{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7MBDP6B72ABPMNURWEHSXGZTE4","short_pith_number":"pith:7MBDP6B7","schema_version":"1.0","canonical_sha256":"fb0237f83fd002f63691b10f2b9b332708a9a370a0efd279ade3ca731d5bbfac","source":{"kind":"arxiv","id":"2309.13598","version":2},"attestation_state":"computed","paper":{"title":"On the Posterior Distribution in Denoising: Application to Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Hila Manor, Tomer Michaeli","submitted_at":"2023-09-24T10:07:40Z","abstract_excerpt":"Denoisers play a central role in many applications, from noise suppression in low-grade imaging sensors, to empowering score-based generative models. The latter category of methods makes use of Tweedie's formula, which links the posterior mean in Gaussian denoising (\\ie the minimum MSE denoiser) with the score of the data distribution. Here, we derive a fundamental relation between the higher-order central moments of the posterior distribution, and the higher-order derivatives of the posterior mean. We harness this result for uncertainty quantification of pre-trained denoisers. Particularly, w"},"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":"2309.13598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-24T10:07:40Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"345fb3263d2a18e79ef0807cd7f95b980b44d51ad7de06c9e0b746f025dfbd5c","abstract_canon_sha256":"0b5baaba842471117f9911e23955a0fb9ab754dbdf92cf041b68201395c2653d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:23.213507Z","signature_b64":"hQ3yrcs3SGygRO3fxDZVVgnPF2hNmo3mGoY4nfMT0ItWBqJsHVYFNHiFZJlu2yHM8JaeHL7PXxatmElOetrUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb0237f83fd002f63691b10f2b9b332708a9a370a0efd279ade3ca731d5bbfac","last_reissued_at":"2026-07-05T07:46:23.212965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:23.212965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Posterior Distribution in Denoising: Application to Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Hila Manor, Tomer Michaeli","submitted_at":"2023-09-24T10:07:40Z","abstract_excerpt":"Denoisers play a central role in many applications, from noise suppression in low-grade imaging sensors, to empowering score-based generative models. The latter category of methods makes use of Tweedie's formula, which links the posterior mean in Gaussian denoising (\\ie the minimum MSE denoiser) with the score of the data distribution. Here, we derive a fundamental relation between the higher-order central moments of the posterior distribution, and the higher-order derivatives of the posterior mean. We harness this result for uncertainty quantification of pre-trained denoisers. Particularly, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13598","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/2309.13598/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":"2309.13598","created_at":"2026-07-05T07:46:23.213027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13598v2","created_at":"2026-07-05T07:46:23.213027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13598","created_at":"2026-07-05T07:46:23.213027+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MBDP6B72ABP","created_at":"2026-07-05T07:46:23.213027+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MBDP6B72ABPMNUR","created_at":"2026-07-05T07:46:23.213027+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MBDP6B7","created_at":"2026-07-05T07:46:23.213027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22723","citing_title":"The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4","json":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4.json","graph_json":"https://pith.science/api/pith-number/7MBDP6B72ABPMNURWEHSXGZTE4/graph.json","events_json":"https://pith.science/api/pith-number/7MBDP6B72ABPMNURWEHSXGZTE4/events.json","paper":"https://pith.science/paper/7MBDP6B7"},"agent_actions":{"view_html":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4","download_json":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4.json","view_paper":"https://pith.science/paper/7MBDP6B7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13598&json=true","fetch_graph":"https://pith.science/api/pith-number/7MBDP6B72ABPMNURWEHSXGZTE4/graph.json","fetch_events":"https://pith.science/api/pith-number/7MBDP6B72ABPMNURWEHSXGZTE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4/action/storage_attestation","attest_author":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4/action/author_attestation","sign_citation":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4/action/citation_signature","submit_replication":"https://pith.science/pith/7MBDP6B72ABPMNURWEHSXGZTE4/action/replication_record"}},"created_at":"2026-07-05T07:46:23.213027+00:00","updated_at":"2026-07-05T07:46:23.213027+00:00"}