{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C3JBBNZGFJFSI6GJZUYJSK7CQT","short_pith_number":"pith:C3JBBNZG","schema_version":"1.0","canonical_sha256":"16d210b7262a4b2478c9cd30992be284f4557c98cecaca2bcb613f729ade2560","source":{"kind":"arxiv","id":"2506.19396","version":1},"attestation_state":"computed","paper":{"title":"Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shanda Li, Shinjae Yoo, Yiming Yang","submitted_at":"2025-06-24T07:53:34Z","abstract_excerpt":"Fourier Neural Operators (FNOs) offer a principled approach for solving complex partial differential equations (PDEs). However, scaling them to handle more complex PDEs requires increasing the number of Fourier modes, which significantly expands the number of model parameters and makes hyperparameter tuning computationally impractical. To address this, we introduce $\\mu$Transfer-FNO, a zero-shot hyperparameter transfer technique that enables optimal configurations, tuned on smaller FNOs, to be directly applied to billion-parameter FNOs without additional tuning. Building on the Maximal Update "},"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":"2506.19396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T07:53:34Z","cross_cats_sorted":[],"title_canon_sha256":"e49ffc3921805b44d104070d65b965a42b037706806a197cf096005d592a3ce7","abstract_canon_sha256":"de97c22820f02b89ce6ddc52c9c66021cf14f3c4f3076fde2ed455847048f0d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:14.561809Z","signature_b64":"HjX29S3DvrlYZSOnsoioPBudoO1my4aUF4w+WuNXT16Cgii6VAVxjRI3W0ZJuB+jKRsudn1UBouDwUTkFmG1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16d210b7262a4b2478c9cd30992be284f4557c98cecaca2bcb613f729ade2560","last_reissued_at":"2026-07-05T11:26:14.561360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:14.561360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shanda Li, Shinjae Yoo, Yiming Yang","submitted_at":"2025-06-24T07:53:34Z","abstract_excerpt":"Fourier Neural Operators (FNOs) offer a principled approach for solving complex partial differential equations (PDEs). However, scaling them to handle more complex PDEs requires increasing the number of Fourier modes, which significantly expands the number of model parameters and makes hyperparameter tuning computationally impractical. To address this, we introduce $\\mu$Transfer-FNO, a zero-shot hyperparameter transfer technique that enables optimal configurations, tuned on smaller FNOs, to be directly applied to billion-parameter FNOs without additional tuning. Building on the Maximal Update "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19396","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/2506.19396/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":"2506.19396","created_at":"2026-07-05T11:26:14.561420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19396v1","created_at":"2026-07-05T11:26:14.561420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19396","created_at":"2026-07-05T11:26:14.561420+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3JBBNZGFJFS","created_at":"2026-07-05T11:26:14.561420+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3JBBNZGFJFSI6GJ","created_at":"2026-07-05T11:26:14.561420+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3JBBNZG","created_at":"2026-07-05T11:26:14.561420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT","json":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT.json","graph_json":"https://pith.science/api/pith-number/C3JBBNZGFJFSI6GJZUYJSK7CQT/graph.json","events_json":"https://pith.science/api/pith-number/C3JBBNZGFJFSI6GJZUYJSK7CQT/events.json","paper":"https://pith.science/paper/C3JBBNZG"},"agent_actions":{"view_html":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT","download_json":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT.json","view_paper":"https://pith.science/paper/C3JBBNZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19396&json=true","fetch_graph":"https://pith.science/api/pith-number/C3JBBNZGFJFSI6GJZUYJSK7CQT/graph.json","fetch_events":"https://pith.science/api/pith-number/C3JBBNZGFJFSI6GJZUYJSK7CQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT/action/storage_attestation","attest_author":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT/action/author_attestation","sign_citation":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT/action/citation_signature","submit_replication":"https://pith.science/pith/C3JBBNZGFJFSI6GJZUYJSK7CQT/action/replication_record"}},"created_at":"2026-07-05T11:26:14.561420+00:00","updated_at":"2026-07-05T11:26:14.561420+00:00"}