{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FUF2MRXYTESIPFAFYOK2JXNFQ7","short_pith_number":"pith:FUF2MRXY","schema_version":"1.0","canonical_sha256":"2d0ba646f89924879405c395a4dda587dd28bceac1dd9617ae86d235c7899ad8","source":{"kind":"arxiv","id":"2502.03332","version":1},"attestation_state":"computed","paper":{"title":"A Mixture-Based Framework for Guiding Diffusion Models","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, Mehdi Abou El Qassime, Yazid Janati","submitted_at":"2025-02-05T16:26:06Z","abstract_excerpt":"Denoising diffusion models have driven significant progress in the field of Bayesian inverse problems. Recent approaches use pre-trained diffusion models as priors to solve a wide range of such problems, only leveraging inference-time compute and thereby eliminating the need to retrain task-specific models on the same dataset. To approximate the posterior of a Bayesian inverse problem, a diffusion model samples from a sequence of intermediate posterior distributions, each with an intractable likelihood function. This work proposes a novel mixture approximation of these intermediate distributio"},"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":"2502.03332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-05T16:26:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5013514c6db371bb462e86a3fe0b9c685bbf392b46faef1b7e63293af92ee512","abstract_canon_sha256":"04e3b0f84956c226c4acf1cbef4286106b4e6ea9998dc308e011cdaa1023cfd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:03.338002Z","signature_b64":"XctaqITbroDfsYGEXhvPMbQYRzjAl0Wh3WDU/fk/P1pbHMEpQXar2uwG6JJ8tmL7nOq1ERYkh7QTXZUPHJSbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d0ba646f89924879405c395a4dda587dd28bceac1dd9617ae86d235c7899ad8","last_reissued_at":"2026-07-05T10:10:03.337532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:03.337532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mixture-Based Framework for Guiding Diffusion Models","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, Mehdi Abou El Qassime, Yazid Janati","submitted_at":"2025-02-05T16:26:06Z","abstract_excerpt":"Denoising diffusion models have driven significant progress in the field of Bayesian inverse problems. Recent approaches use pre-trained diffusion models as priors to solve a wide range of such problems, only leveraging inference-time compute and thereby eliminating the need to retrain task-specific models on the same dataset. To approximate the posterior of a Bayesian inverse problem, a diffusion model samples from a sequence of intermediate posterior distributions, each with an intractable likelihood function. This work proposes a novel mixture approximation of these intermediate distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03332","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/2502.03332/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":"2502.03332","created_at":"2026-07-05T10:10:03.337590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.03332v1","created_at":"2026-07-05T10:10:03.337590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03332","created_at":"2026-07-05T10:10:03.337590+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUF2MRXYTESI","created_at":"2026-07-05T10:10:03.337590+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUF2MRXYTESIPFAF","created_at":"2026-07-05T10:10:03.337590+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUF2MRXY","created_at":"2026-07-05T10:10:03.337590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.05482","citing_title":"Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14267","citing_title":"Image Restoration via Diffusion Models with Dynamic Resolution","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7","json":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7.json","graph_json":"https://pith.science/api/pith-number/FUF2MRXYTESIPFAFYOK2JXNFQ7/graph.json","events_json":"https://pith.science/api/pith-number/FUF2MRXYTESIPFAFYOK2JXNFQ7/events.json","paper":"https://pith.science/paper/FUF2MRXY"},"agent_actions":{"view_html":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7","download_json":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7.json","view_paper":"https://pith.science/paper/FUF2MRXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.03332&json=true","fetch_graph":"https://pith.science/api/pith-number/FUF2MRXYTESIPFAFYOK2JXNFQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/FUF2MRXYTESIPFAFYOK2JXNFQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7/action/storage_attestation","attest_author":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7/action/author_attestation","sign_citation":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7/action/citation_signature","submit_replication":"https://pith.science/pith/FUF2MRXYTESIPFAFYOK2JXNFQ7/action/replication_record"}},"created_at":"2026-07-05T10:10:03.337590+00:00","updated_at":"2026-07-05T10:10:03.337590+00:00"}