{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OQA5JWQE62DAL6GFMC2PD6TO2E","short_pith_number":"pith:OQA5JWQE","schema_version":"1.0","canonical_sha256":"7401d4da04f68605f8c560b4f1fa6ed132fe35501dc582f9e77d7b73049bf7c0","source":{"kind":"arxiv","id":"2111.10510","version":9},"attestation_state":"computed","paper":{"title":"Bayesian Learning via Neural Schr\\\"odinger-F\\\"ollmer Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrius Ovsianas, David Fernandes, Francisco Vargas, Mark Girolami, Neil D. Lawrence, Nikolas N\\\"usken","submitted_at":"2021-11-20T03:51:18Z","abstract_excerpt":"In this work we explore a new framework for approximate Bayesian inference in large datasets based on stochastic control (i.e. Schr\\\"odinger bridges). We advocate stochastic control as a finite time and low variance alternative to popular steady-state methods such as stochastic gradient Langevin dynamics (SGLD). Furthermore, we discuss and adapt the existing theoretical guarantees of this framework and establish connections to already existing VI routines in SDE-based models."},"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":"2111.10510","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-20T03:51:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a6db02716691d3ede2d260924f1ba24f51df7c2daa3bbfe92e4d32a05d6cf73","abstract_canon_sha256":"39de0860fa6019d47ed76a293b8854778b9d88f6069e0fa23132e69fc3fded11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:35.394396Z","signature_b64":"SDEw8h4jSIB7Z5avf0STAOwmNjsdLT4ht5zn0py9s7uKw2DsTVYG0VSRNlrrM1WB9KUx9BxNL2R34X0yfrlsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7401d4da04f68605f8c560b4f1fa6ed132fe35501dc582f9e77d7b73049bf7c0","last_reissued_at":"2026-07-05T05:10:35.393871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:35.393871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Learning via Neural Schr\\\"odinger-F\\\"ollmer Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrius Ovsianas, David Fernandes, Francisco Vargas, Mark Girolami, Neil D. Lawrence, Nikolas N\\\"usken","submitted_at":"2021-11-20T03:51:18Z","abstract_excerpt":"In this work we explore a new framework for approximate Bayesian inference in large datasets based on stochastic control (i.e. Schr\\\"odinger bridges). We advocate stochastic control as a finite time and low variance alternative to popular steady-state methods such as stochastic gradient Langevin dynamics (SGLD). Furthermore, we discuss and adapt the existing theoretical guarantees of this framework and establish connections to already existing VI routines in SDE-based models."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10510","kind":"arxiv","version":9},"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/2111.10510/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":"2111.10510","created_at":"2026-07-05T05:10:35.393930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10510v9","created_at":"2026-07-05T05:10:35.393930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10510","created_at":"2026-07-05T05:10:35.393930+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQA5JWQE62DA","created_at":"2026-07-05T05:10:35.393930+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQA5JWQE62DAL6GF","created_at":"2026-07-05T05:10:35.393930+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQA5JWQE","created_at":"2026-07-05T05:10:35.393930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20052","citing_title":"Annealed Langevin Monte Carlo for Flow ODE Sampling","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E","json":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E.json","graph_json":"https://pith.science/api/pith-number/OQA5JWQE62DAL6GFMC2PD6TO2E/graph.json","events_json":"https://pith.science/api/pith-number/OQA5JWQE62DAL6GFMC2PD6TO2E/events.json","paper":"https://pith.science/paper/OQA5JWQE"},"agent_actions":{"view_html":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E","download_json":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E.json","view_paper":"https://pith.science/paper/OQA5JWQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10510&json=true","fetch_graph":"https://pith.science/api/pith-number/OQA5JWQE62DAL6GFMC2PD6TO2E/graph.json","fetch_events":"https://pith.science/api/pith-number/OQA5JWQE62DAL6GFMC2PD6TO2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E/action/storage_attestation","attest_author":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E/action/author_attestation","sign_citation":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E/action/citation_signature","submit_replication":"https://pith.science/pith/OQA5JWQE62DAL6GFMC2PD6TO2E/action/replication_record"}},"created_at":"2026-07-05T05:10:35.393930+00:00","updated_at":"2026-07-05T05:10:35.393930+00:00"}