{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CMWQA5HIPG2XZZ6SPNLMRFEMZ4","short_pith_number":"pith:CMWQA5HI","schema_version":"1.0","canonical_sha256":"132d0074e879b57ce7d27b56c8948ccf2dc13f153f1d0cd83ffc4eb2d11754ae","source":{"kind":"arxiv","id":"2508.01975","version":1},"attestation_state":"computed","paper":{"title":"Diffusion models for inverse problems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyungjin Chung, Jeongsol Kim, Jong Chul Ye","submitted_at":"2025-08-04T01:26:06Z","abstract_excerpt":"Using diffusion priors to solve inverse problems in imaging have significantly matured over the years. In this chapter, we review the various different approaches that were proposed over the years. We categorize the approaches into the more classic explicit approximation approaches and others, which include variational inference, sequential monte carlo, and decoupled data consistency. We cover the extension to more challenging situations, including blind cases, high-dimensional data, and problems under data scarcity and distribution mismatch. More recent approaches that aim to leverage multimo"},"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":"2508.01975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T01:26:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"64e9bfa1319b8d226eefa1bdbb7281021f5cc2c6c563f158e485f251b7291a8b","abstract_canon_sha256":"75de732a62c84441fdee42ad64342dcc5661a6034e55630cfd635b0f3cc3f468"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:48.892506Z","signature_b64":"hZi94Qq9NyU/UDT95oEwvca3nH/srrZCO7sXgbiQb4syY1uLRBPXvCiyjFvXhkeJozTjnCbJJ7hzK/79h8FZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"132d0074e879b57ce7d27b56c8948ccf2dc13f153f1d0cd83ffc4eb2d11754ae","last_reissued_at":"2026-07-05T11:47:48.892051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:48.892051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion models for inverse problems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyungjin Chung, Jeongsol Kim, Jong Chul Ye","submitted_at":"2025-08-04T01:26:06Z","abstract_excerpt":"Using diffusion priors to solve inverse problems in imaging have significantly matured over the years. In this chapter, we review the various different approaches that were proposed over the years. We categorize the approaches into the more classic explicit approximation approaches and others, which include variational inference, sequential monte carlo, and decoupled data consistency. We cover the extension to more challenging situations, including blind cases, high-dimensional data, and problems under data scarcity and distribution mismatch. More recent approaches that aim to leverage multimo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01975","kind":"arxiv","version":1},"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/2508.01975/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":"2508.01975","created_at":"2026-07-05T11:47:48.892107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01975v1","created_at":"2026-07-05T11:47:48.892107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01975","created_at":"2026-07-05T11:47:48.892107+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMWQA5HIPG2X","created_at":"2026-07-05T11:47:48.892107+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMWQA5HIPG2XZZ6S","created_at":"2026-07-05T11:47:48.892107+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMWQA5HI","created_at":"2026-07-05T11:47:48.892107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19802","citing_title":"Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25299","citing_title":"A Principled Self-Referenced Early Stopping Approach for Deep Image Prior","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05791","citing_title":"Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18365","citing_title":"Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06172","citing_title":"Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21180","citing_title":"Uncertainty-Aware Spatiotemporal Super-Resolution Data Assimilation with Diffusion Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4","json":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4.json","graph_json":"https://pith.science/api/pith-number/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/graph.json","events_json":"https://pith.science/api/pith-number/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/events.json","paper":"https://pith.science/paper/CMWQA5HI"},"agent_actions":{"view_html":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4","download_json":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4.json","view_paper":"https://pith.science/paper/CMWQA5HI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01975&json=true","fetch_graph":"https://pith.science/api/pith-number/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/action/storage_attestation","attest_author":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/action/author_attestation","sign_citation":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/action/citation_signature","submit_replication":"https://pith.science/pith/CMWQA5HIPG2XZZ6SPNLMRFEMZ4/action/replication_record"}},"created_at":"2026-07-05T11:47:48.892107+00:00","updated_at":"2026-07-05T11:47:48.892107+00:00"}