{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LNCDUL7K6UAMFXKJN2YCBWRDUV","short_pith_number":"pith:LNCDUL7K","schema_version":"1.0","canonical_sha256":"5b443a2feaf500c2dd496eb020da23a56105ef200d6782c1da3d39f4b46a402b","source":{"kind":"arxiv","id":"2205.13051","version":1},"attestation_state":"computed","paper":{"title":"Online Deep Equilibrium Learning for Regularization by Denoising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Jiaming Liu, Shirin Shoushtari, Ulugbek S. Kamilov, Weijie Gan, Xiaojian Xu","submitted_at":"2022-05-25T21:06:22Z","abstract_excerpt":"Plug-and-Play Priors (PnP) and Regularization by Denoising (RED) are widely-used frameworks for solving imaging inverse problems by computing fixed-points of operators combining physical measurement models and learned image priors. While traditional PnP/RED formulations have focused on priors specified using image denoisers, there is a growing interest in learning PnP/RED priors that are end-to-end optimal. The recent Deep Equilibrium Models (DEQ) framework has enabled memory-efficient end-to-end learning of PnP/RED priors by implicitly differentiating through the fixed-point equations 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":"2205.13051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2022-05-25T21:06:22Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"170ecd04e7f7b5915d6137417537d75220e48cf164778c285e0a02029e68d0c9","abstract_canon_sha256":"e0182502b0d27559f18290a2e208e2d29cadd8763f5419e4892c0dec6cd48ce6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:39.514266Z","signature_b64":"sN7bI+KDUbIY5XVW7d5vKl914MJjb+kMGKAoRrsd61BCC2ewHkXqDn6aUAuYA+RALHVeEK1TzK5Mv2g+2PWIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b443a2feaf500c2dd496eb020da23a56105ef200d6782c1da3d39f4b46a402b","last_reissued_at":"2026-07-05T04:26:39.513823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:39.513823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Deep Equilibrium Learning for Regularization by Denoising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Jiaming Liu, Shirin Shoushtari, Ulugbek S. Kamilov, Weijie Gan, Xiaojian Xu","submitted_at":"2022-05-25T21:06:22Z","abstract_excerpt":"Plug-and-Play Priors (PnP) and Regularization by Denoising (RED) are widely-used frameworks for solving imaging inverse problems by computing fixed-points of operators combining physical measurement models and learned image priors. While traditional PnP/RED formulations have focused on priors specified using image denoisers, there is a growing interest in learning PnP/RED priors that are end-to-end optimal. The recent Deep Equilibrium Models (DEQ) framework has enabled memory-efficient end-to-end learning of PnP/RED priors by implicitly differentiating through the fixed-point equations without"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13051","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/2205.13051/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":"2205.13051","created_at":"2026-07-05T04:26:39.513880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13051v1","created_at":"2026-07-05T04:26:39.513880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13051","created_at":"2026-07-05T04:26:39.513880+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNCDUL7K6UAM","created_at":"2026-07-05T04:26:39.513880+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNCDUL7K6UAMFXKJ","created_at":"2026-07-05T04:26:39.513880+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNCDUL7K","created_at":"2026-07-05T04:26:39.513880+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/LNCDUL7K6UAMFXKJN2YCBWRDUV","json":"https://pith.science/pith/LNCDUL7K6UAMFXKJN2YCBWRDUV.json","graph_json":"https://pith.science/api/pith-number/LNCDUL7K6UAMFXKJN2YCBWRDUV/graph.json","events_json":"https://pith.science/api/pith-number/LNCDUL7K6UAMFXKJN2YCBWRDUV/events.json","paper":"https://pith.science/paper/LNCDUL7K"},"agent_actions":{"view_html":"https://pith.science/pith/LNCDUL7K6UAMFXKJN2YCBWRDUV","download_json":"https://pith.science/pith/LNCDUL7K6UAMFXKJN2YCBWRDUV.json","view_paper":"https://pith.science/paper/LNCDUL7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13051&json=true","fetch_graph":"https://pith.science/api/pith-number/LNCDUL7K6UAMFXKJN2YCBWRDUV/graph.json","fetch_events":"https://pith.science/api/pith-number/LNCDUL7K6UAMFXKJN2YCBWRDUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNCDUL7K6UAMFXKJN2YCBWRDUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNCDUL7K6UAMFXKJN2YCBWRDUV/action/storage_attestation","attest_author":"https://pith.science/pith/LNCDUL7K6UAMFXKJN2YCBWRDUV/action/author_attestation","sign_citation":"https://pith.science/pith/LNCDUL7K6UAMFXKJN2YCBWRDUV/action/citation_signature","submit_replication":"https://pith.science/pith/LNCDUL7K6UAMFXKJN2YCBWRDUV/action/replication_record"}},"created_at":"2026-07-05T04:26:39.513880+00:00","updated_at":"2026-07-05T04:26:39.513880+00:00"}