{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DGM5LT2SXMCIGPHYJMJEMCL2JW","short_pith_number":"pith:DGM5LT2S","schema_version":"1.0","canonical_sha256":"1999d5cf52bb04833cf84b1246097a4d8b1054349c28174e1460095bcdeeef33","source":{"kind":"arxiv","id":"2410.09945","version":2},"attestation_state":"computed","paper":{"title":"Variational Diffusion Posterior Sampling with Midpoint Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alain Durmus, Badr Moufad, Eric Moulines, Jimmy Olsson, Lisa Bedin, Randal Douc, Yazid Janati","submitted_at":"2024-10-13T18:03:53Z","abstract_excerpt":"Diffusion models have recently shown considerable potential in solving Bayesian inverse problems when used as priors. However, sampling from the resulting denoising posterior distributions remains a challenge as it involves intractable terms. To tackle this issue, state-of-the-art approaches formulate the problem as that of sampling from a surrogate diffusion model targeting the posterior and decompose its scores into two terms: the prior score and an intractable guidance term. While the former is replaced by the pre-trained score of the considered diffusion model, the guidance term has to be "},"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":"2410.09945","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-13T18:03:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b547098aa776248dcab8d077251d15a766d8aaacba2bafe9901f8da9960dd207","abstract_canon_sha256":"f13c6f6b5d798ba60311e0d6fdfffbf0f5b5f0f8c245768993c17d34a517f083"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:44.548514Z","signature_b64":"FOiyMhegQoraJ6m8re1PfNpzQjbApfrzdKy5V91+eYKJrfgiRfdCJCi9fDLTuCpIYIwIzS8OQ6J/Ww2bjVXGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1999d5cf52bb04833cf84b1246097a4d8b1054349c28174e1460095bcdeeef33","last_reissued_at":"2026-07-05T09:53:44.548069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:44.548069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Diffusion Posterior Sampling with Midpoint Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alain Durmus, Badr Moufad, Eric Moulines, Jimmy Olsson, Lisa Bedin, Randal Douc, Yazid Janati","submitted_at":"2024-10-13T18:03:53Z","abstract_excerpt":"Diffusion models have recently shown considerable potential in solving Bayesian inverse problems when used as priors. However, sampling from the resulting denoising posterior distributions remains a challenge as it involves intractable terms. To tackle this issue, state-of-the-art approaches formulate the problem as that of sampling from a surrogate diffusion model targeting the posterior and decompose its scores into two terms: the prior score and an intractable guidance term. While the former is replaced by the pre-trained score of the considered diffusion model, the guidance term has to be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09945","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/2410.09945/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":"2410.09945","created_at":"2026-07-05T09:53:44.548132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09945v2","created_at":"2026-07-05T09:53:44.548132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09945","created_at":"2026-07-05T09:53:44.548132+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGM5LT2SXMCI","created_at":"2026-07-05T09:53:44.548132+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGM5LT2SXMCIGPHY","created_at":"2026-07-05T09:53:44.548132+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGM5LT2S","created_at":"2026-07-05T09:53:44.548132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.20549","citing_title":"Sample-efficient evidence estimation of score based priors for model selection","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW","json":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW.json","graph_json":"https://pith.science/api/pith-number/DGM5LT2SXMCIGPHYJMJEMCL2JW/graph.json","events_json":"https://pith.science/api/pith-number/DGM5LT2SXMCIGPHYJMJEMCL2JW/events.json","paper":"https://pith.science/paper/DGM5LT2S"},"agent_actions":{"view_html":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW","download_json":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW.json","view_paper":"https://pith.science/paper/DGM5LT2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09945&json=true","fetch_graph":"https://pith.science/api/pith-number/DGM5LT2SXMCIGPHYJMJEMCL2JW/graph.json","fetch_events":"https://pith.science/api/pith-number/DGM5LT2SXMCIGPHYJMJEMCL2JW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW/action/storage_attestation","attest_author":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW/action/author_attestation","sign_citation":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW/action/citation_signature","submit_replication":"https://pith.science/pith/DGM5LT2SXMCIGPHYJMJEMCL2JW/action/replication_record"}},"created_at":"2026-07-05T09:53:44.548132+00:00","updated_at":"2026-07-05T09:53:44.548132+00:00"}