{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EIPODJP5AVWGOCG3URWXXP2HKM","short_pith_number":"pith:EIPODJP5","schema_version":"1.0","canonical_sha256":"221ee1a5fd056c6708dba46d7bbf47530db55431e28359598cded7c277372060","source":{"kind":"arxiv","id":"2505.23215","version":1},"attestation_state":"computed","paper":{"title":"Trajectory Generator Matching for Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"C. Wald, G. Steidl, J. Chemseddine, P. Hagemann, T. Jahn","submitted_at":"2025-05-29T07:56:32Z","abstract_excerpt":"Accurately modeling time-continuous stochastic processes from irregular observations remains a significant challenge. In this paper, we leverage ideas from generative modeling of image data to push the boundary of time series generation. For this, we find new generators of SDEs and jump processes, inspired by trajectory flow matching, that have the marginal distributions of the time series of interest. Specifically, we can handle discontinuities of the underlying processes by parameterizing the jump kernel densities by scaled Gaussians that allow for closed form formulas of the corresponding K"},"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":"2505.23215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2025-05-29T07:56:32Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"44e6254818f6c750194a3f1138e91194a91d67fa7d1578a7e6c7861c0dd17498","abstract_canon_sha256":"668eaaeeb91f41f8e4516b7cbf8eda2df32ed97d37eb331920ebe6614ce9da67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:57.658717Z","signature_b64":"cNJ4NpYll0G70taYgj5QcOyNVdk8AlUoI06Zusbt7R+hLty/lYbK2J1S2ODiIpscJONciyeGs++e+BJ7KSswCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"221ee1a5fd056c6708dba46d7bbf47530db55431e28359598cded7c277372060","last_reissued_at":"2026-07-05T11:11:57.658226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:57.658226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trajectory Generator Matching for Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"C. Wald, G. Steidl, J. Chemseddine, P. Hagemann, T. Jahn","submitted_at":"2025-05-29T07:56:32Z","abstract_excerpt":"Accurately modeling time-continuous stochastic processes from irregular observations remains a significant challenge. In this paper, we leverage ideas from generative modeling of image data to push the boundary of time series generation. For this, we find new generators of SDEs and jump processes, inspired by trajectory flow matching, that have the marginal distributions of the time series of interest. Specifically, we can handle discontinuities of the underlying processes by parameterizing the jump kernel densities by scaled Gaussians that allow for closed form formulas of the corresponding K"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23215","kind":"arxiv","version":1},"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/2505.23215/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":"2505.23215","created_at":"2026-07-05T11:11:57.658276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23215v1","created_at":"2026-07-05T11:11:57.658276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23215","created_at":"2026-07-05T11:11:57.658276+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIPODJP5AVWG","created_at":"2026-07-05T11:11:57.658276+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIPODJP5AVWGOCG3","created_at":"2026-07-05T11:11:57.658276+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIPODJP5","created_at":"2026-07-05T11:11:57.658276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.16839","citing_title":"Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM","json":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM.json","graph_json":"https://pith.science/api/pith-number/EIPODJP5AVWGOCG3URWXXP2HKM/graph.json","events_json":"https://pith.science/api/pith-number/EIPODJP5AVWGOCG3URWXXP2HKM/events.json","paper":"https://pith.science/paper/EIPODJP5"},"agent_actions":{"view_html":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM","download_json":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM.json","view_paper":"https://pith.science/paper/EIPODJP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23215&json=true","fetch_graph":"https://pith.science/api/pith-number/EIPODJP5AVWGOCG3URWXXP2HKM/graph.json","fetch_events":"https://pith.science/api/pith-number/EIPODJP5AVWGOCG3URWXXP2HKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM/action/storage_attestation","attest_author":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM/action/author_attestation","sign_citation":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM/action/citation_signature","submit_replication":"https://pith.science/pith/EIPODJP5AVWGOCG3URWXXP2HKM/action/replication_record"}},"created_at":"2026-07-05T11:11:57.658276+00:00","updated_at":"2026-07-05T11:11:57.658276+00:00"}