{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UXFNKFK4N44ZQPMNXUGHPNPP37","short_pith_number":"pith:UXFNKFK4","canonical_record":{"source":{"id":"2605.12573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T11:38:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d9d8ed23f21443386c3f47f4271789b193c2395a2f6f0a2411141813e77b0257","abstract_canon_sha256":"7f7536f882e554141971f9caad724d1918a83bf12ed1a16e32d9b1f80b2a9acc"},"schema_version":"1.0"},"canonical_sha256":"a5cad5155c6f39983d8dbd0c77b5efdfde254571adc2b154c775b384d6738f89","source":{"kind":"arxiv","id":"2605.12573","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12573","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12573v1","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12573","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"UXFNKFK4N44Z","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UXFNKFK4N44ZQPMN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UXFNKFK4","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UXFNKFK4N44ZQPMNXUGHPNPP37","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T11:38:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d9d8ed23f21443386c3f47f4271789b193c2395a2f6f0a2411141813e77b0257","abstract_canon_sha256":"7f7536f882e554141971f9caad724d1918a83bf12ed1a16e32d9b1f80b2a9acc"},"schema_version":"1.0"},"canonical_sha256":"a5cad5155c6f39983d8dbd0c77b5efdfde254571adc2b154c775b384d6738f89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:01.687913Z","signature_b64":"YsdFagbowYjD+c3STC8oBjmpHx2AblWN17ADrkZ8P96m9DSYlD4RL5exhvmJff2L6+BuqihUKQvQQ2nZDuRoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5cad5155c6f39983d8dbd0c77b5efdfde254571adc2b154c775b384d6738f89","last_reissued_at":"2026-05-18T03:10:01.686835Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:01.686835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12573","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nKLK0St5VPaeYlYdZ3dvZYf20OAym4cO2Zmm5eaNGzBIjJHZPTpSLrMD2xFBcreKhmMy51WBO/2mjA3RlaKyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T07:59:49.396824Z"},"content_sha256":"3c002e8e28077d5b5d9f35de498d8c7ba253a496a4abc0094c11e3748ec3c211","schema_version":"1.0","event_id":"sha256:3c002e8e28077d5b5d9f35de498d8c7ba253a496a4abc0094c11e3748ec3c211"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UXFNKFK4N44ZQPMNXUGHPNPP37","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LAMP improves diffusion posterior sampling by adding a lagged temporal correction from second-order discretization while preserving the posterior structure.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Davide Evangelista, Elena Morotti, Francesco Pivi, Maurizio Gabbrielli","submitted_at":"2026-05-12T11:38:36Z","abstract_excerpt":"Diffusion-based posterior sampling (PS) is a leading framework for imaging inverse problems, combining learned priors with measurement constraints. Yet, its standard formulations rely on instantaneous data-consistent estimates, which induce temporal variability in the reverse dynamics. We reinterpret PS from a dynamical perspective, showing that the standard PS update corresponds to a first-order discretization of the diffusion dynamics plus a residual correction capturing the mismatch between the denoised prediction and the data-consistent estimate. A second-order discretization, however, nat"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LAMP preserves the structure of a posterior sampler and improves the reverse transition via a bias-variance trade-off, as shown by one-step risk analysis and consistent gains over DiffPIR and DDRM without increasing denoising evaluations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the second-order discretization term remains stable and beneficial across the full reverse trajectory when combined with the residual correction, rather than only in the one-step analysis.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LAMP adds a lagged temporal correction derived from second-order discretization to diffusion posterior samplers, yielding consistent gains over DiffPIR and DDRM on imaging tasks via a bias-variance trade-off.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LAMP improves diffusion posterior sampling by adding a lagged temporal correction from second-order discretization while preserving the posterior structure.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6b7c48f310e5d1038cfe08d862bebf127cd78b2253dfc8c58c65148a37fcf0dd"},"source":{"id":"2605.12573","kind":"arxiv","version":1},"verdict":{"id":"58d4ff02-a5b9-42e7-90f1-1d34546636dc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:43:19.910008Z","strongest_claim":"LAMP preserves the structure of a posterior sampler and improves the reverse transition via a bias-variance trade-off, as shown by one-step risk analysis and consistent gains over DiffPIR and DDRM without increasing denoising evaluations.","one_line_summary":"LAMP adds a lagged temporal correction derived from second-order discretization to diffusion posterior samplers, yielding consistent gains over DiffPIR and DDRM on imaging tasks via a bias-variance trade-off.