{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OFG4NGDNKZECV5M3WV2HAXDI7U","short_pith_number":"pith:OFG4NGDN","schema_version":"1.0","canonical_sha256":"714dc6986d56482af59bb574705c68fd2eac098d47592d53d5f1d7d91202b66e","source":{"kind":"arxiv","id":"2210.03675","version":3},"attestation_state":"computed","paper":{"title":"Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Rose Yu, Rui Wang, Sercan \\\"O. Arik, Yihe Dong","submitted_at":"2022-10-07T16:33:50Z","abstract_excerpt":"Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs). In this paper, we propose a novel deep sequence model based on the Koopman theory for time series forecasting: Koopman Neural Forecaster (KNF) which leverages DNNs to learn the linear Koopman space and the coefficients of chosen measurement functions. KNF imposes appropriate inductive biases for improved robustness against distributional shifts, employing both a global operator to learn shared characteristics a"},"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":"2210.03675","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T16:33:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"deaa999a919fab80c5dd20cf60b49c30d9f42a1e1c553c4e0c37124081676f59","abstract_canon_sha256":"5e09496e49848e267073e4ca4ef4b20d8e778cf7d6bb8a3abb155b29edcc9fdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:25.088125Z","signature_b64":"yfKUvd9Au/kpoEBvdKKjZFCv8PR8tCn/ql6EjblFTSJfZYwoSenHVdg1+QIsdce+azKliOUnDLXEiAiYFvN5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"714dc6986d56482af59bb574705c68fd2eac098d47592d53d5f1d7d91202b66e","last_reissued_at":"2026-07-05T05:46:25.087677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:25.087677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Rose Yu, Rui Wang, Sercan \\\"O. Arik, Yihe Dong","submitted_at":"2022-10-07T16:33:50Z","abstract_excerpt":"Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs). In this paper, we propose a novel deep sequence model based on the Koopman theory for time series forecasting: Koopman Neural Forecaster (KNF) which leverages DNNs to learn the linear Koopman space and the coefficients of chosen measurement functions. KNF imposes appropriate inductive biases for improved robustness against distributional shifts, employing both a global operator to learn shared characteristics a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03675","kind":"arxiv","version":3},"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/2210.03675/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":"2210.03675","created_at":"2026-07-05T05:46:25.087731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03675v3","created_at":"2026-07-05T05:46:25.087731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03675","created_at":"2026-07-05T05:46:25.087731+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFG4NGDNKZEC","created_at":"2026-07-05T05:46:25.087731+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFG4NGDNKZECV5M3","created_at":"2026-07-05T05:46:25.087731+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFG4NGDN","created_at":"2026-07-05T05:46:25.087731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23957","citing_title":"Learning the Koopman Operator using Attention Free Transformers","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22969","citing_title":"Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01918","citing_title":"Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09917","citing_title":"SPDM: Geometry-Modulated State Space Modeling with Manifold Constraints for Time Series Forecasting","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04278","citing_title":"Non-stationary Diffusion For Probabilistic Time Series Forecasting","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12683","citing_title":"Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U","json":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U.json","graph_json":"https://pith.science/api/pith-number/OFG4NGDNKZECV5M3WV2HAXDI7U/graph.json","events_json":"https://pith.science/api/pith-number/OFG4NGDNKZECV5M3WV2HAXDI7U/events.json","paper":"https://pith.science/paper/OFG4NGDN"},"agent_actions":{"view_html":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U","download_json":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U.json","view_paper":"https://pith.science/paper/OFG4NGDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03675&json=true","fetch_graph":"https://pith.science/api/pith-number/OFG4NGDNKZECV5M3WV2HAXDI7U/graph.json","fetch_events":"https://pith.science/api/pith-number/OFG4NGDNKZECV5M3WV2HAXDI7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U/action/storage_attestation","attest_author":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U/action/author_attestation","sign_citation":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U/action/citation_signature","submit_replication":"https://pith.science/pith/OFG4NGDNKZECV5M3WV2HAXDI7U/action/replication_record"}},"created_at":"2026-07-05T05:46:25.087731+00:00","updated_at":"2026-07-05T05:46:25.087731+00:00"}