{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V73NZBPPZARZ6E7CSC6BHEXY2J","short_pith_number":"pith:V73NZBPP","schema_version":"1.0","canonical_sha256":"aff6dc85efc8239f13e290bc1392f8d2548f754fa835e036797d6d6096a18bbf","source":{"kind":"arxiv","id":"2506.01904","version":1},"attestation_state":"computed","paper":{"title":"Machine-Learned Sampling of Conditioned Path Measures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Qijia Jiang, Reuben Cohn-Gordon","submitted_at":"2025-06-02T17:25:03Z","abstract_excerpt":"We propose algorithms for sampling from posterior path measures $P(C([0, T], \\mathbb{R}^d))$ under a general prior process. This leverages ideas from (1) controlled equilibrium dynamics, which gradually transport between two path measures, and (2) optimization in $\\infty$-dimensional probability space endowed with a Wasserstein metric, which can be used to evolve a density curve under the specified likelihood. The resulting algorithms are theoretically grounded and can be integrated seamlessly with neural networks for learning the target trajectory ensembles, without access to data."},"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":"2506.01904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-02T17:25:03Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"e1c910c66c4b6432c8aa1bc2d2e61cbb1480c191782b98d06caf5fb158833b72","abstract_canon_sha256":"b8ed172e5f4d88f68b0205f1f363f2c8b0953595fb54c232078ad5e8ec5d227f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:21.114438Z","signature_b64":"0G2X002WyFXjVpT4G+y3gU9XH3FP5qanqUxWU0BKAu+COhYz4grHa/OobK8wW+FdT0iv2NXhSeW5hflxwrKtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aff6dc85efc8239f13e290bc1392f8d2548f754fa835e036797d6d6096a18bbf","last_reissued_at":"2026-07-05T11:14:21.113984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:21.113984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine-Learned Sampling of Conditioned Path Measures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Qijia Jiang, Reuben Cohn-Gordon","submitted_at":"2025-06-02T17:25:03Z","abstract_excerpt":"We propose algorithms for sampling from posterior path measures $P(C([0, T], \\mathbb{R}^d))$ under a general prior process. This leverages ideas from (1) controlled equilibrium dynamics, which gradually transport between two path measures, and (2) optimization in $\\infty$-dimensional probability space endowed with a Wasserstein metric, which can be used to evolve a density curve under the specified likelihood. The resulting algorithms are theoretically grounded and can be integrated seamlessly with neural networks for learning the target trajectory ensembles, without access to data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01904","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/2506.01904/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":"2506.01904","created_at":"2026-07-05T11:14:21.114039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01904v1","created_at":"2026-07-05T11:14:21.114039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01904","created_at":"2026-07-05T11:14:21.114039+00:00"},{"alias_kind":"pith_short_12","alias_value":"V73NZBPPZARZ","created_at":"2026-07-05T11:14:21.114039+00:00"},{"alias_kind":"pith_short_16","alias_value":"V73NZBPPZARZ6E7C","created_at":"2026-07-05T11:14:21.114039+00:00"},{"alias_kind":"pith_short_8","alias_value":"V73NZBPP","created_at":"2026-07-05T11:14:21.114039+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J","json":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J.json","graph_json":"https://pith.science/api/pith-number/V73NZBPPZARZ6E7CSC6BHEXY2J/graph.json","events_json":"https://pith.science/api/pith-number/V73NZBPPZARZ6E7CSC6BHEXY2J/events.json","paper":"https://pith.science/paper/V73NZBPP"},"agent_actions":{"view_html":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J","download_json":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J.json","view_paper":"https://pith.science/paper/V73NZBPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01904&json=true","fetch_graph":"https://pith.science/api/pith-number/V73NZBPPZARZ6E7CSC6BHEXY2J/graph.json","fetch_events":"https://pith.science/api/pith-number/V73NZBPPZARZ6E7CSC6BHEXY2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J/action/storage_attestation","attest_author":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J/action/author_attestation","sign_citation":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J/action/citation_signature","submit_replication":"https://pith.science/pith/V73NZBPPZARZ6E7CSC6BHEXY2J/action/replication_record"}},"created_at":"2026-07-05T11:14:21.114039+00:00","updated_at":"2026-07-05T11:14:21.114039+00:00"}