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the second-order discretization term remains stable and beneficial across the full reverse trajectory when combined with the residual correction, rather than only in the one-step analysis.","pith_extraction_headline":"LAMP improves diffusion posterior sampling by adding a lagged temporal correction from second-order discretization while preserving the posterior structure."},"references":{"count":17,"sample":[{"doi":"","year":2023,"title":"Hyungjin Chung, Jeongsol Kim, Michael T. McCann, Marc L. Klasky, and Jong Chul Ye. Diffusion posterior sampling for general noisy inverse problems. InInternational Conference on Learning Representatio","work_id":"4e07eff4-123a-4a0d-83bf-2b0bc67ae774","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Improving diffusion models for inverse problems using manifold constraints.Advances in Neural Information Processing Systems, 35:25683–25696, 2022","work_id":"f867adf9-9c8b-4e3e-af5e-9ea543846030","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Diffusion models beat gans on image synthesis","work_id":"11a4fa70-50e4-4103-b58a-48259ce280d9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Denoising diffusion probabilistic models","work_id":"007f689e-17d2-4add-8618-5321c85e056b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Denoising diffusion restoration models","work_id":"30098793-59a0-459f-8bf7-e8529608aca4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":17,"snapshot_sha256":"999bd6045af544ab4b449bd0738a175538d0bb72a21df240f823301effc5e9a7","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"bba6777d8612f7f1826c2113d97da25304779aa2bff6fdfc22ffade269a76bec"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"58d4ff02-a5b9-42e7-90f1-1d34546636dc"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9s8LEDa9bkUU2HO4vi/e6g6x7DgndNp9BDIT8xhConmEUxRA0Bp5m7EjBWrIcigLGgQDv2LRpLIee7NIoRGsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T07:59:49.398095Z"},"content_sha256":"830bb36ed86dc8cc40a6cc0cb9e222455bdffa3ddf0d967cf24c19f2d187eba1","schema_version":"1.0","event_id":"sha256:830bb36ed86dc8cc40a6cc0cb9e222455bdffa3ddf0d967cf24c19f2d187eba1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UXFNKFK4N44ZQPMNXUGHPNPP37/bundle.json","state_url":"https://pith.science/pith/UXFNKFK4N44ZQPMNXUGHPNPP37/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UXFNKFK4N44ZQPMNXUGHPNPP37/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T07:59:49Z","links":{"resolver":"https://pith.science/pith/UXFNKFK4N44ZQPMNXUGHPNPP37","bundle":"https://pith.science/pith/UXFNKFK4N44ZQPMNXUGHPNPP37/bundle.json","state":"https://pith.science/pith/UXFNKFK4N44ZQPMNXUGHPNPP37/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UXFNKFK4N44ZQPMNXUGHPNPP37/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UXFNKFK4N44ZQPMNXUGHPNPP37","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7f7536f882e554141971f9caad724d1918a83bf12ed1a16e32d9b1f80b2a9acc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T11:38:36Z","title_canon_sha256":"d9d8ed23f21443386c3f47f4271789b193c2395a2f6f0a2411141813e77b0257"},"schema_version":"1.0","source":{"id":"2605.12573","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12573","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12573v1","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12573","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"UXFNKFK4N44Z","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UXFNKFK4N44ZQPMN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UXFNKFK4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:830bb36ed86dc8cc40a6cc0cb9e222455bdffa3ddf0d967cf24c19f2d187eba1","target":"graph","created_at":"2026-05-18T03:10:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"LAMP preserves the structure of a posterior sampler and improves the reverse transition via a bias-variance trade-off, as shown by one-step risk analysis and consistent gains over DiffPIR and DDRM without increasing denoising evaluations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the second-order discretization term remains stable and beneficial across the full reverse trajectory when combined with the residual correction, rather than only in the one-step analysis."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LAMP adds a lagged temporal correction derived from second-order discretization to diffusion posterior samplers, yielding consistent gains over DiffPIR and DDRM on imaging tasks via a bias-variance trade-off."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LAMP improves diffusion posterior sampling by adding a lagged temporal correction from second-order discretization while preserving the posterior structure."