{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7DEMCYRXTL3U6CVUQ5AV7PKF5H","short_pith_number":"pith:7DEMCYRX","schema_version":"1.0","canonical_sha256":"f8c8c162379af74f0ab487415fbd45e9ecdc5eff71a52cc2ff19190efd1bd281","source":{"kind":"arxiv","id":"2506.12203","version":1},"attestation_state":"computed","paper":{"title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anming Gu, Edward Chien, Kristjan Greenewald","submitted_at":"2025-06-13T20:13:37Z","abstract_excerpt":"We provide an algorithm to privately generate continuous-time data (e.g. marginals from stochastic differential equations), which has applications in highly sensitive domains involving time-series data such as healthcare. We leverage the connections between trajectory inference and continuous-time synthetic data generation, along with a computational method based on mean-field Langevin dynamics. As discretized mean-field Langevin dynamics and noisy particle gradient descent are equivalent, DP results for noisy SGD can be applied to our setting. We provide experiments that generate realistic tr"},"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":"2506.12203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T20:13:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3b6ec5d66eb4d7acc3c0b713719ac0f157cc92d951b4cedbe535b44f12040b19","abstract_canon_sha256":"bfc2de8bc1e798fc8b0e51049606241ae660fd2e691012edf1e09d886e3358ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:23.232431Z","signature_b64":"F/CYZde7kX1Cb/OEX/P0MR6xBV9sBWNBpNevT05nfOjsi4YbMBPJwHIgHMxOqPm3RU5D4vxctkVi6YIsNl8MDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c8c162379af74f0ab487415fbd45e9ecdc5eff71a52cc2ff19190efd1bd281","last_reissued_at":"2026-07-05T11:21:23.231933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:23.231933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anming Gu, Edward Chien, Kristjan Greenewald","submitted_at":"2025-06-13T20:13:37Z","abstract_excerpt":"We provide an algorithm to privately generate continuous-time data (e.g. marginals from stochastic differential equations), which has applications in highly sensitive domains involving time-series data such as healthcare. We leverage the connections between trajectory inference and continuous-time synthetic data generation, along with a computational method based on mean-field Langevin dynamics. As discretized mean-field Langevin dynamics and noisy particle gradient descent are equivalent, DP results for noisy SGD can be applied to our setting. We provide experiments that generate realistic tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12203","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/2506.12203/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":"2506.12203","created_at":"2026-07-05T11:21:23.231987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12203v1","created_at":"2026-07-05T11:21:23.231987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12203","created_at":"2026-07-05T11:21:23.231987+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DEMCYRXTL3U","created_at":"2026-07-05T11:21:23.231987+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DEMCYRXTL3U6CVU","created_at":"2026-07-05T11:21:23.231987+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DEMCYRX","created_at":"2026-07-05T11:21:23.231987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09151","citing_title":"Convergence Rate of the Solution of Multi-marginal Schrodinger Bridge Problem with Marginal Constraints from SDEs","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H","json":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H.json","graph_json":"https://pith.science/api/pith-number/7DEMCYRXTL3U6CVUQ5AV7PKF5H/graph.json","events_json":"https://pith.science/api/pith-number/7DEMCYRXTL3U6CVUQ5AV7PKF5H/events.json","paper":"https://pith.science/paper/7DEMCYRX"},"agent_actions":{"view_html":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H","download_json":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H.json","view_paper":"https://pith.science/paper/7DEMCYRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12203&json=true","fetch_graph":"https://pith.science/api/pith-number/7DEMCYRXTL3U6CVUQ5AV7PKF5H/graph.json","fetch_events":"https://pith.science/api/pith-number/7DEMCYRXTL3U6CVUQ5AV7PKF5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H/action/storage_attestation","attest_author":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H/action/author_attestation","sign_citation":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H/action/citation_signature","submit_replication":"https://pith.science/pith/7DEMCYRXTL3U6CVUQ5AV7PKF5H/action/replication_record"}},"created_at":"2026-07-05T11:21:23.231987+00:00","updated_at":"2026-07-05T11:21:23.231987+00:00"}