{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LBKQZOMNADQCBHHKH7OTGZJSRT","short_pith_number":"pith:LBKQZOMN","schema_version":"1.0","canonical_sha256":"58550cb98d00e0209cea3fdd3365328ce617299506cd85d169920587a85d391c","source":{"kind":"arxiv","id":"2308.14106","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Schr\\\"{o}dinger Bridges for Bayesian Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Arnaud Doucet, Jeremy Heng, Valentin De Bortoli","submitted_at":"2023-08-27T13:22:55Z","abstract_excerpt":"Denoising diffusion models are a novel class of generative models that have recently become extremely popular in machine learning. In this paper, we describe how such ideas can also be used to sample from posterior distributions and, more generally, any target distribution whose density is known up to a normalizing constant. The key idea is to consider a forward ``noising'' diffusion initialized at the target distribution which ``transports'' this latter to a normal distribution for long diffusion times. The time-reversal of this process, the ``denoising'' diffusion, thus ``transports'' the no"},"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":"2308.14106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.CO","submitted_at":"2023-08-27T13:22:55Z","cross_cats_sorted":[],"title_canon_sha256":"8f9c43ea96764eb75484f52b7755036f42af4b3398913657270e13dc71d701b4","abstract_canon_sha256":"d2577bae47421ae65e61c6c81a6abca0dc44f23a1389da96a882f500dd2e8db3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:21.846676Z","signature_b64":"HojsAltl7V3hch33nIsXd8gcfGj7N+7fPoGa0rUjxzAkVTwtr8pBREq3rHb1oV8vocZisuZHBIwRglhOtwqFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58550cb98d00e0209cea3fdd3365328ce617299506cd85d169920587a85d391c","last_reissued_at":"2026-07-05T06:45:21.846273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:21.846273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Schr\\\"{o}dinger Bridges for Bayesian Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Arnaud Doucet, Jeremy Heng, Valentin De Bortoli","submitted_at":"2023-08-27T13:22:55Z","abstract_excerpt":"Denoising diffusion models are a novel class of generative models that have recently become extremely popular in machine learning. In this paper, we describe how such ideas can also be used to sample from posterior distributions and, more generally, any target distribution whose density is known up to a normalizing constant. The key idea is to consider a forward ``noising'' diffusion initialized at the target distribution which ``transports'' this latter to a normal distribution for long diffusion times. The time-reversal of this process, the ``denoising'' diffusion, thus ``transports'' the no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14106","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/2308.14106/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":"2308.14106","created_at":"2026-07-05T06:45:21.846338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14106v1","created_at":"2026-07-05T06:45:21.846338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14106","created_at":"2026-07-05T06:45:21.846338+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBKQZOMNADQC","created_at":"2026-07-05T06:45:21.846338+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBKQZOMNADQCBHHK","created_at":"2026-07-05T06:45:21.846338+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBKQZOMN","created_at":"2026-07-05T06:45:21.846338+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/LBKQZOMNADQCBHHKH7OTGZJSRT","json":"https://pith.science/pith/LBKQZOMNADQCBHHKH7OTGZJSRT.json","graph_json":"https://pith.science/api/pith-number/LBKQZOMNADQCBHHKH7OTGZJSRT/graph.json","events_json":"https://pith.science/api/pith-number/LBKQZOMNADQCBHHKH7OTGZJSRT/events.json","paper":"https://pith.science/paper/LBKQZOMN"},"agent_actions":{"view_html":"https://pith.science/pith/LBKQZOMNADQCBHHKH7OTGZJSRT","download_json":"https://pith.science/pith/LBKQZOMNADQCBHHKH7OTGZJSRT.json","view_paper":"https://pith.science/paper/LBKQZOMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14106&json=true","fetch_graph":"https://pith.science/api/pith-number/LBKQZOMNADQCBHHKH7OTGZJSRT/graph.json","fetch_events":"https://pith.science/api/pith-number/LBKQZOMNADQCBHHKH7OTGZJSRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBKQZOMNADQCBHHKH7OTGZJSRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBKQZOMNADQCBHHKH7OTGZJSRT/action/storage_attestation","attest_author":"https://pith.science/pith/LBKQZOMNADQCBHHKH7OTGZJSRT/action/author_attestation","sign_citation":"https://pith.science/pith/LBKQZOMNADQCBHHKH7OTGZJSRT/action/citation_signature","submit_replication":"https://pith.science/pith/LBKQZOMNADQCBHHKH7OTGZJSRT/action/replication_record"}},"created_at":"2026-07-05T06:45:21.846338+00:00","updated_at":"2026-07-05T06:45:21.846338+00:00"}