}],"snapshot_sha256":"6b7c48f310e5d1038cfe08d862bebf127cd78b2253dfc8c58c65148a37fcf0dd"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"bba6777d8612f7f1826c2113d97da25304779aa2bff6fdfc22ffade269a76bec"},"paper":{"abstract_excerpt":"Diffusion-based posterior sampling (PS) is a leading framework for imaging inverse problems, combining learned priors with measurement constraints. Yet, its standard formulations rely on instantaneous data-consistent estimates, which induce temporal variability in the reverse dynamics. We reinterpret PS from a dynamical perspective, showing that the standard PS update corresponds to a first-order discretization of the diffusion dynamics plus a residual correction capturing the mismatch between the denoised prediction and the data-consistent estimate. A second-order discretization, however, nat","authors_text":"Davide Evangelista, Elena Morotti, Francesco Pivi, Maurizio Gabbrielli","cross_cats":["cs.AI","cs.LG"],"headline":"LAMP improves diffusion posterior sampling by adding a lagged temporal correction from second-order discretization while preserving the posterior structure.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T11:38:36Z","title":"Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration"},"references":{"count":17,"internal_anchors":0,"resolved_work":17,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Hyungjin Chung, Jeongsol Kim, Michael T. McCann, Marc L. Klasky, and Jong Chul Ye. Diffusion posterior sampling for general noisy inverse problems. InInternational Conference on Learning Representatio","work_id":"4e07eff4-123a-4a0d-83bf-2b0bc67ae774","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Improving diffusion models for inverse problems using manifold constraints.Advances in Neural Information Processing Systems, 35:25683–25696, 2022","work_id":"f867adf9-9c8b-4e3e-af5e-9ea543846030","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Diffusion models beat gans on image synthesis","work_id":"11a4fa70-50e4-4103-b58a-48259ce280d9","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Denoising diffusion probabilistic models","work_id":"007f689e-17d2-4add-8618-5321c85e056b","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Denoising diffusion restoration models","work_id":"30098793-59a0-459f-8bf7-e8529608aca4","year":2022}],"snapshot_sha256":"999bd6045af544ab4b449bd0738a175538d0bb72a21df240f823301effc5e9a7"},"source":{"id":"2605.12573","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:43:19.910008Z","id":"58d4ff02-a5b9-42e7-90f1-1d34546636dc","model_set":{"reader":"grok-4.3"},"one_line_summary":"LAMP adds a lagged temporal correction derived from second-order discretization to diffusion posterior samplers, yielding consistent gains over DiffPIR and DDRM on imaging tasks via a bias-variance trade-off.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LAMP improves diffusion posterior sampling by adding a lagged temporal correction from second-order discretization while preserving the posterior structure.","strongest_claim":"LAMP preserves the structure of a posterior sampler and improves the reverse transition via a bias-variance trade-off, as shown by one-step risk analysis and consistent gains over DiffPIR and DDRM without increasing denoising evaluations.","weakest_assumption":"That the second-order discretization term remains stable and beneficial across the full reverse trajectory when combined with the residual correction, rather than only in the one-step analysis."}},"verdict_id":"58d4ff02-a5b9-42e7-90f1-1d34546636dc"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c002e8e28077d5b5d9f35de498d8c7ba253a496a4abc0094c11e3748ec3c211","target":"record","created_at":"2026-05-18T03:10:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7f7536f882e554141971f9caad724d1918a83bf12ed1a16e32d9b1f80b2a9acc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T11:38:36Z","title_canon_sha256":"d9d8ed23f21443386c3f47f4271789b193c2395a2f6f0a2411141813e77b0257"},"schema_version":"1.0","source":{"id":"2605.12573","kind":"arxiv","version":1}},"canonical_sha256":"a5cad5155c6f39983d8dbd0c77b5efdfde254571adc2b154c775b384d6738f89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5cad5155c6f39983d8dbd0c77b5efdfde254571adc2b154c775b384d6738f89","first_computed_at":"2026-05-18T03:10:01.686835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:01.686835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YsdFagbowYjD+c3STC8oBjmpHx2AblWN17ADrkZ8P96m9DSYlD4RL5exhvmJff2L6+BuqihUKQvQQ2nZDuRoAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:01.687913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12573","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c002e8e28077d5b5d9f35de498d8c7ba253a496a4abc0094c11e3748ec3c211","sha256:830bb36ed86dc8cc40a6cc0cb9e222455bdffa3ddf0d967cf24c19f2d187eba1"],"state_sha256":"224db08aacfd1c3b0d94039c7547bbd0488f3e661879416d6f7a077ffadb4208"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gUEqz6oxTmAhxobyqQgaOG2F5KCJ/lNahfaU393NYQsFrYnLszi3YLJXamEBzZ+5Ne4+i6HbvScrTckIN8gpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T07:59:49.403648Z","bundle_sha256":"943ed0696afedd7fc88a614050861c0fa5ccffb938977a69038388ddcc6d51a7"}}