{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PLEFZJW5EZOVHL5EVSDJAKTIYX","short_pith_number":"pith:PLEFZJW5","canonical_record":{"source":{"id":"2605.15754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-05-15T09:15:01Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"6525041d00ee4efb6aa1670605574ce932ef6cf6161cef0cebd03eecd9945650","abstract_canon_sha256":"056ab8f50256124dfa775e8bc3270d1e9a422e6d9fe7c063eff5fe45fa153117"},"schema_version":"1.0"},"canonical_sha256":"7ac85ca6dd265d53afa4ac86902a68c5fe1950f009c15521203584b78d6af245","source":{"kind":"arxiv","id":"2605.15754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15754","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15754v1","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15754","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"PLEFZJW5EZOV","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"PLEFZJW5EZOVHL5E","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"PLEFZJW5","created_at":"2026-05-20T00:01:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PLEFZJW5EZOVHL5EVSDJAKTIYX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-05-15T09:15:01Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"6525041d00ee4efb6aa1670605574ce932ef6cf6161cef0cebd03eecd9945650","abstract_canon_sha256":"056ab8f50256124dfa775e8bc3270d1e9a422e6d9fe7c063eff5fe45fa153117"},"schema_version":"1.0"},"canonical_sha256":"7ac85ca6dd265d53afa4ac86902a68c5fe1950f009c15521203584b78d6af245","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:16.441691Z","signature_b64":"TIRP/4ONie8FfB8pWvwx25ji+1N3lP+tqZdcoaGJJr02HU9E1WFVuUgCH/9YJiAejNy81r2s7lxHhygyrhAZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ac85ca6dd265d53afa4ac86902a68c5fe1950f009c15521203584b78d6af245","last_reissued_at":"2026-05-20T00:01:16.440830Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:16.440830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15754","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pjyg3x9MOLEJfK5SkvlNRNvl7pxfIyvGd7ppizWWP3800dE8SLejnNjQOd7Aq9ybn6prcxggbxFYp7OsFIHfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:12:44.256556Z"},"content_sha256":"963f68982ccf9cf8d3e74071de56b0b56a44562d9e6ee5684ae18045633ecf8f","schema_version":"1.0","event_id":"sha256:963f68982ccf9cf8d3e74071de56b0b56a44562d9e6ee5684ae18045633ecf8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PLEFZJW5EZOVHL5EVSDJAKTIYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatiotemporal decoupled physics-informed Stone-Weierstrass neural operator for long-time prediction of time-dependent parametric PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Encoding spatial and temporal information via separate subnetworks allows a physics-informed neural operator to avoid error accumulation in long-time predictions of parametric PDEs.","cross_cats":["cs.CE"],"primary_cat":"physics.comp-ph","authors_text":"Guofeng Su, Hongxiang Ma, Lang Qin, Rui Yang, Shan Ding, Yongfu Tian","submitted_at":"2026-05-15T09:15:01Z","abstract_excerpt":"Driven by rapid advances in artificial intelligence and modern GPU computing capabilities, deep learning methods based on the optimization paradigm have provided new pathways to solve spatiotemporal physical problems, whose mathematical core lies in solving partial differential equations (PDEs). As an emerging class of function-space learning methods, neural operators (NOs) have exhibited great potential in efficient PDE solving. However, existing mainstream neural operator frameworks suffer from critical bottlenecks when modeling time-dependent PDEs over long time horizons, including accuracy"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By encoding spatial and temporal information via two separate subnetworks, the PI-SWNO framework structurally mitigates the accumulation of errors over extended time intervals while the time-marching batch-wise sampling resolves the memory bottleneck.