{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CTONCEK6NVUQWFW4ECIOPJ6LAW","short_pith_number":"pith:CTONCEK6","schema_version":"1.0","canonical_sha256":"14dcd1115e6d690b16dc2090e7a7cb0581ea148047e05adc1870b30d51a2452d","source":{"kind":"arxiv","id":"2304.11449","version":2},"attestation_state":"computed","paper":{"title":"Posterior Sampling in High Dimension via Diffusion Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Andrea Montanari, Yuchen Wu","submitted_at":"2023-04-22T17:10:28Z","abstract_excerpt":"Sampling from the posterior is a key technical problem in Bayesian statistics. Rigorous guarantees are difficult to obtain for Markov Chain Monte Carlo algorithms of common use. In this paper, we study an alternative class of algorithms based on diffusion processes and variational methods. The diffusion is constructed in such a way that, at its final time, it approximates the target posterior distribution. The drift of this diffusion is given by the posterior expectation of the unknown parameter vector ${\\boldsymbol \\theta}$ given the data and the additional noisy observations.\n  In order to c"},"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":"2304.11449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-04-22T17:10:28Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"1bae4a0c26ec3359f121a5a82cfd68387003005591386a6ef892c0a60c76ffe0","abstract_canon_sha256":"3beb4010d38f064531c39b4d026781c76397c5f05ae1f392e91496cbbcab70e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:19.362129Z","signature_b64":"//f2mHYU51PREusxvvMXf5DU8k0TRnsz4Qy2OnjNK9dm0p34Ov+6fnsG/QVK9s3fXFjyCvBr0aLBtKVx6gvoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14dcd1115e6d690b16dc2090e7a7cb0581ea148047e05adc1870b30d51a2452d","last_reissued_at":"2026-07-05T08:58:19.361661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:19.361661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Posterior Sampling in High Dimension via Diffusion Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Andrea Montanari, Yuchen Wu","submitted_at":"2023-04-22T17:10:28Z","abstract_excerpt":"Sampling from the posterior is a key technical problem in Bayesian statistics. Rigorous guarantees are difficult to obtain for Markov Chain Monte Carlo algorithms of common use. In this paper, we study an alternative class of algorithms based on diffusion processes and variational methods. The diffusion is constructed in such a way that, at its final time, it approximates the target posterior distribution. The drift of this diffusion is given by the posterior expectation of the unknown parameter vector ${\\boldsymbol \\theta}$ given the data and the additional noisy observations.\n  In order to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11449","kind":"arxiv","version":2},"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/2304.11449/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":"2304.11449","created_at":"2026-07-05T08:58:19.361720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11449v2","created_at":"2026-07-05T08:58:19.361720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11449","created_at":"2026-07-05T08:58:19.361720+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTONCEK6NVUQ","created_at":"2026-07-05T08:58:19.361720+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTONCEK6NVUQWFW4","created_at":"2026-07-05T08:58:19.361720+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTONCEK6","created_at":"2026-07-05T08:58:19.361720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06813","citing_title":"Mixing of Glauber Dynamics on High Overlap Gibbs Measures","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07220","citing_title":"On the Robustness of Distribution Support under Diffusion Guidance","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20092","citing_title":"How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07220","citing_title":"On the Robustness of Distribution Support under Diffusion Guidance","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW","json":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW.json","graph_json":"https://pith.science/api/pith-number/CTONCEK6NVUQWFW4ECIOPJ6LAW/graph.json","events_json":"https://pith.science/api/pith-number/CTONCEK6NVUQWFW4ECIOPJ6LAW/events.json","paper":"https://pith.science/paper/CTONCEK6"},"agent_actions":{"view_html":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW","download_json":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW.json","view_paper":"https://pith.science/paper/CTONCEK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11449&json=true","fetch_graph":"https://pith.science/api/pith-number/CTONCEK6NVUQWFW4ECIOPJ6LAW/graph.json","fetch_events":"https://pith.science/api/pith-number/CTONCEK6NVUQWFW4ECIOPJ6LAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW/action/storage_attestation","attest_author":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW/action/author_attestation","sign_citation":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW/action/citation_signature","submit_replication":"https://pith.science/pith/CTONCEK6NVUQWFW4ECIOPJ6LAW/action/replication_record"}},"created_at":"2026-07-05T08:58:19.361720+00:00","updated_at":"2026-07-05T08:58:19.361720+00:00"}