{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FUN46D7BETNOP7IF6G4QIQE4HG","short_pith_number":"pith:FUN46D7B","schema_version":"1.0","canonical_sha256":"2d1bcf0fe124dae7fd05f1b904409c399b7683b87944256500393d88ecf9adff","source":{"kind":"arxiv","id":"2302.05290","version":4},"attestation_state":"computed","paper":{"title":"Removing Structured Noise with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Faik C. Meral, Hans van Gorp, Jason Yu, Jean-Luc Robert, Junseob Shin, Ruud J.G. van Sloun, Tristan S.W. Stevens","submitted_at":"2023-01-20T23:42:25Z","abstract_excerpt":"Solving ill-posed inverse problems requires careful formulation of prior beliefs over the signals of interest and an accurate description of their manifestation into noisy measurements. Handcrafted signal priors based on e.g. sparsity are increasingly replaced by data-driven deep generative models, and several groups have recently shown that state-of-the-art score-based diffusion models yield particularly strong performance and flexibility. In this paper, we show that the powerful paradigm of posterior sampling with diffusion models can be extended to include rich, structured, noise models. To"},"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":"2302.05290","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-20T23:42:25Z","cross_cats_sorted":["eess.IV","eess.SP"],"title_canon_sha256":"9a8a4cfae1ec5dfd71b8d40e67ad1009e0d02bc329bc2373a8d9d39875758b3b","abstract_canon_sha256":"049c885f9fae316b4cd2a15abeda6a3c781cae585bd608f37f98115eefc8ce70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:51.027442Z","signature_b64":"LSgHUeW2DNC4rVrUyj0bLb6q8zCn5guxeWx3kN3Mgtr6dD3fQoxogd49RRYjaQG93PDRb/yonunpD2X5NI7NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d1bcf0fe124dae7fd05f1b904409c399b7683b87944256500393d88ecf9adff","last_reissued_at":"2026-07-05T11:52:51.026972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:51.026972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Removing Structured Noise with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Faik C. Meral, Hans van Gorp, Jason Yu, Jean-Luc Robert, Junseob Shin, Ruud J.G. van Sloun, Tristan S.W. Stevens","submitted_at":"2023-01-20T23:42:25Z","abstract_excerpt":"Solving ill-posed inverse problems requires careful formulation of prior beliefs over the signals of interest and an accurate description of their manifestation into noisy measurements. Handcrafted signal priors based on e.g. sparsity are increasingly replaced by data-driven deep generative models, and several groups have recently shown that state-of-the-art score-based diffusion models yield particularly strong performance and flexibility. In this paper, we show that the powerful paradigm of posterior sampling with diffusion models can be extended to include rich, structured, noise models. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05290","kind":"arxiv","version":4},"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/2302.05290/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":"2302.05290","created_at":"2026-07-05T11:52:51.027038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05290v4","created_at":"2026-07-05T11:52:51.027038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05290","created_at":"2026-07-05T11:52:51.027038+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUN46D7BETNO","created_at":"2026-07-05T11:52:51.027038+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUN46D7BETNOP7IF","created_at":"2026-07-05T11:52:51.027038+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUN46D7B","created_at":"2026-07-05T11:52:51.027038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.18365","citing_title":"Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG","json":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG.json","graph_json":"https://pith.science/api/pith-number/FUN46D7BETNOP7IF6G4QIQE4HG/graph.json","events_json":"https://pith.science/api/pith-number/FUN46D7BETNOP7IF6G4QIQE4HG/events.json","paper":"https://pith.science/paper/FUN46D7B"},"agent_actions":{"view_html":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG","download_json":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG.json","view_paper":"https://pith.science/paper/FUN46D7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05290&json=true","fetch_graph":"https://pith.science/api/pith-number/FUN46D7BETNOP7IF6G4QIQE4HG/graph.json","fetch_events":"https://pith.science/api/pith-number/FUN46D7BETNOP7IF6G4QIQE4HG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG/action/storage_attestation","attest_author":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG/action/author_attestation","sign_citation":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG/action/citation_signature","submit_replication":"https://pith.science/pith/FUN46D7BETNOP7IF6G4QIQE4HG/action/replication_record"}},"created_at":"2026-07-05T11:52:51.027038+00:00","updated_at":"2026-07-05T11:52:51.027038+00:00"}