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The decoupling paradigm that combines time-invariant spatial basis functions with time-varying evolution coefficients will prevent error accumulation for the target class of time-dependent parametric PDEs, as grounded in the Stone-Weierstrass approximation theorem.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A spatiotemporally decoupled physics-informed Stone-Weierstrass neural operator for stable long-time prediction of time-dependent parametric PDEs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Encoding spatial and temporal information via separate subnetworks allows a physics-informed neural operator to avoid error accumulation in long-time predictions of parametric PDEs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d5c09db45d5d5a4d873e48665a59c2a3d59f670e7ac490e09e663fdf2c7d7114"},"source":{"id":"2605.15754","kind":"arxiv","version":1},"verdict":{"id":"27756ae7-a92b-463a-bca3-2b77f0974ac1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:51:22.695549Z","strongest_claim":"By encoding spatial and temporal information via two separate subnetworks, the PI-SWNO framework structurally mitigates the accumulation of errors over extended time intervals while the time-marching batch-wise sampling resolves the memory bottleneck.","one_line_summary":"A spatiotemporally decoupled physics-informed Stone-Weierstrass neural operator for stable long-time prediction of time-dependent parametric PDEs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The decoupling paradigm that combines time-invariant spatial basis functions with time-varying evolution coefficients will prevent error accumulation for the target class of time-dependent parametric PDEs, as grounded in the Stone-Weierstrass approximation theorem.","pith_extraction_headline":"Encoding spatial and temporal information via separate subnetworks allows a physics-informed neural operator to avoid error accumulation in long-time predictions of parametric PDEs."},"integrity":{"clean":false,"summary":{"advisory":2,"critical":0,"by_detector":{"doi_compliance":{"total":2,"advisory":2,"critical":0,"informational":0}},"informational":0},"endpoint":"/pith/2605.15754/integrity.json","findings":[{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.ijheatmasstransfer.2026.128335.URLhttps://www.sciencedirect.com/science/article/pii/S0017931026000116) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":23,"audited_at":"2026-05-19T19:01:44.045081Z","detected_doi":"10.1016/j.ijheatmasstransfer.2026.128335.URLhttps://www.sciencedirect.com/science/article/pii/S0017931026000116","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null},{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2508.05190.URLhttps://ui.adsabs.harvard.edu/abs/2025arXiv250805190M) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":11,"audited_at":"2026-05-19T19:01:44.045081Z","detected_doi":"10.48550/arXiv.2508.05190.URLhttps://ui.adsabs.harvard.edu/abs/2025arXiv250805190M","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T19:01:44.045081Z","status":"completed","version":"1.0.0","findings_count":2},{"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.022066Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.767272Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.963693Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f9729fb3dd9f1f253ef52d70d50855e25ad67617b2933433ec7208e7739d81d4"},"references":{"count":41,"sample":[{"doi":"10.1016/j.matcom.2021.10.010","year":2022,"title":"A. M. Vargas, Finite difference method for solving fractional differential equations at irregular meshes, Mathematics and Computers in Simulation 193 (2022) 204–216.doi:https: //doi.org/10.1016/j.matc","work_id":"e2d28a6f-e487-4b01-a2d2-5e76ad86c71b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.cma.2016.02.030","year":2016,"title":"K. Kergrene, I. Babuška, U. Banerjee, Stable generalized finite element method and associated iterative schemes; application to interface prob- lems, Computer Methods in Applied Mechanics and Engineer","work_id":"aaf6d767-4769-42a3-befb-cf1dcc320cb2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.amc.2015.03.078","year":2016,"title":"P. Buchmüller, J. Dreher, C. Helzel, Finite