{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z5TXQKIB3FYZ5FCVQDE52B3SPX","short_pith_number":"pith:Z5TXQKIB","schema_version":"1.0","canonical_sha256":"cf67782901d9719e945580c9dd07727dd198c2d8d7fd1e694a70f5d0ae7c933b","source":{"kind":"arxiv","id":"2505.17353","version":2},"attestation_state":"computed","paper":{"title":"Dual Ascent Diffusion for Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Axel Levy, Gordon Wetzstein, Minseo Kim","submitted_at":"2025-05-23T00:12:20Z","abstract_excerpt":"Ill-posed inverse problems are fundamental in many domains, ranging from astrophysics to medical imaging. Emerging diffusion models provide a powerful prior for solving these problems. Existing maximum-a-posteriori (MAP) or posterior sampling approaches, however, rely on different computational approximations, leading to inaccurate or suboptimal samples. To address this issue, we introduce a new approach to solving MAP problems with diffusion model priors using a dual ascent optimization framework. Our framework achieves better image quality as measured by various metrics for image restoration"},"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":"2505.17353","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T00:12:20Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"52325ae0f93ff43f60f11cd6a19ed1fa57e22bf05623be1202703222b1f264b8","abstract_canon_sha256":"0a39b4aeb2f734b430a42343083b72d61565833f43b8ddabd2264ad3f0b8dc26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:17.989505Z","signature_b64":"ZHuo7xzhQwTtbiY57eJ9LDcYJOtIvD5TlUIgTgQVi2H4n6rk4qBY/B+lYfl+qQYQB5MozClrB86CPr3MfpDPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf67782901d9719e945580c9dd07727dd198c2d8d7fd1e694a70f5d0ae7c933b","last_reissued_at":"2026-05-17T23:39:17.988980Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:17.988980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Ascent Diffusion for Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Axel Levy, Gordon Wetzstein, Minseo Kim","submitted_at":"2025-05-23T00:12:20Z","abstract_excerpt":"Ill-posed inverse problems are fundamental in many domains, ranging from astrophysics to medical imaging. Emerging diffusion models provide a powerful prior for solving these problems. Existing maximum-a-posteriori (MAP) or posterior sampling approaches, however, rely on different computational approximations, leading to inaccurate or suboptimal samples. To address this issue, we introduce a new approach to solving MAP problems with diffusion model priors using a dual ascent optimization framework. Our framework achieves better image quality as measured by various metrics for image restoration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17353","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":""},"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":"2505.17353","created_at":"2026-05-17T23:39:17.989064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17353v2","created_at":"2026-05-17T23:39:17.989064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17353","created_at":"2026-05-17T23:39:17.989064+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5TXQKIB3FYZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5TXQKIB3FYZ5FCV","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5TXQKIB","created_at":"2026-05-18T12:33:37.589309+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/Z5TXQKIB3FYZ5FCVQDE52B3SPX","json":"https://pith.science/pith/Z5TXQKIB3FYZ5FCVQDE52B3SPX.json","graph_json":"https://pith.science/api/pith-number/Z5TXQKIB3FYZ5FCVQDE52B3SPX/graph.json","events_json":"https://pith.science/api/pith-number/Z5TXQKIB3FYZ5FCVQDE52B3SPX/events.json","paper":"https://pith.science/paper/Z5TXQKIB"},"agent_actions":{"view_html":"https://pith.science/pith/Z5TXQKIB3FYZ5FCVQDE52B3SPX","download_json":"https://pith.science/pith/Z5TXQKIB3FYZ5FCVQDE52B3SPX.json","view_paper":"https://pith.science/paper/Z5TXQKIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17353&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5TXQKIB3FYZ5FCVQDE52B3SPX/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5TXQKIB3FYZ5FCVQDE52B3SPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5TXQKIB3FYZ5FCVQDE52B3SPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5TXQKIB3FYZ5FCVQDE52B3SPX/action/storage_attestation","attest_author":"https://pith.science/pith/Z5TXQKIB3FYZ5FCVQDE52B3SPX/action/author_attestation","sign_citation":"https://pith.science/pith/Z5TXQKIB3FYZ5FCVQDE52B3SPX/action/citation_signature","submit_replication":"https://pith.science/pith/Z5TXQKIB3FYZ5FCVQDE52B3SPX/action/replication_record"}},"created_at":"2026-05-17T23:39:17.989064+00:00","updated_at":"2026-05-17T23:39:17.989064+00:00"}