{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DXP7OMN4E6ENZHTMIBBAFOEN22","short_pith_number":"pith:DXP7OMN4","schema_version":"1.0","canonical_sha256":"1ddff731bc2788dc9e6c404202b88dd6954b15d74262399e35fb4a83fb477d42","source":{"kind":"arxiv","id":"2307.01050","version":12},"attestation_state":"computed","paper":{"title":"Transport meets Variational Inference: Controlled Monte Carlo Diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Denis Blessing, Francisco Vargas, Nikolas N\\\"usken, Shreyas Padhy","submitted_at":"2023-07-03T14:28:36Z","abstract_excerpt":"Connecting optimal transport and variational inference, we present a principled and systematic framework for sampling and generative modelling centred around divergences on path space. Our work culminates in the development of the \\emph{Controlled Monte Carlo Diffusion} sampler (CMCD) for Bayesian computation, a score-based annealing technique that crucially adapts both forward and backward dynamics in a diffusion model. On the way, we clarify the relationship between the EM-algorithm and iterative proportional fitting (IPF) for Schr{\\\"o}dinger bridges, deriving as well a regularised objective"},"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":"2307.01050","kind":"arxiv","version":12},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-07-03T14:28:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"83ea83c95c050c2f3e7b776f89884a0e032667dcf3d8e75c83b19e6732e4ba43","abstract_canon_sha256":"05a822b50b306cc38bed4c342387dd8a01be0ba8dd4d29fac5281916ee256101"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:45.706262Z","signature_b64":"V0ZDDDlQLEU/cWzHBQPeJoMef8pUeTWBEJxJt3p2zB88/l6gRk4rKBIxXynWn4AAA9ZQei/CpubSwc437R4pDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ddff731bc2788dc9e6c404202b88dd6954b15d74262399e35fb4a83fb477d42","last_reissued_at":"2026-07-05T10:59:45.705771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:45.705771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transport meets Variational Inference: Controlled Monte Carlo Diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Denis Blessing, Francisco Vargas, Nikolas N\\\"usken, Shreyas Padhy","submitted_at":"2023-07-03T14:28:36Z","abstract_excerpt":"Connecting optimal transport and variational inference, we present a principled and systematic framework for sampling and generative modelling centred around divergences on path space. Our work culminates in the development of the \\emph{Controlled Monte Carlo Diffusion} sampler (CMCD) for Bayesian computation, a score-based annealing technique that crucially adapts both forward and backward dynamics in a diffusion model. On the way, we clarify the relationship between the EM-algorithm and iterative proportional fitting (IPF) for Schr{\\\"o}dinger bridges, deriving as well a regularised objective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01050","kind":"arxiv","version":12},"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/2307.01050/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":"2307.01050","created_at":"2026-07-05T10:59:45.705829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01050v12","created_at":"2026-07-05T10:59:45.705829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01050","created_at":"2026-07-05T10:59:45.705829+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXP7OMN4E6EN","created_at":"2026-07-05T10:59:45.705829+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXP7OMN4E6ENZHTM","created_at":"2026-07-05T10:59:45.705829+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXP7OMN4","created_at":"2026-07-05T10:59:45.705829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08160","citing_title":"Weak Poincar\\'e Inequalities via Approximate Stochastic Localization: Application to Sampling the Sherrington-Kirkpatrick Model","ref_index":195,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31498","citing_title":"Scalable Inference-Time Annealing with Surrogate Likelihood Estimators","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03718","citing_title":"Potential Hessian Ascent III: Sampling the Sherrington--Kirkpatrick Model at Beta < 1/2","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03718","citing_title":"Potential Hessian Ascent III: Sampling the Sherrington--Kirkpatrick Model at Beta < 1/2","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22","json":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22.json","graph_json":"https://pith.science/api/pith-number/DXP7OMN4E6ENZHTMIBBAFOEN22/graph.json","events_json":"https://pith.science/api/pith-number/DXP7OMN4E6ENZHTMIBBAFOEN22/events.json","paper":"https://pith.science/paper/DXP7OMN4"},"agent_actions":{"view_html":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22","download_json":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22.json","view_paper":"https://pith.science/paper/DXP7OMN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01050&json=true","fetch_graph":"https://pith.science/api/pith-number/DXP7OMN4E6ENZHTMIBBAFOEN22/graph.json","fetch_events":"https://pith.science/api/pith-number/DXP7OMN4E6ENZHTMIBBAFOEN22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22/action/storage_attestation","attest_author":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22/action/author_attestation","sign_citation":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22/action/citation_signature","submit_replication":"https://pith.science/pith/DXP7OMN4E6ENZHTMIBBAFOEN22/action/replication_record"}},"created_at":"2026-07-05T10:59:45.705829+00:00","updated_at":"2026-07-05T10:59:45.705829+00:00"}