-05-17T23:41:41.725831+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZTQJG7KSNFF","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZTQJG7KSNFFLY3T","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZTQJG7K","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.24814","citing_title":"A Greedy PDE Router for Blending Neural Operators and Classical Methods","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18686","citing_title":"Neural Spectral Bias and Conformal Correlators I: Introduction and Applications","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5","json":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5.json","graph_json":"https://pith.science/api/pith-number/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/graph.json","events_json":"https://pith.science/api/pith-number/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/events.json","paper":"https://pith.science/paper/6ZTQJG7K"},"agent_actions":{"view_html":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5","download_json":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5.json","view_paper":"https://pith.science/paper/6ZTQJG7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09235&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/action/storage_attestation","attest_author":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/action/author_attestation","sign_citation":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/action/citation_signature","submit_replication":"https://pith.science/pith/6ZTQJG7KSNFFLY3TDZ4AMSMKW5/action/replication_record"}},"created_at":"2026-05-17T23:41:41.725831+00:00","updated_at":"2026-05-17T23:41:41.725831+00:00"}