{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KEWAV4Z6FUSAMP3IIKOXBFXTL4","short_pith_number":"pith:KEWAV4Z6","schema_version":"1.0","canonical_sha256":"512c0af33e2d24063f68429d7096f35f058fe976c8b5183f5366ba55e2dc91fa","source":{"kind":"arxiv","id":"2301.12686","version":2},"attestation_state":"computed","paper":{"title":"GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Koichi Saito, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2023-01-30T06:27:48Z","abstract_excerpt":"Pre-trained diffusion models have been successfully used as priors in a variety of linear inverse problems, where the goal is to reconstruct a signal from noisy linear measurements. However, existing approaches require knowledge of the linear operator. In this paper, we propose GibbsDDRM, an extension of Denoising Diffusion Restoration Models (DDRM) to a blind setting in which the linear measurement operator is unknown. GibbsDDRM constructs a joint distribution of the data, measurements, and linear operator by using a pre-trained diffusion model for the data prior, and it solves the problem by"},"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":"2301.12686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T06:27:48Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"bac10e735ba1d7fcc1d19bd03bf97ade6a96cc08d9d1772554e8ab02e95880ed","abstract_canon_sha256":"a15e71b92a43c1e90e9393756882215ca0f8888b9867fef447d3893332fe9289"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:48.313213Z","signature_b64":"062vhBB9TV901HWGeRsdzYNWrVsJf2/7O8bo12UH1g2L2veUu7SP0xTJ92Nr55hazAr1D6xdCwGGwFszWn0KDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"512c0af33e2d24063f68429d7096f35f058fe976c8b5183f5366ba55e2dc91fa","last_reissued_at":"2026-07-05T06:24:48.312709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:48.312709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Koichi Saito, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2023-01-30T06:27:48Z","abstract_excerpt":"Pre-trained diffusion models have been successfully used as priors in a variety of linear inverse problems, where the goal is to reconstruct a signal from noisy linear measurements. However, existing approaches require knowledge of the linear operator. In this paper, we propose GibbsDDRM, an extension of Denoising Diffusion Restoration Models (DDRM) to a blind setting in which the linear measurement operator is unknown. GibbsDDRM constructs a joint distribution of the data, measurements, and linear operator by using a pre-trained diffusion model for the data prior, and it solves the problem by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12686","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/2301.12686/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":"2301.12686","created_at":"2026-07-05T06:24:48.312765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12686v2","created_at":"2026-07-05T06:24:48.312765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12686","created_at":"2026-07-05T06:24:48.312765+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEWAV4Z6FUSA","created_at":"2026-07-05T06:24:48.312765+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEWAV4Z6FUSAMP3I","created_at":"2026-07-05T06:24:48.312765+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEWAV4Z6","created_at":"2026-07-05T06:24:48.312765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4","json":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4.json","graph_json":"https://pith.science/api/pith-number/KEWAV4Z6FUSAMP3IIKOXBFXTL4/graph.json","events_json":"https://pith.science/api/pith-number/KEWAV4Z6FUSAMP3IIKOXBFXTL4/events.json","paper":"https://pith.science/paper/KEWAV4Z6"},"agent_actions":{"view_html":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4","download_json":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4.json","view_paper":"https://pith.science/paper/KEWAV4Z6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12686&json=true","fetch_graph":"https://pith.science/api/pith-number/KEWAV4Z6FUSAMP3IIKOXBFXTL4/graph.json","fetch_events":"https://pith.science/api/pith-number/KEWAV4Z6FUSAMP3IIKOXBFXTL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4/action/storage_attestation","attest_author":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4/action/author_attestation","sign_citation":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4/action/citation_signature","submit_replication":"https://pith.science/pith/KEWAV4Z6FUSAMP3IIKOXBFXTL4/action/replication_record"}},"created_at":"2026-07-05T06:24:48.312765+00:00","updated_at":"2026-07-05T06:24:48.312765+00:00"}