{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UJ5KWMCF4HHHZ5IUNYIHHP6VGP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9d6b92ebfa1c8f6d742fdc4db5131c6d9d274b61dd5bf9e1ae51ffa84c8d8ba4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:53:36Z","title_canon_sha256":"1cdbe8c64e8de1a2b71c01b8db89e0a2dcfa6007075abb315a18a531ecf5a9ed"},"schema_version":"1.0","source":{"id":"2605.12997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12997","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12997v1","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12997","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"UJ5KWMCF4HHH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UJ5KWMCF4HHHZ5IU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UJ5KWMCF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:419439ad9ae110ffa2677aacf4b3dfdee623238773c9d9e4f766f65561e80202","target":"graph","created_at":"2026-05-18T03:09:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Under frequency shifts, FNO exhibits a sharp increase in error under unseen high-frequency inputs, whereas DeepONet shows milder degradation despite higher overall error. These differences arise from how each architecture represents and responds to variations in frequency structure."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That independently varying input frequency and coefficient smoothness produces distribution shifts representative of those encountered in practical PDE applications."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FNO exhibits strong frequency bias with sharp OOD error growth on high-frequency inputs in wave equations, while DeepONet shows milder degradation despite higher baseline error."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"FNO shows sharp error jumps on unseen high frequencies in wave equations while DeepONet degrades more gradually."}],"snapshot_sha256":"e7a2a1ba68f4f39fc36babfa20dd22c673f0bcd0166bc392ee8b427f4fae0cf8"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Neural operators learn to map initial conditions to the terminal solution of partial differential equations (PDEs), providing a surrogate for the full operator mapping. This enables rapid prediction across different input configurations. While recent neural operator architectures have demonstrated strong performance on diverse PDE tasks, their behavior under structured distribution shifts remains insufficiently understood. To investigate this, we study operator learning in a wave propagation setting governed by a one-dimensional variable-coefficient wave equation, using two representative arch","authors_text":"An Luo, Runlong Xie","cross_cats":[],"headline":"FNO shows sharp error jumps on unseen high frequencies in wave equations while DeepONet degrades more gradually.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:53:36Z","title":"Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation"},"references":{"count":71,"internal_anchors":1,"resolved_work":71,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Langley , title =","work_id":"6cd283dc-0548-45e9-af07-6bc1005593ad","year":2000},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"T. M. Mitchell. The Need for Biases in Learning Generalizations. 1980","work_id":"6b09bca6-ef5d-4a83-8c8e-219f23cbd761","year":1980},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"M. J. Kearns , title =","work_id":"8efd8073-6f5d-45c5-94d5-62d366b52518","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Machine Learning: An Artificial Intelligence Approach, Vol. I. 1983","work_id":"51835800-f16e-4534-8339-d3ea09147556","year":1983},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"R. O. Duda and P. E. Hart and D. G. Stork. Pattern Classification. 2000","work_id":"a24cb892-7ac9-4509-8f5b-abbdfb15998b","year":2000}],"snapshot_sha256":"8ae687608c54812f2c8aca278875f1757fa717f0e6c98e8b3b9d52050b5a324d"},"source":{"id":"2605.12997","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:43:48.297455Z","id":"f1b1bddc-c170-4d3d-bc24-bcd8f7964a9b","model_set":{"reader":"grok-4.3"},"one_line_summary":"FNO exhibits strong frequency bias with sharp OOD error growth on high-frequency inputs in wave equations, while DeepONet shows milder degradation despite higher baseline error.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"FNO shows sharp error jumps on unseen high frequencies in wave equations while DeepONet degrades more gradually.","strongest_claim":"Under frequency shifts, FNO exhibits a sharp increase in error under unseen high-frequency inputs, whereas DeepONet shows milder degradation despite higher overall error. These differences arise from how each architecture represents and responds to variations in frequency structure.","weakest_assumption":"That independently varying input frequency and coefficient smoothness produces distribution shifts representative of those encountered in practical PDE applications."}},"verdict_id":"f1b1bddc-c170-4d3d-bc24-bcd8f7964a9b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e08b79e232710dae31a857cff34a0c04334cdbcff8f5f11b13fe500e4e7435bf","target":"record","created_at":"2026-05-18T03:09:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9d6b92ebfa1c8f6d742fdc4db5131c6d9d274b61dd5bf9e1ae51ffa84c8d8ba4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:53:36Z","title_canon_sha256":"1cdbe8c64e8de1a2b71c01b8db89e0a2dcfa6007075abb315a18a531ecf5a9ed"},"schema_version":"1.0","source":{"id":"2605.12997","kind":"arxiv","version":1}},"canonical_sha256":"a27aab3045e1ce7cf5146e1073bfd533c8e53bbe879e5d1e88d64158eb603ba1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a27aab3045e1ce7cf5146e1073bfd533c8e53bbe879e5d1e88d64158eb603ba1","first_computed_at":"2026-05-18T03:09:00.477770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:00.477770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MYSzKE2AvnVLSk/BpSmWY/SaWkUN+JYDShmDC2Ppcy2XqbMkN/bJeRVGYLdRD2YBqs0QrJtzer/P36QaExHEDA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:00.478249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e08b79e232710dae31a857cff34a0c04334cdbcff8f5f11b13fe500e4e7435bf","sha256:419439ad9ae110ffa2677aacf4b3dfdee623238773c9d9e4f766f65561e80202"],"state_sha256":"4b5c12e4d9bea3d86ff69358372c40add7650933e25e3549b44a8ba2ec295894"}