{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RGCM5LGBOZTOKNAFOIFY2HDUTA","short_pith_number":"pith:RGCM5LGB","schema_version":"1.0","canonical_sha256":"8984ceacc17666e53405720b8d1c74981dfd832d6e9eb87dec294fff8a45d162","source":{"kind":"arxiv","id":"2310.02619","version":2},"attestation_state":"computed","paper":{"title":"Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilan Naiman, Michael W. Mahoney, N. Benjamin Erichson, Omri Azencot, Pu Ren","submitted_at":"2023-10-04T07:14:43Z","abstract_excerpt":"Generating realistic time series data is important for many engineering and scientific applications. Existing work tackles this problem using generative adversarial networks (GANs). However, GANs are unstable during training, and they can suffer from mode collapse. While variational autoencoders (VAEs) are known to be more robust to the these issues, they are (surprisingly) less considered for time series generation. In this work, we introduce Koopman VAE (KoVAE), a new generative framework that is based on a novel design for the model prior, and that can be optimized for either regular and ir"},"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":"2310.02619","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T07:14:43Z","cross_cats_sorted":[],"title_canon_sha256":"b4d69095eee99d50c93d39cb0efab8dc1d824da891d7ec1ac09a03a078007c5a","abstract_canon_sha256":"e284926ab8d36a793334c3eb3c87e08baae2dbde4c4bc6fae1a6324d619585b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:32.223525Z","signature_b64":"YcX1TYI/UjLLQjwWOhZKLhwTqVpyMOrCCxt+BCty+Xwdfxcqpb5woHlrKv8oNV0PVctwD+oiyT2gvFD+hznrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8984ceacc17666e53405720b8d1c74981dfd832d6e9eb87dec294fff8a45d162","last_reissued_at":"2026-07-05T08:18:32.223059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:32.223059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilan Naiman, Michael W. Mahoney, N. Benjamin Erichson, Omri Azencot, Pu Ren","submitted_at":"2023-10-04T07:14:43Z","abstract_excerpt":"Generating realistic time series data is important for many engineering and scientific applications. Existing work tackles this problem using generative adversarial networks (GANs). However, GANs are unstable during training, and they can suffer from mode collapse. While variational autoencoders (VAEs) are known to be more robust to the these issues, they are (surprisingly) less considered for time series generation. In this work, we introduce Koopman VAE (KoVAE), a new generative framework that is based on a novel design for the model prior, and that can be optimized for either regular and ir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02619","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/2310.02619/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":"2310.02619","created_at":"2026-07-05T08:18:32.223115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02619v2","created_at":"2026-07-05T08:18:32.223115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02619","created_at":"2026-07-05T08:18:32.223115+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGCM5LGBOZTO","created_at":"2026-07-05T08:18:32.223115+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGCM5LGBOZTOKNAF","created_at":"2026-07-05T08:18:32.223115+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGCM5LGB","created_at":"2026-07-05T08:18:32.223115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.14202","citing_title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA","json":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA.json","graph_json":"https://pith.science/api/pith-number/RGCM5LGBOZTOKNAFOIFY2HDUTA/graph.json","events_json":"https://pith.science/api/pith-number/RGCM5LGBOZTOKNAFOIFY2HDUTA/events.json","paper":"https://pith.science/paper/RGCM5LGB"},"agent_actions":{"view_html":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA","download_json":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA.json","view_paper":"https://pith.science/paper/RGCM5LGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02619&json=true","fetch_graph":"https://pith.science/api/pith-number/RGCM5LGBOZTOKNAFOIFY2HDUTA/graph.json","fetch_events":"https://pith.science/api/pith-number/RGCM5LGBOZTOKNAFOIFY2HDUTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA/action/storage_attestation","attest_author":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA/action/author_attestation","sign_citation":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA/action/citation_signature","submit_replication":"https://pith.science/pith/RGCM5LGBOZTOKNAFOIFY2HDUTA/action/replication_record"}},"created_at":"2026-07-05T08:18:32.223115+00:00","updated_at":"2026-07-05T08:18:32.223115+00:00"}