{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7QHSTXYHCDYRHTZ44MJXWXPYA7","short_pith_number":"pith:7QHSTXYH","schema_version":"1.0","canonical_sha256":"fc0f29df0710f113cf3ce3137b5df807e2136ddae3939bc4d2d034f4de627256","source":{"kind":"arxiv","id":"2506.03979","version":2},"attestation_state":"computed","paper":{"title":"Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NA","eess.IV","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoxuan Chen, Lexing Ying, Martin Renqiang Min, Yinuo Ren, Zachary Izzo","submitted_at":"2025-06-04T14:09:25Z","abstract_excerpt":"Diffusion models (DMs) have proven to be effective in modeling high-dimensional distributions, leading to their widespread adoption for representing complex priors in Bayesian inverse problems (BIPs). However, current DM-based posterior sampling methods proposed for solving common BIPs rely on heuristic approximations to the generative process. To exploit the generative capability of DMs and avoid the usage of such approximations, we propose an ensemble-based algorithm that performs posterior sampling without the use of heuristic approximations. Our algorithm is motivated by existing works tha"},"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":"2506.03979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T14:09:25Z","cross_cats_sorted":["cs.CV","cs.NA","eess.IV","math.NA","stat.ML"],"title_canon_sha256":"22a8ddd95f97935057a48e7b6f38c726da19a41e00d0630dc44897c190b21f63","abstract_canon_sha256":"cb9d29151fb4b1c516901ee4d49c8d7ae85f27f6e6fb849d1b425a382c50dcc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:10.215701Z","signature_b64":"XykYpayzchRt7fRJvIrs9tgass0HbNkH0vLGG4QmdVHKqe7DnvNlGIkfh7stCzZv0VmR1lM7j1AJDTwfc2tlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc0f29df0710f113cf3ce3137b5df807e2136ddae3939bc4d2d034f4de627256","last_reissued_at":"2026-07-05T11:16:10.215030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:10.215030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NA","eess.IV","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoxuan Chen, Lexing Ying, Martin Renqiang Min, Yinuo Ren, Zachary Izzo","submitted_at":"2025-06-04T14:09:25Z","abstract_excerpt":"Diffusion models (DMs) have proven to be effective in modeling high-dimensional distributions, leading to their widespread adoption for representing complex priors in Bayesian inverse problems (BIPs). However, current DM-based posterior sampling methods proposed for solving common BIPs rely on heuristic approximations to the generative process. To exploit the generative capability of DMs and avoid the usage of such approximations, we propose an ensemble-based algorithm that performs posterior sampling without the use of heuristic approximations. Our algorithm is motivated by existing works tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03979","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/2506.03979/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":"2506.03979","created_at":"2026-07-05T11:16:10.215114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03979v2","created_at":"2026-07-05T11:16:10.215114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03979","created_at":"2026-07-05T11:16:10.215114+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QHSTXYHCDYR","created_at":"2026-07-05T11:16:10.215114+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QHSTXYHCDYRHTZ4","created_at":"2026-07-05T11:16:10.215114+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QHSTXYH","created_at":"2026-07-05T11:16:10.215114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18745","citing_title":"SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2405.15643","citing_title":"An Unconditional Representation of the Conditional Score in Infinite-Dimensional Linear Inverse Problems","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18745","citing_title":"SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17850","citing_title":"Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16966","citing_title":"Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02924","citing_title":"How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07907","citing_title":"Consistency Regularised Gradient Flows for Inverse Problems","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7","json":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7.json","graph_json":"https://pith.science/api/pith-number/7QHSTXYHCDYRHTZ44MJXWXPYA7/graph.json","events_json":"https://pith.science/api/pith-number/7QHSTXYHCDYRHTZ44MJXWXPYA7/events.json","paper":"https://pith.science/paper/7QHSTXYH"},"agent_actions":{"view_html":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7","download_json":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7.json","view_paper":"https://pith.science/paper/7QHSTXYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03979&json=true","fetch_graph":"https://pith.science/api/pith-number/7QHSTXYHCDYRHTZ44MJXWXPYA7/graph.json","fetch_events":"https://pith.science/api/pith-number/7QHSTXYHCDYRHTZ44MJXWXPYA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7/action/storage_attestation","attest_author":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7/action/author_attestation","sign_citation":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7/action/citation_signature","submit_replication":"https://pith.science/pith/7QHSTXYHCDYRHTZ44MJXWXPYA7/action/replication_record"}},"created_at":"2026-07-05T11:16:10.215114+00:00","updated_at":"2026-07-05T11:16:10.215114+00:00"}