{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X4P7SXODM5CNTIO4MSZXTI6YOR","short_pith_number":"pith:X4P7SXOD","schema_version":"1.0","canonical_sha256":"bf1ff95dc36744d9a1dc64b379a3d87447883b73dfe658889770895ac42161e0","source":{"kind":"arxiv","id":"2405.00126","version":1},"attestation_state":"computed","paper":{"title":"A variational approach to sampling in diffusion processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"math.OC","authors_text":"Maxim Raginsky","submitted_at":"2024-04-30T18:21:42Z","abstract_excerpt":"We revisit the work of Mitter and Newton on an information-theoretic interpretation of Bayes' formula through the Gibbs variational principle. This formulation allowed them to pose nonlinear estimation for diffusion processes as a problem in stochastic optimal control, so that the posterior density of the signal given the observation path could be sampled by adding a drift to the signal process. We show that this control-theoretic approach to sampling provides a common mechanism underlying several distinct problems involving diffusion processes, specifically importance sampling using Feynman-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":"2405.00126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-04-30T18:21:42Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"ae7d805b8abe4641255a6b67e2b0d87b2f03e7ffc3dc7a7e594096c543480e77","abstract_canon_sha256":"a3bba323de96f4bd2f0a84b5e86f3fb46f41e587c5984dadaae9136cc72aef3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:08.898837Z","signature_b64":"yXRG9xG8BpRCxrKGdZ37HgF+sWsBmWdjL3BgGAYwxlFO2jAKSF/OcZwL0qfNas0dJaycnMp52IjxFYrK6336CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf1ff95dc36744d9a1dc64b379a3d87447883b73dfe658889770895ac42161e0","last_reissued_at":"2026-07-05T08:14:08.892385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:08.892385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A variational approach to sampling in diffusion processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"math.OC","authors_text":"Maxim Raginsky","submitted_at":"2024-04-30T18:21:42Z","abstract_excerpt":"We revisit the work of Mitter and Newton on an information-theoretic interpretation of Bayes' formula through the Gibbs variational principle. This formulation allowed them to pose nonlinear estimation for diffusion processes as a problem in stochastic optimal control, so that the posterior density of the signal given the observation path could be sampled by adding a drift to the signal process. We show that this control-theoretic approach to sampling provides a common mechanism underlying several distinct problems involving diffusion processes, specifically importance sampling using Feynman-K"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00126","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/2405.00126/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":"2405.00126","created_at":"2026-07-05T08:14:08.895388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00126v1","created_at":"2026-07-05T08:14:08.895388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00126","created_at":"2026-07-05T08:14:08.895388+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4P7SXODM5CN","created_at":"2026-07-05T08:14:08.895388+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4P7SXODM5CNTIO4","created_at":"2026-07-05T08:14:08.895388+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4P7SXOD","created_at":"2026-07-05T08:14:08.895388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.21860","citing_title":"Pathwise Learning of Stochastic Dynamical Systems with Partial Observations","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR","json":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR.json","graph_json":"https://pith.science/api/pith-number/X4P7SXODM5CNTIO4MSZXTI6YOR/graph.json","events_json":"https://pith.science/api/pith-number/X4P7SXODM5CNTIO4MSZXTI6YOR/events.json","paper":"https://pith.science/paper/X4P7SXOD"},"agent_actions":{"view_html":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR","download_json":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR.json","view_paper":"https://pith.science/paper/X4P7SXOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00126&json=true","fetch_graph":"https://pith.science/api/pith-number/X4P7SXODM5CNTIO4MSZXTI6YOR/graph.json","fetch_events":"https://pith.science/api/pith-number/X4P7SXODM5CNTIO4MSZXTI6YOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR/action/storage_attestation","attest_author":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR/action/author_attestation","sign_citation":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR/action/citation_signature","submit_replication":"https://pith.science/pith/X4P7SXODM5CNTIO4MSZXTI6YOR/action/replication_record"}},"created_at":"2026-07-05T08:14:08.895388+00:00","updated_at":"2026-07-05T08:14:08.895388+00:00"}