{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EPCQP56XAIUN5TMTUCIJZYK5NE","short_pith_number":"pith:EPCQP56X","schema_version":"1.0","canonical_sha256":"23c507f7d70228decd93a0909ce15d690ade9237404ad2a78015bc56e74aea70","source":{"kind":"arxiv","id":"2402.02494","version":3},"attestation_state":"computed","paper":{"title":"Variance representations and convergence rates for data-driven approximations of Koopman operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.DS","authors_text":"Feliks N\\\"uske, Friedrich M. Philipp, Karl Worthmann, Manuel Schaller, Sebastian Peitz, Septimus Boshoff","submitted_at":"2024-02-04T13:58:48Z","abstract_excerpt":"We rigorously derive novel error bounds for extended dynamic mode decomposition (EDMD) to approximate the Koopman operator for discrete- and continuous time (stochastic) systems; both for i.i.d. and ergodic sampling under non-restrictive assumptions. We show exponential convergence rates for i.i.d. sampling and provide the first superlinear convergence rates for ergodic sampling of deterministic systems. The proofs are based on novel exact variance representations for the empirical estimators of mass and stiffness matrix. Moreover, we verify the accuracy of the derived error bounds and converg"},"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":"2402.02494","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.DS","submitted_at":"2024-02-04T13:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"4ce3e39071f38eadeaf31bb3744934fd79155b235b6f8407973be71ccc76f64c","abstract_canon_sha256":"b1eee9ee8e964ba0393cccc170529918139abe614184e5a5ef92ddaa6165b148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:49.253222Z","signature_b64":"G+aUSdYllInRTdixPocN7Gk1bmIVDw/FJhVuz0FbGykFDRWJQGyIQGUMCuWo7eL3kOXYzVcDKKq+bIvHJ2lJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23c507f7d70228decd93a0909ce15d690ade9237404ad2a78015bc56e74aea70","last_reissued_at":"2026-07-05T08:21:49.252728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:49.252728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance representations and convergence rates for data-driven approximations of Koopman operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.DS","authors_text":"Feliks N\\\"uske, Friedrich M. Philipp, Karl Worthmann, Manuel Schaller, Sebastian Peitz, Septimus Boshoff","submitted_at":"2024-02-04T13:58:48Z","abstract_excerpt":"We rigorously derive novel error bounds for extended dynamic mode decomposition (EDMD) to approximate the Koopman operator for discrete- and continuous time (stochastic) systems; both for i.i.d. and ergodic sampling under non-restrictive assumptions. We show exponential convergence rates for i.i.d. sampling and provide the first superlinear convergence rates for ergodic sampling of deterministic systems. The proofs are based on novel exact variance representations for the empirical estimators of mass and stiffness matrix. Moreover, we verify the accuracy of the derived error bounds and converg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02494","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/2402.02494/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":"2402.02494","created_at":"2026-07-05T08:21:49.252788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02494v3","created_at":"2026-07-05T08:21:49.252788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02494","created_at":"2026-07-05T08:21:49.252788+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPCQP56XAIUN","created_at":"2026-07-05T08:21:49.252788+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPCQP56XAIUN5TMT","created_at":"2026-07-05T08:21:49.252788+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPCQP56X","created_at":"2026-07-05T08:21:49.252788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31438","citing_title":"Flow map learning in nonlinear vector autoregressive models: influence of the feature-library structure on the training error","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16016","citing_title":"Residual SCI Upper Bounds And Lower Witnesses For Koopman Approximate Point Spectra In $L^p$ For $1