{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HT3P5BJPD2DWHCMMX5E54RTYUR","short_pith_number":"pith:HT3P5BJP","schema_version":"1.0","canonical_sha256":"3cf6fe852f1e8763898cbf49de4678a4531280f68b9a05a47423d33844120508","source":{"kind":"arxiv","id":"2410.02057","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Deep Restoration Priors for Imaging Inverse Problems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Albert Peng, Mauricio Delbracio, Peyman Milanfar, Ulugbek S. Kamilov, Weijie Gan, Yuyang Hu","submitted_at":"2024-10-02T22:06:49Z","abstract_excerpt":"Deep neural networks trained as image denoisers are widely used as priors for solving imaging inverse problems. While Gaussian denoising is thought sufficient for learning image priors, we show that priors from deep models pre-trained as more general restoration operators can perform better. We introduce Stochastic deep Restoration Priors (ShaRP), a novel method that leverages an ensemble of such restoration models to regularize inverse problems. ShaRP improves upon methods using Gaussian denoiser priors by better handling structured artifacts and enabling self-supervised training even without"},"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":"2410.02057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2024-10-02T22:06:49Z","cross_cats_sorted":[],"title_canon_sha256":"4f26c90395b4c6b0b0f29d6916658eff1ea5d64bf8fcd8c27f0a94cc2fa57a77","abstract_canon_sha256":"5c634429c23836e8c19d6975e94a9179cd7a5cd8908b542a2e72b12a6de34c9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:59.889719Z","signature_b64":"id+H+w/HBsDXjFW348KFCwSCA2ppOY60sILk1xZ66FrDtIi7RvN446bIqcMNC+nLPero0mh5+3zKvMwtG7lPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cf6fe852f1e8763898cbf49de4678a4531280f68b9a05a47423d33844120508","last_reissued_at":"2026-07-05T09:14:59.889227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:59.889227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Deep Restoration Priors for Imaging Inverse Problems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Albert Peng, Mauricio Delbracio, Peyman Milanfar, Ulugbek S. Kamilov, Weijie Gan, Yuyang Hu","submitted_at":"2024-10-02T22:06:49Z","abstract_excerpt":"Deep neural networks trained as image denoisers are widely used as priors for solving imaging inverse problems. While Gaussian denoising is thought sufficient for learning image priors, we show that priors from deep models pre-trained as more general restoration operators can perform better. We introduce Stochastic deep Restoration Priors (ShaRP), a novel method that leverages an ensemble of such restoration models to regularize inverse problems. ShaRP improves upon methods using Gaussian denoiser priors by better handling structured artifacts and enabling self-supervised training even without"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02057","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/2410.02057/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":"2410.02057","created_at":"2026-07-05T09:14:59.889283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02057v1","created_at":"2026-07-05T09:14:59.889283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02057","created_at":"2026-07-05T09:14:59.889283+00:00"},{"alias_kind":"pith_short_12","alias_value":"HT3P5BJPD2DW","created_at":"2026-07-05T09:14:59.889283+00:00"},{"alias_kind":"pith_short_16","alias_value":"HT3P5BJPD2DWHCMM","created_at":"2026-07-05T09:14:59.889283+00:00"},{"alias_kind":"pith_short_8","alias_value":"HT3P5BJP","created_at":"2026-07-05T09:14:59.889283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.01608","citing_title":"NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR","json":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR.json","graph_json":"https://pith.science/api/pith-number/HT3P5BJPD2DWHCMMX5E54RTYUR/graph.json","events_json":"https://pith.science/api/pith-number/HT3P5BJPD2DWHCMMX5E54RTYUR/events.json","paper":"https://pith.science/paper/HT3P5BJP"},"agent_actions":{"view_html":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR","download_json":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR.json","view_paper":"https://pith.science/paper/HT3P5BJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02057&json=true","fetch_graph":"https://pith.science/api/pith-number/HT3P5BJPD2DWHCMMX5E54RTYUR/graph.json","fetch_events":"https://pith.science/api/pith-number/HT3P5BJPD2DWHCMMX5E54RTYUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR/action/storage_attestation","attest_author":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR/action/author_attestation","sign_citation":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR/action/citation_signature","submit_replication":"https://pith.science/pith/HT3P5BJPD2DWHCMMX5E54RTYUR/action/replication_record"}},"created_at":"2026-07-05T09:14:59.889283+00:00","updated_at":"2026-07-05T09:14:59.889283+00:00"}