volume weno methods for hyperbolic conservation laws on cartesian grids with adaptive mesh refinement, Applied Mathematics and Computation 272 (2016) 460–47","work_id":"cdf276d1-aac6-4dc6-b0a5-89380528cf21","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.jcp.2018.10.045","year":2019,"title":"M. Raissi, P. Perdikaris, G. Karniadakis, Physics-informed neu- ral networks: A deep learning framework for solving forward 60 and inverse problems involving nonlinear partial differential equa- tions","work_id":"16a1de8a-4145-44c7-a263-8f01bfe9ca2e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Z. Li, K. Meidani, A. B. Farimani, Transformer for partial differen- tial equations’ operator learning, Transactions on Machine Learning Re- search (2023). URLhttps://openreview.net/forum?id=EPPqt3uER","work_id":"929e2a5c-a58d-4fe7-9cc6-dd9a005e62c9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"322a8bd108f2932bfdd2e27ac7cdfa94c9e6ff753f871de51eef83f6c2054a7f","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8df019f48a89d5326f196c3c0b3b7599a3638db7ffb555a7c3db91df2991a3e4"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"27756ae7-a92b-463a-bca3-2b77f0974ac1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eOLuZwUD9gXxHF7bnwxiUvh7DGELzdq/VYGFhqY4MZqvECMdIe5tt2IuzUYuibZP4td6U0knyZGsoEKbcxXcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:12:44.258738Z"},"content_sha256":"f94d099904eb8609e4b125e527da0b055b432e4976bc0dd4be4b6ba450dd61cf","schema_version":"1.0","event_id":"sha256:f94d099904eb8609e4b125e527da0b055b432e4976bc0dd4be4b6ba450dd61cf"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:PLEFZJW5EZOVHL5EVSDJAKTIYX","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.ijheatmasstransfer.2026.128335.URLhttps://www.sciencedirect.com/science/article/pii/S0017931026000116) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"S. Ding, Y. Tian, L. Qin, H. Ma, R. Yang, Physics-informed hierar- chical neural operator for solving inverse problem of unsteady heat conduction, International Journal of Heat and Mass Transfer 258 (2026) 128335.doi:https://doi.org/10.1016","arxiv_id":"2605.15754","detector":"doi_compliance","evidence":{"ref_index":23,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"S. Ding, Y. Tian, L. Qin, H. Ma, R. Yang, Physics-informed hierar- chical neural operator for solving inverse problem of unsteady heat conduction, International Journal of Heat and Mass Transfer 258 (2026) 128335.doi:https://doi.org/10.1016","reconstructed_doi":"10.1016/j.ijheatmasstransfer.2026.128335.URLhttps://www.sciencedirect.com/science/article/pii/S0017931026000116"},"severity":"advisory","ref_index":23,"audited_at":"2026-05-19T19:01:44.045081Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.ijheatmasstransfer.2026.128335.URLhttps://www.sciencedirect.com/science/article/pii/S0017931026000116","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"aab90f338e0a98e431fbb6a00717d180eeb664905445c98a590f609248d67b82","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":2646,"payload_sha256":"2640c39c6cafcadabaf9aead0879d09f619bb80d4e4550697061fa8b44f5d167","signature_b64":"AAu/1WHnnOTWCarIZQAuqevJdbMaSydGcWW54ElTxGxHk37aFwH1ACQsbvz/n9LR4Lbd/3VGBHexP+nvvJ1pCg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T19:02:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OLRIX562LbZ39hH2MRwr9LCzgsMImuwQ3bqAMTQsin8igeqKnM0Xq6MUAxf6SCGqw0oCQFz5mw8Y6AG0g0gOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:12:44.263422Z"},"content_sha256":"f9a8362ecf196d9a06b86d757e3a9459154e9e41f2d53de7ba8a77e1b6eed74d","schema_version":"1.0","event_id":"sha256:f9a8362ecf196d9a06b86d757e3a9459154e9e41f2d53de7ba8a77e1b6eed74d"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:PLEFZJW5EZOVHL5EVSDJAKTIYX","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2508.05190.URLhttps://ui.adsabs.harvard.edu/abs/2025arXiv250805190M) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"L. Mandl, D. Nayak, T. Ricken, S. Goswami, Physics-informed time- integrated deeponet: Temporal tangent space operator learning for high-accuracy inference (August 01, 2025 2025).doi:10.48550/arXiv. 