{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RCDGJ7OZFGZBPAHMELYJGZRH3T","short_pith_number":"pith:RCDGJ7OZ","schema_version":"1.0","canonical_sha256":"888664fdd929b21780ec22f0936627dcdad7b364b3d6eda85d8a98779d5ac26e","source":{"kind":"arxiv","id":"2506.13614","version":1},"attestation_state":"computed","paper":{"title":"Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Gregory Bellchambers","submitted_at":"2025-06-16T15:43:28Z","abstract_excerpt":"The success of diffusion models has driven interest in performing conditional sampling via training-free guidance of the denoising process to solve image restoration and other inverse problems. A popular class of methods, based on Diffusion Posterior Sampling (DPS), attempts to approximate the intractable posterior score function directly. In this work, we present a novel expression for the exact posterior score for purely denoising tasks that is tractable in terms of the unconditional score function. We leverage this result to analyze the time-dependent error in the DPS score for denoising ta"},"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":"2506.13614","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-16T15:43:28Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"e0a14efae40488164963e83b607d8001402a4a45e6801daab3ef83a78594f881","abstract_canon_sha256":"d1d9c22058adaa2363be676b47f39d577085a91e91fb853d05dc6200858c12ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:23.443970Z","signature_b64":"I8NSk1PgOEJ9YYNd/Jk204a/iUNbsU25Sn6rRhnY9scZHqHjhUa+7V6xJi/d3GfRKBCKA5GbN0PFygZw18IyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"888664fdd929b21780ec22f0936627dcdad7b364b3d6eda85d8a98779d5ac26e","last_reissued_at":"2026-07-05T11:22:23.443172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:23.443172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Gregory Bellchambers","submitted_at":"2025-06-16T15:43:28Z","abstract_excerpt":"The success of diffusion models has driven interest in performing conditional sampling via training-free guidance of the denoising process to solve image restoration and other inverse problems. A popular class of methods, based on Diffusion Posterior Sampling (DPS), attempts to approximate the intractable posterior score function directly. In this work, we present a novel expression for the exact posterior score for purely denoising tasks that is tractable in terms of the unconditional score function. We leverage this result to analyze the time-dependent error in the DPS score for denoising ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13614","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/2506.13614/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":"2506.13614","created_at":"2026-07-05T11:22:23.443223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13614v1","created_at":"2026-07-05T11:22:23.443223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13614","created_at":"2026-07-05T11:22:23.443223+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCDGJ7OZFGZB","created_at":"2026-07-05T11:22:23.443223+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCDGJ7OZFGZBPAHM","created_at":"2026-07-05T11:22:23.443223+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCDGJ7OZ","created_at":"2026-07-05T11:22:23.443223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.07715","citing_title":"Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T","json":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T.json","graph_json":"https://pith.science/api/pith-number/RCDGJ7OZFGZBPAHMELYJGZRH3T/graph.json","events_json":"https://pith.science/api/pith-number/RCDGJ7OZFGZBPAHMELYJGZRH3T/events.json","paper":"https://pith.science/paper/RCDGJ7OZ"},"agent_actions":{"view_html":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T","download_json":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T.json","view_paper":"https://pith.science/paper/RCDGJ7OZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13614&json=true","fetch_graph":"https://pith.science/api/pith-number/RCDGJ7OZFGZBPAHMELYJGZRH3T/graph.json","fetch_events":"https://pith.science/api/pith-number/RCDGJ7OZFGZBPAHMELYJGZRH3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T/action/storage_attestation","attest_author":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T/action/author_attestation","sign_citation":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T/action/citation_signature","submit_replication":"https://pith.science/pith/RCDGJ7OZFGZBPAHMELYJGZRH3T/action/replication_record"}},"created_at":"2026-07-05T11:22:23.443223+00:00","updated_at":"2026-07-05T11:22:23.443223+00:00"}