{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F3SAMOM4YANBY32BQ5OBS6RJPP","short_pith_number":"pith:F3SAMOM4","schema_version":"1.0","canonical_sha256":"2ee406399cc01a1c6f41875c197a297bfcee93c07aec83d05db8fc08a1585f82","source":{"kind":"arxiv","id":"2602.07715","version":2},"attestation_state":"computed","paper":{"title":"Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joseph Keshet, Michael Elad, Roi Benita","submitted_at":"2026-02-07T21:44:52Z","abstract_excerpt":"Recovering a signal from its degraded measurements is a long standing challenge in science and engineering. Recently, zero-shot diffusion based methods have been proposed for such inverse problems, offering a posterior sampling based solution that leverages prior knowledge. Such algorithms incorporate the observations through inference, often leaning on manual tuning and heuristics. In this work we propose a rigorous analysis of these approximate posterior samplers, relying on a Gaussianity assumption of the prior. Under this regime, we show that both the ideal posterior sampler and diffusion-"},"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":"2602.07715","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-07T21:44:52Z","cross_cats_sorted":[],"title_canon_sha256":"bc90433cf36e449bffd59c6429bbae01d1de65c24d577e71c498026d8dddb748","abstract_canon_sha256":"398318956a6a3e690fe54629fd824f01fc75686d4f6e001162bdba305876161c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:05.182133Z","signature_b64":"0xO062XBsZTgjsQDZv7Z8rKghgslAn88Ar0owEffMdKhs12J+eX4DrgQJGOX908mY7vYCTwUweNHY6DdMNBCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ee406399cc01a1c6f41875c197a297bfcee93c07aec83d05db8fc08a1585f82","last_reissued_at":"2026-05-20T00:03:05.181276Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:05.181276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joseph Keshet, Michael Elad, Roi Benita","submitted_at":"2026-02-07T21:44:52Z","abstract_excerpt":"Recovering a signal from its degraded measurements is a long standing challenge in science and engineering. Recently, zero-shot diffusion based methods have been proposed for such inverse problems, offering a posterior sampling based solution that leverages prior knowledge. Such algorithms incorporate the observations through inference, often leaning on manual tuning and heuristics. In this work we propose a rigorous analysis of these approximate posterior samplers, relying on a Gaussianity assumption of the prior. Under this regime, we show that both the ideal posterior sampler and diffusion-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07715","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/2602.07715/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":"2602.07715","created_at":"2026-05-20T00:03:05.181428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.07715v2","created_at":"2026-05-20T00:03:05.181428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07715","created_at":"2026-05-20T00:03:05.181428+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3SAMOM4YANB","created_at":"2026-05-20T00:03:05.181428+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3SAMOM4YANBY32B","created_at":"2026-05-20T00:03:05.181428+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3SAMOM4","created_at":"2026-05-20T00:03:05.181428+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/F3SAMOM4YANBY32BQ5OBS6RJPP","json":"https://pith.science/pith/F3SAMOM4YANBY32BQ5OBS6RJPP.json","graph_json":"https://pith.science/api/pith-number/F3SAMOM4YANBY32BQ5OBS6RJPP/graph.json","events_json":"https://pith.science/api/pith-number/F3SAMOM4YANBY32BQ5OBS6RJPP/events.json","paper":"https://pith.science/paper/F3SAMOM4"},"agent_actions":{"view_html":"https://pith.science/pith/F3SAMOM4YANBY32BQ5OBS6RJPP","download_json":"https://pith.science/pith/F3SAMOM4YANBY32BQ5OBS6RJPP.json","view_paper":"https://pith.science/paper/F3SAMOM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.07715&json=true","fetch_graph":"https://pith.science/api/pith-number/F3SAMOM4YANBY32BQ5OBS6RJPP/graph.json","fetch_events":"https://pith.science/api/pith-number/F3SAMOM4YANBY32BQ5OBS6RJPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3SAMOM4YANBY32BQ5OBS6RJPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3SAMOM4YANBY32BQ5OBS6RJPP/action/storage_attestation","attest_author":"https://pith.science/pith/F3SAMOM4YANBY32BQ5OBS6RJPP/action/author_attestation","sign_citation":"https://pith.science/pith/F3SAMOM4YANBY32BQ5OBS6RJPP/action/citation_signature","submit_replication":"https://pith.science/pith/F3SAMOM4YANBY32BQ5OBS6RJPP/action/replication_record"}},"created_at":"2026-05-20T00:03:05.181428+00:00","updated_at":"2026-05-20T00:03:05.181428+00:00"}