2508.05190. URLhttps://ui.adsabs.harvard.","arxiv_id":"2605.15754","detector":"doi_compliance","evidence":{"ref_index":11,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"L. Mandl, D. Nayak, T. Ricken, S. Goswami, Physics-informed time- integrated deeponet: Temporal tangent space operator learning for high-accuracy inference (August 01, 2025 2025).doi:10.48550/arXiv. 2508.05190. URLhttps://ui.adsabs.harvard.","reconstructed_doi":"10.48550/arXiv.2508.05190.URLhttps://ui.adsabs.harvard.edu/abs/2025arXiv250805190M"},"severity":"advisory","ref_index":11,"audited_at":"2026-05-19T19:01:44.045081Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2508.05190.URLhttps://ui.adsabs.harvard.edu/abs/2025arXiv250805190M","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"580f69e31a1dff1fb6b9853d56baa5e62994fd4f28b3f249ba9931782a81a259","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":2645,"payload_sha256":"f9c6fa9d7b7aa1d61ef2e19023a9c8807a431427bbf429d83a3840ed7aaa3757","signature_b64":"MxHsa5ixtAp8GhBam0wgnDB8lHg6x5GoXO7ItwtBwfF8a6NQjmrE8FY3mtp85XE6XgFE3y4PiOoeDyqwEOsfBA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T19:02:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHDkaTGaSlwbczj6Ujj0par7XB8hiSpQus5iJBTsGX2ZNsYFaMCAdDZ/cR868B1WRd0tpcgwPtM7cnxmZ1lACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:12:44.264225Z"},"content_sha256":"38e4665aaf2d3beb29306a70fdbcdf97ddcea8d4b35689a6dc6745888880c0c0","schema_version":"1.0","event_id":"sha256:38e4665aaf2d3beb29306a70fdbcdf97ddcea8d4b35689a6dc6745888880c0c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLEFZJW5EZOVHL5EVSDJAKTIYX/bundle.json","state_url":"https://pith.science/pith/PLEFZJW5EZOVHL5EVSDJAKTIYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLEFZJW5EZOVHL5EVSDJAKTIYX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T09:12:44Z","links":{"resolver":"https://pith.science/pith/PLEFZJW5EZOVHL5EVSDJAKTIYX","bundle":"https://pith.science/pith/PLEFZJW5EZOVHL5EVSDJAKTIYX/bundle.json","state":"https://pith.science/pith/PLEFZJW5EZOVHL5EVSDJAKTIYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLEFZJW5EZOVHL5EVSDJAKTIYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PLEFZJW5EZOVHL5EVSDJAKTIYX","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"056ab8f50256124dfa775e8bc3270d1e9a422e6d9fe7c063eff5fe45fa153117","cross_cats_sorted":["cs.CE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-05-15T09:15:01Z","title_canon_sha256":"6525041d00ee4efb6aa1670605574ce932ef6cf6161cef0cebd03eecd9945650"},"schema_version":"1.0","source":{"id":"2605.15754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15754","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15754v1","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15754","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"PLEFZJW5EZOV","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"PLEFZJW5EZOVHL5E","created_at":"2026-05-20T00:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"PLEFZJW5","created_at":"2026-05-20T00:01:16Z"}],"graph_snapshots":[{"event_id":"sha256:f94d099904eb8609e4b125e527da0b055b432e4976bc0dd4be4b6ba450dd61cf","target":"graph","created_at":"2026-05-20T00:01:16Z","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":"By encoding spatial and temporal information via two separate subnetworks, the PI-SWNO framework structurally mitigates the accumulation of errors over extended time intervals while the time-marching batch-wise sampling resolves the memory bottleneck."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The decoupling paradigm that combines time-invariant spatial basis functions with time-varying evolution coefficients will prevent error accumulation for the target class of time-dependent parametric PDEs, as grounded in the Stone-Weierstrass approximation theorem."