{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2HOQMALW5NQESTMVDQKA6UAOX4","short_pith_number":"pith:2HOQMALW","schema_version":"1.0","canonical_sha256":"d1dd060176eb60494d951c140f500ebf321fe06a782720ddf96cfca1f7613e15","source":{"kind":"arxiv","id":"2310.03546","version":3},"attestation_state":"computed","paper":{"title":"Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andr\\'es Almansa, Jiaming Liu, Marien Renaud, Ulugbek S. Kamilov, Valentin De Bortoli","submitted_at":"2023-10-05T13:57:53Z","abstract_excerpt":"Posterior sampling has been shown to be a powerful Bayesian approach for solving imaging inverse problems. The recent plug-and-play unadjusted Langevin algorithm (PnP-ULA) has emerged as a promising method for Monte Carlo sampling and minimum mean squared error (MMSE) estimation by combining physical measurement models with deep-learning priors specified using image denoisers. However, the intricate relationship between the sampling distribution of PnP-ULA and the mismatched data-fidelity and denoiser has not been theoretically analyzed. We address this gap by proposing a posterior-L2 pseudome"},"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":"2310.03546","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-05T13:57:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ba2e21fc0b4a0c2936db4cb67a3804c8864d48066e643339c4626bd78464d08c","abstract_canon_sha256":"2cfe5156517ca14291bb58f01d72ffe1760c66d90e78cbd80c625b0c08a454a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:11.842163Z","signature_b64":"A4koXMm8uOBY1X9ss9fR2Ngv+t0/pvKuXQgyjCuVefurwOartzx2C2Jr/jROZu0iyPYgCT//PW/DNBML7I8uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1dd060176eb60494d951c140f500ebf321fe06a782720ddf96cfca1f7613e15","last_reissued_at":"2026-07-05T11:52:11.841823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:11.841823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andr\\'es Almansa, Jiaming Liu, Marien Renaud, Ulugbek S. Kamilov, Valentin De Bortoli","submitted_at":"2023-10-05T13:57:53Z","abstract_excerpt":"Posterior sampling has been shown to be a powerful Bayesian approach for solving imaging inverse problems. The recent plug-and-play unadjusted Langevin algorithm (PnP-ULA) has emerged as a promising method for Monte Carlo sampling and minimum mean squared error (MMSE) estimation by combining physical measurement models with deep-learning priors specified using image denoisers. However, the intricate relationship between the sampling distribution of PnP-ULA and the mismatched data-fidelity and denoiser has not been theoretically analyzed. We address this gap by proposing a posterior-L2 pseudome"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03546","kind":"arxiv","version":3},"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/2310.03546/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":"2310.03546","created_at":"2026-07-05T11:52:11.841877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03546v3","created_at":"2026-07-05T11:52:11.841877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03546","created_at":"2026-07-05T11:52:11.841877+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HOQMALW5NQE","created_at":"2026-07-05T11:52:11.841877+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HOQMALW5NQESTMV","created_at":"2026-07-05T11:52:11.841877+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HOQMALW","created_at":"2026-07-05T11:52:11.841877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01412","citing_title":"Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4","json":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4.json","graph_json":"https://pith.science/api/pith-number/2HOQMALW5NQESTMVDQKA6UAOX4/graph.json","events_json":"https://pith.science/api/pith-number/2HOQMALW5NQESTMVDQKA6UAOX4/events.json","paper":"https://pith.science/paper/2HOQMALW"},"agent_actions":{"view_html":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4","download_json":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4.json","view_paper":"https://pith.science/paper/2HOQMALW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03546&json=true","fetch_graph":"https://pith.science/api/pith-number/2HOQMALW5NQESTMVDQKA6UAOX4/graph.json","fetch_events":"https://pith.science/api/pith-number/2HOQMALW5NQESTMVDQKA6UAOX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4/action/storage_attestation","attest_author":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4/action/author_attestation","sign_citation":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4/action/citation_signature","submit_replication":"https://pith.science/pith/2HOQMALW5NQESTMVDQKA6UAOX4/action/replication_record"}},"created_at":"2026-07-05T11:52:11.841877+00:00","updated_at":"2026-07-05T11:52:11.841877+00:00"}