{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VD5TL5EPVBGPE5UVYZEHWLMTBX","short_pith_number":"pith:VD5TL5EP","schema_version":"1.0","canonical_sha256":"a8fb35f48fa84cf27695c6487b2d930dc76d603ce7855906416fa8e4a0fa1bd9","source":{"kind":"arxiv","id":"2306.10619","version":2},"attestation_state":"computed","paper":{"title":"Towards Stability of Autoregressive Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Jed Brown, Michael McCabe, Peter Harrington, Shashank Subramanian","submitted_at":"2023-06-18T18:57:02Z","abstract_excerpt":"Neural operators have proven to be a promising approach for modeling spatiotemporal systems in the physical sciences. However, training these models for large systems can be quite challenging as they incur significant computational and memory expense -- these systems are often forced to rely on autoregressive time-stepping of the neural network to predict future temporal states. While this is effective in managing costs, it can lead to uncontrolled error growth over time and eventual instability. We analyze the sources of this autoregressive error growth using prototypical neural operator mode"},"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":"2306.10619","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-18T18:57:02Z","cross_cats_sorted":["cs.NA","math.NA","physics.flu-dyn"],"title_canon_sha256":"7de47220be2d264bf8f6a18534e6063612d18348050755f0ad3ae13a38cb44fa","abstract_canon_sha256":"b0ef6b7c74386b4a15ebf53d3a377ef4cdf5bdbcfaa3851628511078969d1217"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:19.652524Z","signature_b64":"8/HL+wsiForOEF/iiFyC+f/Y6U8WxHJGL6hI19kNKM4Xfs0z/o6fdoL4SMaec1l4Y8paiHSKjCrwuGoT1RDuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8fb35f48fa84cf27695c6487b2d930dc76d603ce7855906416fa8e4a0fa1bd9","last_reissued_at":"2026-07-05T07:22:19.652019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:19.652019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Stability of Autoregressive Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Jed Brown, Michael McCabe, Peter Harrington, Shashank Subramanian","submitted_at":"2023-06-18T18:57:02Z","abstract_excerpt":"Neural operators have proven to be a promising approach for modeling spatiotemporal systems in the physical sciences. However, training these models for large systems can be quite challenging as they incur significant computational and memory expense -- these systems are often forced to rely on autoregressive time-stepping of the neural network to predict future temporal states. While this is effective in managing costs, it can lead to uncontrolled error growth over time and eventual instability. We analyze the sources of this autoregressive error growth using prototypical neural operator mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10619","kind":"arxiv","version":2},"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/2306.10619/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":"2306.10619","created_at":"2026-07-05T07:22:19.652075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10619v2","created_at":"2026-07-05T07:22:19.652075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10619","created_at":"2026-07-05T07:22:19.652075+00:00"},{"alias_kind":"pith_short_12","alias_value":"VD5TL5EPVBGP","created_at":"2026-07-05T07:22:19.652075+00:00"},{"alias_kind":"pith_short_16","alias_value":"VD5TL5EPVBGPE5UV","created_at":"2026-07-05T07:22:19.652075+00:00"},{"alias_kind":"pith_short_8","alias_value":"VD5TL5EP","created_at":"2026-07-05T07:22:19.652075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28122","citing_title":"Higher-Order Fourier Neural Operator: Explicit Mode Mixer for Nonlinear PDEs","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17091","citing_title":"Mechanism Learning: Prototype-Anchored Mechanism Inference for Scientific Forecasting","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX","json":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX.json","graph_json":"https://pith.science/api/pith-number/VD5TL5EPVBGPE5UVYZEHWLMTBX/graph.json","events_json":"https://pith.science/api/pith-number/VD5TL5EPVBGPE5UVYZEHWLMTBX/events.json","paper":"https://pith.science/paper/VD5TL5EP"},"agent_actions":{"view_html":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX","download_json":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX.json","view_paper":"https://pith.science/paper/VD5TL5EP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10619&json=true","fetch_graph":"https://pith.science/api/pith-number/VD5TL5EPVBGPE5UVYZEHWLMTBX/graph.json","fetch_events":"https://pith.science/api/pith-number/VD5TL5EPVBGPE5UVYZEHWLMTBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX/action/storage_attestation","attest_author":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX/action/author_attestation","sign_citation":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX/action/citation_signature","submit_replication":"https://pith.science/pith/VD5TL5EPVBGPE5UVYZEHWLMTBX/action/replication_record"}},"created_at":"2026-07-05T07:22:19.652075+00:00","updated_at":"2026-07-05T07:22:19.652075+00:00"}