{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y6R6NDEJDZ3BF6UIYS7Q4FU3WE","short_pith_number":"pith:Y6R6NDEJ","schema_version":"1.0","canonical_sha256":"c7a3e68c891e7612fa88c4bf0e169bb11f52e2368b5ada0f0c0755ea3f9a8c51","source":{"kind":"arxiv","id":"2210.10890","version":3},"attestation_state":"computed","paper":{"title":"Mitigating spectral bias for the multiscale operator learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Bo Xu, Lei Zhang, Shuhao Cao, Xinliang Liu","submitted_at":"2022-10-19T21:09:29Z","abstract_excerpt":"Neural operators have emerged as a powerful tool for learning the mapping between infinite-dimensional parameter and solution spaces of partial differential equations (PDEs). In this work, we focus on multiscale PDEs that have important applications such as reservoir modeling and turbulence prediction. We demonstrate that for such PDEs, the spectral bias towards low-frequency components presents a significant challenge for existing neural operators. To address this challenge, we propose a hierarchical attention neural operator (HANO) inspired by the hierarchical matrix approach. HANO features "},"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":"2210.10890","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-19T21:09:29Z","cross_cats_sorted":["cs.AI","cs.NA","math.NA"],"title_canon_sha256":"3157f87cc91fb3728eabeb21a7a475761f1222f741214a97b7dabb8939a6865b","abstract_canon_sha256":"7fd45b3380c200ca2cedd2ca447982c5eab68c16607c8cfdc4f930539dee2603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:13.183729Z","signature_b64":"t4AI45Ux650Ox8vEm8DRD4i+vYQ0ES9tKVKwrhvdUhDH+maFm6q5KMMjhQ6dreRcRp11Vs+GdEchNxRgNRydCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7a3e68c891e7612fa88c4bf0e169bb11f52e2368b5ada0f0c0755ea3f9a8c51","last_reissued_at":"2026-07-05T08:29:13.183215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:13.183215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating spectral bias for the multiscale operator learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Bo Xu, Lei Zhang, Shuhao Cao, Xinliang Liu","submitted_at":"2022-10-19T21:09:29Z","abstract_excerpt":"Neural operators have emerged as a powerful tool for learning the mapping between infinite-dimensional parameter and solution spaces of partial differential equations (PDEs). In this work, we focus on multiscale PDEs that have important applications such as reservoir modeling and turbulence prediction. We demonstrate that for such PDEs, the spectral bias towards low-frequency components presents a significant challenge for existing neural operators. To address this challenge, we propose a hierarchical attention neural operator (HANO) inspired by the hierarchical matrix approach. HANO features "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10890","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/2210.10890/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":"2210.10890","created_at":"2026-07-05T08:29:13.183281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10890v3","created_at":"2026-07-05T08:29:13.183281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10890","created_at":"2026-07-05T08:29:13.183281+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6R6NDEJDZ3B","created_at":"2026-07-05T08:29:13.183281+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6R6NDEJDZ3BF6UI","created_at":"2026-07-05T08:29:13.183281+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6R6NDEJ","created_at":"2026-07-05T08:29:13.183281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31559","citing_title":"Functional Attention: From Pairwise Affinities to Functional Correspondences","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2402.02366","citing_title":"Transolver: A Fast Transformer Solver for PDEs on General Geometries","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE","json":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE.json","graph_json":"https://pith.science/api/pith-number/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/graph.json","events_json":"https://pith.science/api/pith-number/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/events.json","paper":"https://pith.science/paper/Y6R6NDEJ"},"agent_actions":{"view_html":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE","download_json":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE.json","view_paper":"https://pith.science/paper/Y6R6NDEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10890&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/action/storage_attestation","attest_author":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/action/author_attestation","sign_citation":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/action/citation_signature","submit_replication":"https://pith.science/pith/Y6R6NDEJDZ3BF6UIYS7Q4FU3WE/action/replication_record"}},"created_at":"2026-07-05T08:29:13.183281+00:00","updated_at":"2026-07-05T08:29:13.183281+00:00"}