{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7K2CQJMEI5UCURSG6MYVK35PW4","short_pith_number":"pith:7K2CQJME","schema_version":"1.0","canonical_sha256":"fab428258447682a4646f331556fafb70dcdc0f898a6cf575d35df8b2adb3f8e","source":{"kind":"arxiv","id":"2405.16749","version":2},"attestation_state":"computed","paper":{"title":"DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hengkang Wang, Ju Sun, Taihui Li, Tiancong Chen, Xu Zhang, Yuxiang Wan","submitted_at":"2024-05-27T01:38:30Z","abstract_excerpt":"Pretrained diffusion models (DMs) have recently been popularly used in solving inverse problems (IPs). The existing methods mostly interleave iterative steps in the reverse diffusion process and iterative steps to bring the iterates closer to satisfying the measurement constraint. However, such interleaving methods struggle to produce final results that look like natural objects of interest (i.e., manifold feasibility) and fit the measurement (i.e., measurement feasibility), especially for nonlinear IPs. Moreover, their capabilities to deal with noisy IPs with unknown types and levels of measu"},"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":"2405.16749","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T01:38:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c5613a970552698d6206af9e57b50889f728a24112587a6c6bb935a9de3877f4","abstract_canon_sha256":"5d702e498e093657594d1ba6e73ab0b2ecc4fb6a029653b072da09f2cb9191dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:46.359184Z","signature_b64":"/E1W2DGZQWRllsT242mUjV1AzEvDnjXYglLWSUNGvNbvHh/HihiNQxN/RX1xRRGKhZxnmapTgHthPn7UqEugBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fab428258447682a4646f331556fafb70dcdc0f898a6cf575d35df8b2adb3f8e","last_reissued_at":"2026-07-05T09:31:46.358705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:46.358705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hengkang Wang, Ju Sun, Taihui Li, Tiancong Chen, Xu Zhang, Yuxiang Wan","submitted_at":"2024-05-27T01:38:30Z","abstract_excerpt":"Pretrained diffusion models (DMs) have recently been popularly used in solving inverse problems (IPs). The existing methods mostly interleave iterative steps in the reverse diffusion process and iterative steps to bring the iterates closer to satisfying the measurement constraint. However, such interleaving methods struggle to produce final results that look like natural objects of interest (i.e., manifold feasibility) and fit the measurement (i.e., measurement feasibility), especially for nonlinear IPs. Moreover, their capabilities to deal with noisy IPs with unknown types and levels of measu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16749","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/2405.16749/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":"2405.16749","created_at":"2026-07-05T09:31:46.358758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16749v2","created_at":"2026-07-05T09:31:46.358758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16749","created_at":"2026-07-05T09:31:46.358758+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K2CQJMEI5UC","created_at":"2026-07-05T09:31:46.358758+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K2CQJMEI5UCURSG","created_at":"2026-07-05T09:31:46.358758+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K2CQJME","created_at":"2026-07-05T09:31:46.358758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.16520","citing_title":"Saving Foundation Flow-Matching Priors for Inverse Problems","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2410.00083","citing_title":"A Survey on Diffusion Models for Inverse Problems","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4","json":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4.json","graph_json":"https://pith.science/api/pith-number/7K2CQJMEI5UCURSG6MYVK35PW4/graph.json","events_json":"https://pith.science/api/pith-number/7K2CQJMEI5UCURSG6MYVK35PW4/events.json","paper":"https://pith.science/paper/7K2CQJME"},"agent_actions":{"view_html":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4","download_json":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4.json","view_paper":"https://pith.science/paper/7K2CQJME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16749&json=true","fetch_graph":"https://pith.science/api/pith-number/7K2CQJMEI5UCURSG6MYVK35PW4/graph.json","fetch_events":"https://pith.science/api/pith-number/7K2CQJMEI5UCURSG6MYVK35PW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4/action/storage_attestation","attest_author":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4/action/author_attestation","sign_citation":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4/action/citation_signature","submit_replication":"https://pith.science/pith/7K2CQJMEI5UCURSG6MYVK35PW4/action/replication_record"}},"created_at":"2026-07-05T09:31:46.358758+00:00","updated_at":"2026-07-05T09:31:46.358758+00:00"}