{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HX2AH4V5WEPK6KWMUTEHZJY5J5","short_pith_number":"pith:HX2AH4V5","schema_version":"1.0","canonical_sha256":"3df403f2bdb11eaf2acca4c87ca71d4f59974ab200e15da03bf9ff6833b1b07e","source":{"kind":"arxiv","id":"2310.01391","version":1},"attestation_state":"computed","paper":{"title":"A Restoration Network as an Implicit Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Mauricio Delbracio, Peyman Milanfar, Ulugbek S. Kamilov, Yuyang Hu","submitted_at":"2023-10-02T17:48:42Z","abstract_excerpt":"Image denoisers have been shown to be powerful priors for solving inverse problems in imaging. In this work, we introduce a generalization of these methods that allows any image restoration network to be used as an implicit prior. The proposed method uses priors specified by deep neural networks pre-trained as general restoration operators. The method provides a principled approach for adapting state-of-the-art restoration models for other inverse problems. Our theoretical result analyzes its convergence to a stationary point of a global functional associated with the restoration operator. Num"},"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":"2310.01391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2023-10-02T17:48:42Z","cross_cats_sorted":[],"title_canon_sha256":"c54de19f28ffff8f8f1df39f11aacb24dfff54d74ef19e06786c9099d9a5d447","abstract_canon_sha256":"518edc307b9d23d2a57cd74cc94d8f09bc80490ff19746a7e02f082a9e66cb89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:26.118407Z","signature_b64":"8MD1Sv5ZDl+5SzoXS0/+1BpE/l4pSMb+U+ZmUCBmRbPwbHA6yFizuAE+jqjownY+VSAKp/OZDrYs0o8A+WgACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3df403f2bdb11eaf2acca4c87ca71d4f59974ab200e15da03bf9ff6833b1b07e","last_reissued_at":"2026-07-05T06:56:26.117923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:26.117923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Restoration Network as an Implicit Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Mauricio Delbracio, Peyman Milanfar, Ulugbek S. Kamilov, Yuyang Hu","submitted_at":"2023-10-02T17:48:42Z","abstract_excerpt":"Image denoisers have been shown to be powerful priors for solving inverse problems in imaging. In this work, we introduce a generalization of these methods that allows any image restoration network to be used as an implicit prior. The proposed method uses priors specified by deep neural networks pre-trained as general restoration operators. The method provides a principled approach for adapting state-of-the-art restoration models for other inverse problems. Our theoretical result analyzes its convergence to a stationary point of a global functional associated with the restoration operator. Num"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01391","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/2310.01391/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":"2310.01391","created_at":"2026-07-05T06:56:26.117982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01391v1","created_at":"2026-07-05T06:56:26.117982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01391","created_at":"2026-07-05T06:56:26.117982+00:00"},{"alias_kind":"pith_short_12","alias_value":"HX2AH4V5WEPK","created_at":"2026-07-05T06:56:26.117982+00:00"},{"alias_kind":"pith_short_16","alias_value":"HX2AH4V5WEPK6KWM","created_at":"2026-07-05T06:56:26.117982+00:00"},{"alias_kind":"pith_short_8","alias_value":"HX2AH4V5","created_at":"2026-07-05T06:56:26.117982+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":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5","json":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5.json","graph_json":"https://pith.science/api/pith-number/HX2AH4V5WEPK6KWMUTEHZJY5J5/graph.json","events_json":"https://pith.science/api/pith-number/HX2AH4V5WEPK6KWMUTEHZJY5J5/events.json","paper":"https://pith.science/paper/HX2AH4V5"},"agent_actions":{"view_html":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5","download_json":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5.json","view_paper":"https://pith.science/paper/HX2AH4V5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01391&json=true","fetch_graph":"https://pith.science/api/pith-number/HX2AH4V5WEPK6KWMUTEHZJY5J5/graph.json","fetch_events":"https://pith.science/api/pith-number/HX2AH4V5WEPK6KWMUTEHZJY5J5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5/action/storage_attestation","attest_author":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5/action/author_attestation","sign_citation":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5/action/citation_signature","submit_replication":"https://pith.science/pith/HX2AH4V5WEPK6KWMUTEHZJY5J5/action/replication_record"}},"created_at":"2026-07-05T06:56:26.117982+00:00","updated_at":"2026-07-05T06:56:26.117982+00:00"}