{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6JZ5634JBW7B2NLBVWIOJTOTXX","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":"2c46fb6674250f933f27b36c6d7aa15ec50a32365458f577390e6165d3880fc1","cross_cats_sorted":["cs.CV","cs.LG","math.PR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.med-ph","submitted_at":"2025-12-05T15:17:29Z","title_canon_sha256":"e50d015cc3a42f39cef0a46079884772b721690a92be2ff65e218ac3961607a1"},"schema_version":"1.0","source":{"id":"2512.05791","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.05791","created_at":"2026-05-26T01:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2512.05791v2","created_at":"2026-05-26T01:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05791","created_at":"2026-05-26T01:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"6JZ5634JBW7B","created_at":"2026-05-26T01:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"6JZ5634JBW7B2NLB","created_at":"2026-05-26T01:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"6JZ5634J","created_at":"2026-05-26T01:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:e639e32999c586409c56ffce5e2bee1ec9898bba85a8cb884bfe7d0faea14da6","target":"graph","created_at":"2026-05-26T01:03:19Z","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":"For posterior sampling in Cartesian and non-Cartesian accelerated MRI the new approach outperforms annealed sampling and DPS in terms of reconstruction speed and sample quality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the preconditioner derived for the reverse diffusion process remains effective and stable across different acceleration factors, trajectory types, and anatomical regions without retuning or retraining."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Preconditioned ULA with exact likelihood enables faster, higher-quality posterior sampling for Cartesian and non-Cartesian MRI reconstructions than annealed sampling or DPS."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Preconditioning the unadjusted Langevin algorithm enables fast, robust posterior sampling for diffusion-based MRI reconstruction from undersampled data."}],"snapshot_sha256":"5e6b8f76f9513ae22b30abde1e3e282e7f264a63e264cf9ff58d3a75736b6c2b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2512.05791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Purpose: The Unadjusted Langevin Algorithm (ULA) in combination with diffusion models can generate high quality MRI reconstructions with uncertainty estimation from highly undersampled k-space data. However, sampling methods such as diffusion posterior sampling (DPS) or likelihood annealing suffer from long reconstruction times and the need for parameter tuning. The purpose of this work is to develop a robust sampling algorithm with fast convergence.\n  Theory and Methods: In the reverse diffusion process used for sampling the posterior, the exact likelihood is multiplied with the diffused prio","authors_text":"Jonathan I. Tamir, Martin Uecker, Moritz Blumenthal, Tina Holliber","cross_cats":["cs.CV","cs.LG","math.PR"],"headline":"Preconditioning the unadjusted Langevin algorithm enables fast, robust posterior sampling for diffusion-based MRI reconstruction from undersampled data.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.med-ph","submitted_at":"2025-12-05T15:17:29Z","title":"Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm"},"references":{"count":31,"internal_anchors":2,"resolved_work":31,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Robust compressed sensing MRI with deep generative priors","work_id":"03a531e0-23ef-438e-929a-feb472bd6bf0","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Score-based diffusion models for accelerated MRI","work_id":"952b772f-7eef-463a-83c2-7005e55fa062","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Bayesian MRI reconstruc- tion with joint uncertainty estimation using diffusion models.Magnetic Resonance in Medicine2023; 90:295–311","work_id":"fce710d4-7b35-4bd5-914c-47b3374bc916","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Generative Modeling by Estimating Gradients of the Data Distribution","work_id":"4e82caa9-93af-4568-a401-d2ab775ecf46","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Denoising diffusion probabilistic models","work_id":"32f7aa71-014a-458b-84c9-9e8efeac5e38","year":2020}],"snapshot_sha256":"ab1b7b3de6e0496e48240fa24a03d8616d1ea1973a4bcd6dc0d6f9f2f8bd7dd5"},"source":{"id":"2512.05791","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T00:58:48.103306Z","id":"cb706efc-2b65-4d0a-a363-8f39547f06ce","model_set":{"reader":"grok-4.3"},"one_line_summary":"Preconditioned ULA with exact likelihood enables faster, higher-quality posterior sampling for Cartesian and non-Cartesian MRI reconstructions than annealed sampling or DPS.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Preconditioning the unadjusted Langevin algorithm enables fast, robust posterior sampling for diffusion-based MRI reconstruction from undersampled data.","strongest_claim":"For posterior sampling in Cartesian and non-Cartesian accelerated MRI the new approach outperforms annealed sampling and DPS in terms of reconstruction speed and sample quality.","weakest_assumption":"That the preconditioner derived for the reverse diffusion process remains effective and stable across different acceleration factors, trajectory types, and anatomical regions without retuning or retraining."}},"verdict_id":"cb706efc-2b65-4d0a-a363-8f39547f06ce"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:66a95203f248d408aa3f05350fcc98a10ed72c314364105cb4bba31a30b0614f","target":"record","created_at":"2026-05-26T01:03:19Z","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":"2c46fb6674250f933f27b36c6d7aa15ec50a32365458f577390e6165d3880fc1","cross_cats_sorted":["cs.CV","cs.LG","math.PR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.med-ph","submitted_at":"2025-12-05T15:17:29Z","title_canon_sha256":"e50d015cc3a42f39cef0a46079884772b721690a92be2ff65e218ac3961607a1"},"schema_version":"1.0","source":{"id":"2512.05791","kind":"arxiv","version":2}},"canonical_sha256":"f273df6f890dbe1d3561ad90e4cdd3bdfa5214528d49d2e0d5356a57244b3260","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f273df6f890dbe1d3561ad90e4cdd3bdfa5214528d49d2e0d5356a57244b3260","first_computed_at":"2026-05-26T01:03:19.374405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:19.374405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w2Yupuhn/bqtnN/XqH/AQCITTtKssM04EIfxRK0seEcDw8g/ga0P8ropaouCQrvj3aMbmac6rNZYnPGyCbgPDQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:19.375016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.05791","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66a95203f248d408aa3f05350fcc98a10ed72c314364105cb4bba31a30b0614f","sha256:e639e32999c586409c56ffce5e2bee1ec9898bba85a8cb884bfe7d0faea14da6"],"state_sha256":"3271e78c11e5dd1c36e87a8429593848ede4f393c5e67f0d0798a98247454e09"}