{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6UT644EJWTA4MCEU36VYELHPYL","short_pith_number":"pith:6UT644EJ","schema_version":"1.0","canonical_sha256":"f527ee7089b4c1c60894dfab822cefc2f7443cdeaa01926523e5923d721ac6ce","source":{"kind":"arxiv","id":"2003.02236","version":2},"attestation_state":"computed","paper":{"title":"Forecasting Sequential Data using Consistent Koopman Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.DS"],"primary_cat":"physics.comp-ph","authors_text":"Michael W. Mahoney, N. Benjamin Erichson, Omri Azencot, Vanessa Lin","submitted_at":"2020-03-04T18:24:30Z","abstract_excerpt":"Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences. A new class of physics-based methods related to Koopman theory has been introduced, offering an alternative for processing nonlinear dynamical systems. In this work, we propose a novel Consistent Koopman Autoencoder model which, unlike the majority of existing work, leverages the forward and backward dynamics. Key to our approach is a new analysis which explores the interplay between consistent dynamics and their associated Koopman operators. Our net"},"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":"2003.02236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2020-03-04T18:24:30Z","cross_cats_sorted":["cs.LG","math.DS"],"title_canon_sha256":"ba1e622c97c1d65fdee4a02d5a93e8179b9d4562f66def7ee6168ba88f320bb9","abstract_canon_sha256":"a9bbf39fb38419a3e31924bab67807203ad37c811a28d3d214bca7dfc1bdb20c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:41.116163Z","signature_b64":"OzXMNIvzIkZXLBx2iuFyu+jQQxY42uWgpbBZidmXS4grhEqCUnJoGSJSL3/u1vJ3qt8YG1BwZ/Hdt1cf2KpsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f527ee7089b4c1c60894dfab822cefc2f7443cdeaa01926523e5923d721ac6ce","last_reissued_at":"2026-07-05T01:14:41.114993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:41.114993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forecasting Sequential Data using Consistent Koopman Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.DS"],"primary_cat":"physics.comp-ph","authors_text":"Michael W. Mahoney, N. Benjamin Erichson, Omri Azencot, Vanessa Lin","submitted_at":"2020-03-04T18:24:30Z","abstract_excerpt":"Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences. A new class of physics-based methods related to Koopman theory has been introduced, offering an alternative for processing nonlinear dynamical systems. In this work, we propose a novel Consistent Koopman Autoencoder model which, unlike the majority of existing work, leverages the forward and backward dynamics. Key to our approach is a new analysis which explores the interplay between consistent dynamics and their associated Koopman operators. Our net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02236","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/2003.02236/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":"2003.02236","created_at":"2026-07-05T01:14:41.115041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.02236v2","created_at":"2026-07-05T01:14:41.115041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02236","created_at":"2026-07-05T01:14:41.115041+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UT644EJWTA4","created_at":"2026-07-05T01:14:41.115041+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UT644EJWTA4MCEU","created_at":"2026-07-05T01:14:41.115041+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UT644EJ","created_at":"2026-07-05T01:14:41.115041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06500","citing_title":"Leveraging Metrologically Useful States in Quantum Reservoir Networks","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22969","citing_title":"Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05416","citing_title":"Reduced-Order Surrogates for Forced Flexible Mesh Coastal-Ocean Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14424","citing_title":"Non-intrusive Learning of Physics-Informed Spatio-temporal Surrogate for Accelerating Design","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL","json":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL.json","graph_json":"https://pith.science/api/pith-number/6UT644EJWTA4MCEU36VYELHPYL/graph.json","events_json":"https://pith.science/api/pith-number/6UT644EJWTA4MCEU36VYELHPYL/events.json","paper":"https://pith.science/paper/6UT644EJ"},"agent_actions":{"view_html":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL","download_json":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL.json","view_paper":"https://pith.science/paper/6UT644EJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.02236&json=true","fetch_graph":"https://pith.science/api/pith-number/6UT644EJWTA4MCEU36VYELHPYL/graph.json","fetch_events":"https://pith.science/api/pith-number/6UT644EJWTA4MCEU36VYELHPYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL/action/storage_attestation","attest_author":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL/action/author_attestation","sign_citation":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL/action/citation_signature","submit_replication":"https://pith.science/pith/6UT644EJWTA4MCEU36VYELHPYL/action/replication_record"}},"created_at":"2026-07-05T01:14:41.115041+00:00","updated_at":"2026-07-05T01:14:41.115041+00:00"}