{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FNPC4U5ILM5XFSMHHW7TWRNR4B","short_pith_number":"pith:FNPC4U5I","schema_version":"1.0","canonical_sha256":"2b5e2e53a85b3b72c9873dbf3b45b1e04f65ed9b35bf3c23c883af53d8b79444","source":{"kind":"arxiv","id":"2011.08698","version":1},"attestation_state":"computed","paper":{"title":"Denoising Score-Matching for Uncertainty Quantification in Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.SP","physics.med-ph"],"primary_cat":"stat.ML","authors_text":"Benjamin Remy, Francois Lanusse, Jean-Luc Starck, Philippe Ciuciu, Zaccharie Ramzi","submitted_at":"2020-11-16T18:33:06Z","abstract_excerpt":"Deep neural networks have proven extremely efficient at solving a wide rangeof inverse problems, but most often the uncertainty on the solution they provideis hard to quantify. In this work, we propose a generic Bayesian framework forsolving inverse problems, in which we limit the use of deep neural networks tolearning a prior distribution on the signals to recover. We adopt recent denoisingscore matching techniques to learn this prior from data, and subsequently use it aspart of an annealed Hamiltonian Monte-Carlo scheme to sample the full posteriorof image inverse problems. We apply this fra"},"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":"2011.08698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2020-11-16T18:33:06Z","cross_cats_sorted":["cs.CV","cs.LG","eess.SP","physics.med-ph"],"title_canon_sha256":"80af44e2ac595ee4627d5eb28f84fd67f73792b400d3b2230739e67f256eb976","abstract_canon_sha256":"9dea9f355c9e41e18c1104c6d4be9c18cb9a935455d2e24adb1e46404783d595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:07.991870Z","signature_b64":"5oTwkGqWdtPWlXwVuJHK5xyj8SrhPwIOWJBAxa8+/mRi6WRBwtUcB5/H5wirZirOICKn+KjcnVqJx2uhSMDVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b5e2e53a85b3b72c9873dbf3b45b1e04f65ed9b35bf3c23c883af53d8b79444","last_reissued_at":"2026-07-05T01:52:07.991429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:07.991429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoising Score-Matching for Uncertainty Quantification in Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.SP","physics.med-ph"],"primary_cat":"stat.ML","authors_text":"Benjamin Remy, Francois Lanusse, Jean-Luc Starck, Philippe Ciuciu, Zaccharie Ramzi","submitted_at":"2020-11-16T18:33:06Z","abstract_excerpt":"Deep neural networks have proven extremely efficient at solving a wide rangeof inverse problems, but most often the uncertainty on the solution they provideis hard to quantify. In this work, we propose a generic Bayesian framework forsolving inverse problems, in which we limit the use of deep neural networks tolearning a prior distribution on the signals to recover. We adopt recent denoisingscore matching techniques to learn this prior from data, and subsequently use it aspart of an annealed Hamiltonian Monte-Carlo scheme to sample the full posteriorof image inverse problems. We apply this fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08698","kind":"arxiv","version":1},"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/2011.08698/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":"2011.08698","created_at":"2026-07-05T01:52:07.991485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.08698v1","created_at":"2026-07-05T01:52:07.991485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08698","created_at":"2026-07-05T01:52:07.991485+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNPC4U5ILM5X","created_at":"2026-07-05T01:52:07.991485+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNPC4U5ILM5XFSMH","created_at":"2026-07-05T01:52:07.991485+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNPC4U5I","created_at":"2026-07-05T01:52:07.991485+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/FNPC4U5ILM5XFSMHHW7TWRNR4B","json":"https://pith.science/pith/FNPC4U5ILM5XFSMHHW7TWRNR4B.json","graph_json":"https://pith.science/api/pith-number/FNPC4U5ILM5XFSMHHW7TWRNR4B/graph.json","events_json":"https://pith.science/api/pith-number/FNPC4U5ILM5XFSMHHW7TWRNR4B/events.json","paper":"https://pith.science/paper/FNPC4U5I"},"agent_actions":{"view_html":"https://pith.science/pith/FNPC4U5ILM5XFSMHHW7TWRNR4B","download_json":"https://pith.science/pith/FNPC4U5ILM5XFSMHHW7TWRNR4B.json","view_paper":"https://pith.science/paper/FNPC4U5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.08698&json=true","fetch_graph":"https://pith.science/api/pith-number/FNPC4U5ILM5XFSMHHW7TWRNR4B/graph.json","fetch_events":"https://pith.science/api/pith-number/FNPC4U5ILM5XFSMHHW7TWRNR4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNPC4U5ILM5XFSMHHW7TWRNR4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNPC4U5ILM5XFSMHHW7TWRNR4B/action/storage_attestation","attest_author":"https://pith.science/pith/FNPC4U5ILM5XFSMHHW7TWRNR4B/action/author_attestation","sign_citation":"https://pith.science/pith/FNPC4U5ILM5XFSMHHW7TWRNR4B/action/citation_signature","submit_replication":"https://pith.science/pith/FNPC4U5ILM5XFSMHHW7TWRNR4B/action/replication_record"}},"created_at":"2026-07-05T01:52:07.991485+00:00","updated_at":"2026-07-05T01:52:07.991485+00:00"}