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A spatiotemporally decoupled physics-informed Stone-Weierstrass neural operator for stable long-time prediction of time-dependent parametric PDEs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Encoding spatial and temporal information via separate subnetworks allows a physics-informed neural operator to avoid error accumulation in long-time predictions of parametric PDEs."}],"snapshot_sha256":"d5c09db45d5d5a4d873e48665a59c2a3d59f670e7ac490e09e663fdf2c7d7114"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8df019f48a89d5326f196c3c0b3b7599a3638db7ffb555a7c3db91df2991a3e4"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":2,"name":"doi_compliance","ran_at":"2026-05-19T19:01:44.045081Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.022066Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.767272Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.963693Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15754/integrity.json","findings":[{"audited_at":"2026-05-19T19:01:44.045081Z","detected_arxiv_id":null,"detected_doi":"10.1016/j.ijheatmasstransfer.2026.128335.URLhttps://www.sciencedirect.com/science/article/pii/S0017931026000116","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.ijheatmasstransfer.2026.128335.URLhttps://www.sciencedirect.com/science/article/pii/S0017931026000116) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":23,"severity":"advisory","verdict_class":"incontrovertible"},{"audited_at":"2026-05-19T19:01:44.045081Z","detected_arxiv_id":null,"detected_doi":"10.48550/arXiv.2508.05190.URLhttps://ui.adsabs.harvard.edu/abs/2025arXiv250805190M","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2508.05190.URLhttps://ui.adsabs.harvard.edu/abs/2025arXiv250805190M) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":11,"severity":"advisory","verdict_class":"incontrovertible"}],"snapshot_sha256":"f9729fb3dd9f1f253ef52d70d50855e25ad67617b2933433ec7208e7739d81d4","summary":{"advisory":2,"by_detector":{"doi_compliance":{"advisory":2,"critical":0,"informational":0,"total":2}},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Driven by rapid advances in artificial intelligence and modern GPU computing capabilities, deep learning methods based on the optimization paradigm have provided new pathways to solve spatiotemporal physical problems, whose mathematical core lies in solving partial differential equations (PDEs). As an emerging class of function-space learning methods, neural operators (NOs) have exhibited great potential in efficient PDE solving. However, existing mainstream neural operator frameworks suffer from critical bottlenecks when modeling time-dependent PDEs over long time horizons, including accuracy","authors_text":"Guofeng Su, Hongxiang Ma, Lang Qin, Rui Yang, Shan Ding, Yongfu Tian","cross_cats":["cs.CE"],"headline":"Encoding spatial and temporal information via separate subnetworks allows a physics-informed neural operator to avoid error accumulation in long-time predictions of parametric PDEs.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-05-15T09:15:01Z","title":"Spatiotemporal decoupled physics-informed Stone-Weierstrass neural operator for long-time prediction of time-dependent parametric PDEs"},"references":{"count":41,"internal_anchors":5,"resolved_work":41,"sample":[{"cited_arxiv_id":"","doi":"10.1016/j.matcom.2021.10.010","is_internal_anchor":false,"ref_index":1,"title":"A. M. Vargas, Finite difference method for solving fractional differential equations at irregular meshes, Mathematics and Computers in Simulation 193 (2022) 204–216.doi:https: //doi.org/10.1016/j.matc","work_id":"e2d28a6f-e487-4b01-a2d2-5e76ad86c71b","year":2022},{"cited_arxiv_id":"","doi":"10.1016/j.cma.2016.02.030","is_internal_anchor":false,"ref_index":2,"title":"K. Kergrene, I. Babuška, U. Banerjee, Stable generalized finite element method and associated iterative schemes; application to interface prob- lems, Computer Methods in Applied Mechanics and Engineer","work_id":"aaf6d767-4769-42a3-befb-cf1dcc320cb2","year":2016},{"cited_arxiv_id":"","doi":"10.1016/j.amc.2015.03.078","is_internal_anchor":false,"ref_index":3,"title":"P. Buchmüller, J. Dreher, C. Helzel, Finite