{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RDCGP3WQE2DLIXOPWJFE2DCBP6","short_pith_number":"pith:RDCGP3WQ","schema_version":"1.0","canonical_sha256":"88c467eed02686b45dcfb24a4d0c417fbbd6869cc7794c925173da78fa998af1","source":{"kind":"arxiv","id":"2407.17213","version":1},"attestation_state":"computed","paper":{"title":"Spectrum-Informed Multistage Neural Networks: Multiscale Function Approximators of Machine Precision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ching-Yao Lai, Jakin Ng, Yongji Wang","submitted_at":"2024-07-24T12:11:09Z","abstract_excerpt":"Deep learning frameworks have become powerful tools for approaching scientific problems such as turbulent flow, which has wide-ranging applications. In practice, however, existing scientific machine learning approaches have difficulty fitting complex, multi-scale dynamical systems to very high precision, as required in scientific contexts. We propose using the novel multistage neural network approach with a spectrum-informed initialization to learn the residue from the previous stage, utilizing the spectral biases associated with neural networks to capture high frequency features in the residu"},"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":"2407.17213","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-24T12:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"7b833df2dd6e69e04cb31a2d6c5e38a47d12e4077f531498019f9271d3a7c2c7","abstract_canon_sha256":"6abe8e7988509ce0c2f34d9c1946268d74adf9302529bdb285090e853607588d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:03.937717Z","signature_b64":"j7cydsAQyS/AIjGQOPfj9x6qOdyWqHrH/DIto+XnzHyIQ3mTnepoRroHdQLQMFSADf9vxiUqNUeruHI6WIb/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88c467eed02686b45dcfb24a4d0c417fbbd6869cc7794c925173da78fa998af1","last_reissued_at":"2026-07-05T08:48:03.937238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:03.937238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectrum-Informed Multistage Neural Networks: Multiscale Function Approximators of Machine Precision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ching-Yao Lai, Jakin Ng, Yongji Wang","submitted_at":"2024-07-24T12:11:09Z","abstract_excerpt":"Deep learning frameworks have become powerful tools for approaching scientific problems such as turbulent flow, which has wide-ranging applications. In practice, however, existing scientific machine learning approaches have difficulty fitting complex, multi-scale dynamical systems to very high precision, as required in scientific contexts. We propose using the novel multistage neural network approach with a spectrum-informed initialization to learn the residue from the previous stage, utilizing the spectral biases associated with neural networks to capture high frequency features in the residu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17213","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/2407.17213/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":"2407.17213","created_at":"2026-07-05T08:48:03.937293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17213v1","created_at":"2026-07-05T08:48:03.937293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17213","created_at":"2026-07-05T08:48:03.937293+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDCGP3WQE2DL","created_at":"2026-07-05T08:48:03.937293+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDCGP3WQE2DLIXOP","created_at":"2026-07-05T08:48:03.937293+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDCGP3WQ","created_at":"2026-07-05T08:48:03.937293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08935","citing_title":"PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08935","citing_title":"PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":272,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6","json":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6.json","graph_json":"https://pith.science/api/pith-number/RDCGP3WQE2DLIXOPWJFE2DCBP6/graph.json","events_json":"https://pith.science/api/pith-number/RDCGP3WQE2DLIXOPWJFE2DCBP6/events.json","paper":"https://pith.science/paper/RDCGP3WQ"},"agent_actions":{"view_html":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6","download_json":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6.json","view_paper":"https://pith.science/paper/RDCGP3WQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17213&json=true","fetch_graph":"https://pith.science/api/pith-number/RDCGP3WQE2DLIXOPWJFE2DCBP6/graph.json","fetch_events":"https://pith.science/api/pith-number/RDCGP3WQE2DLIXOPWJFE2DCBP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6/action/storage_attestation","attest_author":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6/action/author_attestation","sign_citation":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6/action/citation_signature","submit_replication":"https://pith.science/pith/RDCGP3WQE2DLIXOPWJFE2DCBP6/action/replication_record"}},"created_at":"2026-07-05T08:48:03.937293+00:00","updated_at":"2026-07-05T08:48:03.937293+00:00"}