{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LWKJNLKW7ZSW5DGWX2EQMINRTM","short_pith_number":"pith:LWKJNLKW","schema_version":"1.0","canonical_sha256":"5d9496ad56fe656e8cd6be890621b19b300da4fd273b2c766a2fc665d91f4148","source":{"kind":"arxiv","id":"2209.11888","version":2},"attestation_state":"computed","paper":{"title":"JPEG Artifact Correction using Denoising Diffusion Restoration Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Bahjat Kawar, Jiaming Song, Michael Elad, Stefano Ermon","submitted_at":"2022-09-23T23:47:00Z","abstract_excerpt":"Diffusion models can be used as learned priors for solving various inverse problems. However, most existing approaches are restricted to linear inverse problems, limiting their applicability to more general cases. In this paper, we build upon Denoising Diffusion Restoration Models (DDRM) and propose a method for solving some non-linear inverse problems. We leverage the pseudo-inverse operator used in DDRM and generalize this concept for other measurement operators, which allows us to use pre-trained unconditional diffusion models for applications such as JPEG artifact correction. We empiricall"},"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":"2209.11888","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2022-09-23T23:47:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f8234e0ae1f6cdba6de132fbef1630c3a95e151c40e9e83ddad031e39ea2a2c1","abstract_canon_sha256":"a8772e38ca19649fde72396ddd5adb717b0697d08fd36ef75deb3166045352c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:01.137841Z","signature_b64":"GAFS3x46JzV7T2QYC4nkUoz5brenyyEY/XGFfTvc5AjCxtvvgfMxnGs5BRQwjEgmoza/j60fzsIvixTRBz11BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d9496ad56fe656e8cd6be890621b19b300da4fd273b2c766a2fc665d91f4148","last_reissued_at":"2026-07-05T05:19:01.137405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:01.137405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JPEG Artifact Correction using Denoising Diffusion Restoration Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Bahjat Kawar, Jiaming Song, Michael Elad, Stefano Ermon","submitted_at":"2022-09-23T23:47:00Z","abstract_excerpt":"Diffusion models can be used as learned priors for solving various inverse problems. However, most existing approaches are restricted to linear inverse problems, limiting their applicability to more general cases. In this paper, we build upon Denoising Diffusion Restoration Models (DDRM) and propose a method for solving some non-linear inverse problems. We leverage the pseudo-inverse operator used in DDRM and generalize this concept for other measurement operators, which allows us to use pre-trained unconditional diffusion models for applications such as JPEG artifact correction. We empiricall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11888","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/2209.11888/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":"2209.11888","created_at":"2026-07-05T05:19:01.137463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11888v2","created_at":"2026-07-05T05:19:01.137463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11888","created_at":"2026-07-05T05:19:01.137463+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWKJNLKW7ZSW","created_at":"2026-07-05T05:19:01.137463+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWKJNLKW7ZSW5DGW","created_at":"2026-07-05T05:19:01.137463+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWKJNLKW","created_at":"2026-07-05T05:19:01.137463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19992","citing_title":"An Ordinary Differential Equation Sampler with Stochastic Start for Diffusion Bridge Models","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM","json":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM.json","graph_json":"https://pith.science/api/pith-number/LWKJNLKW7ZSW5DGWX2EQMINRTM/graph.json","events_json":"https://pith.science/api/pith-number/LWKJNLKW7ZSW5DGWX2EQMINRTM/events.json","paper":"https://pith.science/paper/LWKJNLKW"},"agent_actions":{"view_html":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM","download_json":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM.json","view_paper":"https://pith.science/paper/LWKJNLKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11888&json=true","fetch_graph":"https://pith.science/api/pith-number/LWKJNLKW7ZSW5DGWX2EQMINRTM/graph.json","fetch_events":"https://pith.science/api/pith-number/LWKJNLKW7ZSW5DGWX2EQMINRTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM/action/storage_attestation","attest_author":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM/action/author_attestation","sign_citation":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM/action/citation_signature","submit_replication":"https://pith.science/pith/LWKJNLKW7ZSW5DGWX2EQMINRTM/action/replication_record"}},"created_at":"2026-07-05T05:19:01.137463+00:00","updated_at":"2026-07-05T05:19:01.137463+00:00"}