volume weno methods for hyperbolic conservation laws on cartesian grids with adaptive mesh refinement, Applied Mathematics and Computation 272 (2016) 460–47","work_id":"cdf276d1-aac6-4dc6-b0a5-89380528cf21","year":2016},{"cited_arxiv_id":"","doi":"10.1016/j.jcp.2018.10.045","is_internal_anchor":false,"ref_index":4,"title":"M. Raissi, P. Perdikaris, G. Karniadakis, Physics-informed neu- ral networks: A deep learning framework for solving forward 60 and inverse problems involving nonlinear partial differential equa- tions","work_id":"16a1de8a-4145-44c7-a263-8f01bfe9ca2e","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Z. Li, K. Meidani, A. B. Farimani, Transformer for partial differen- tial equations’ operator learning, Transactions on Machine Learning Re- search (2023). URLhttps://openreview.net/forum?id=EPPqt3uER","work_id":"929e2a5c-a58d-4fe7-9cc6-dd9a005e62c9","year":2023}],"snapshot_sha256":"322a8bd108f2932bfdd2e27ac7cdfa94c9e6ff753f871de51eef83f6c2054a7f"},"source":{"id":"2605.15754","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T18:51:22.695549Z","id":"27756ae7-a92b-463a-bca3-2b77f0974ac1","model_set":{"reader":"grok-4.3"},"one_line_summary":"A spatiotemporally decoupled physics-informed Stone-Weierstrass neural operator for stable long-time prediction of time-dependent parametric PDEs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Encoding spatial and temporal information via separate subnetworks allows a physics-informed neural operator to avoid error accumulation in long-time predictions of parametric PDEs.","strongest_claim":"By encoding spatial and temporal information via two separate subnetworks, the PI-SWNO framework structurally mitigates the accumulation of errors over extended time intervals while the time-marching batch-wise sampling resolves the memory bottleneck.","weakest_assumption":"The decoupling paradigm that combines time-invariant spatial basis functions with time-varying evolution coefficients will prevent error accumulation for the target class of time-dependent parametric PDEs, as grounded in the Stone-Weierstrass approximation theorem."}},"verdict_id":"27756ae7-a92b-463a-bca3-2b77f0974ac1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:963f68982ccf9cf8d3e74071de56b0b56a44562d9e6ee5684ae18045633ecf8f","target":"record","created_at":"2026-05-20T00:01:16Z","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":"056ab8f50256124dfa775e8bc3270d1e9a422e6d9fe7c063eff5fe45fa153117","cross_cats_sorted":["cs.CE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2026-05-15T09:15:01Z","title_canon_sha256":"6525041d00ee4efb6aa1670605574ce932ef6cf6161cef0cebd03eecd9945650"},"schema_version":"1.0","source":{"id":"2605.15754","kind":"arxiv","version":1}},"canonical_sha256":"7ac85ca6dd265d53afa4ac86902a68c5fe1950f009c15521203584b78d6af245","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ac85ca6dd265d53afa4ac86902a68c5fe1950f009c15521203584b78d6af245","first_computed_at":"2026-05-20T00:01:16.440830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:16.440830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TIRP/4ONie8FfB8pWvwx25ji+1N3lP+tqZdcoaGJJr02HU9E1WFVuUgCH/9YJiAejNy81r2s7lxHhygyrhAZBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:16.441691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15754","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:38e4665aaf2d3beb29306a70fdbcdf97ddcea8d4b35689a6dc6745888880c0c0","sha256:f9a8362ecf196d9a06b86d757e3a9459154e9e41f2d53de7ba8a77e1b6eed74d"]}],"invalid_events":[],"applied_event_ids":["sha256:963f68982ccf9cf8d3e74071de56b0b56a44562d9e6ee5684ae18045633ecf8f","sha256:f94d099904eb8609e4b125e527da0b055b432e4976bc0dd4be4b6ba450dd61cf"],"state_sha256":"0012d690111425967f96ca00bc1bf513abf0caa5a52c40d330d5315cffa9eadb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oj1AwGDGIZ7byacmjxyLHK19Hm/ENfIQSkKB6XGsPKnal9U1P+KtDVnw/3SbyMljY2kVTtWjCmGrTusosQC6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T09:12:44.273590Z","bundle_sha256":"9554e36bf957663e739b403eb28f87e147368f1fa113836e45ae747dcd529467"}}