{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:INRTZETAGJ3IK422TPOSV4DWGT","short_pith_number":"pith:INRTZETA","schema_version":"1.0","canonical_sha256":"43633c9260327685735a9bdd2af07634dbafee88215c384b1671951f7e228d80","source":{"kind":"arxiv","id":"2505.20721","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Neural Operators: Stable Long-Term PDE Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Chen-Song Zhang, Wansheng Wang, Zaijun Ye","submitted_at":"2025-05-27T05:04:35Z","abstract_excerpt":"Neural operators have emerged as powerful tools for learning solution operators of partial differential equations. However, in time-dependent problems, standard training strategies such as teacher forcing introduce a mismatch between training and inference, leading to compounding errors in long-term autoregressive predictions. To address this issue, we propose Recurrent Neural Operators (RNOs)-a novel framework that integrates recurrent training into neural operator architectures. Instead of conditioning each training step on ground-truth inputs, RNOs recursively apply the operator to their ow"},"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":"2505.20721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T05:04:35Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"f7e11ea3f9b500e3f01935dd27d958d70a9dddd07f7e2e9a9f952ad887247332","abstract_canon_sha256":"8242e0c125b403ed38bd3406487c61851f060b0351d25fd613f1c6951a373062"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:17.448383Z","signature_b64":"xrh+Junt24Nq6ob1NWdkA/dLkqZJKsw+JpSWkcaCDpHYR+afta+BTochlvZKDMl07pcxq8zrs3CjDDG1g7VPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43633c9260327685735a9bdd2af07634dbafee88215c384b1671951f7e228d80","last_reissued_at":"2026-07-05T11:10:17.447896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:17.447896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Neural Operators: Stable Long-Term PDE Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Chen-Song Zhang, Wansheng Wang, Zaijun Ye","submitted_at":"2025-05-27T05:04:35Z","abstract_excerpt":"Neural operators have emerged as powerful tools for learning solution operators of partial differential equations. However, in time-dependent problems, standard training strategies such as teacher forcing introduce a mismatch between training and inference, leading to compounding errors in long-term autoregressive predictions. To address this issue, we propose Recurrent Neural Operators (RNOs)-a novel framework that integrates recurrent training into neural operator architectures. Instead of conditioning each training step on ground-truth inputs, RNOs recursively apply the operator to their ow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20721","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/2505.20721/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":"2505.20721","created_at":"2026-07-05T11:10:17.447955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20721v1","created_at":"2026-07-05T11:10:17.447955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20721","created_at":"2026-07-05T11:10:17.447955+00:00"},{"alias_kind":"pith_short_12","alias_value":"INRTZETAGJ3I","created_at":"2026-07-05T11:10:17.447955+00:00"},{"alias_kind":"pith_short_16","alias_value":"INRTZETAGJ3IK422","created_at":"2026-07-05T11:10:17.447955+00:00"},{"alias_kind":"pith_short_8","alias_value":"INRTZETA","created_at":"2026-07-05T11:10:17.447955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25413","citing_title":"Autoregression-Free Neural Operators for Time-Dependent PDEs","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00233","citing_title":"Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10154","citing_title":"Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT","json":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT.json","graph_json":"https://pith.science/api/pith-number/INRTZETAGJ3IK422TPOSV4DWGT/graph.json","events_json":"https://pith.science/api/pith-number/INRTZETAGJ3IK422TPOSV4DWGT/events.json","paper":"https://pith.science/paper/INRTZETA"},"agent_actions":{"view_html":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT","download_json":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT.json","view_paper":"https://pith.science/paper/INRTZETA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20721&json=true","fetch_graph":"https://pith.science/api/pith-number/INRTZETAGJ3IK422TPOSV4DWGT/graph.json","fetch_events":"https://pith.science/api/pith-number/INRTZETAGJ3IK422TPOSV4DWGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT/action/storage_attestation","attest_author":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT/action/author_attestation","sign_citation":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT/action/citation_signature","submit_replication":"https://pith.science/pith/INRTZETAGJ3IK422TPOSV4DWGT/action/replication_record"}},"created_at":"2026-07-05T11:10:17.447955+00:00","updated_at":"2026-07-05T11:10:17.447955+00:00"}