{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5GFSG3ZTAWRCFFXNF5BQ2ZI25M","short_pith_number":"pith:5GFSG3ZT","schema_version":"1.0","canonical_sha256":"e98b236f3305a22296ed2f430d651aeb092e91ee04aec2b1991cd37c52152929","source":{"kind":"arxiv","id":"2110.10093","version":4},"attestation_state":"computed","paper":{"title":"Stochastic Primal-Dual Deep Unrolling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC"],"primary_cat":"eess.IV","authors_text":"Carola-Bibiane Sch\\\"onlieb, Junqi Tang, Subhadip Mukherjee","submitted_at":"2021-10-19T16:46:03Z","abstract_excerpt":"We propose a new type of efficient deep-unrolling networks for solving imaging inverse problems. Conventional deep-unrolling methods require full forward operator and its adjoint across each layer, and hence can be significantly more expensive computationally as compared with other end-to-end methods that are based on post-processing of model-based reconstructions, especially for 3D image reconstruction tasks. We develop a stochastic (ordered-subsets) variant of the classical learned primal-dual (LPD), which is a state-of-the-art unrolling network for tomographic image reconstruction. The prop"},"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":"2110.10093","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-10-19T16:46:03Z","cross_cats_sorted":["cs.CV","math.OC"],"title_canon_sha256":"ed63f35593648f92546985605447895e35373eb776b6fa02239bb4bf04101554","abstract_canon_sha256":"f210f27ce80084931843fbd8e580359d924b38301d5340e25035ff2cf342bae7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:51.150199Z","signature_b64":"n5O7WKEPq0jZmkHkzYyroG5dLrUZiNVqJqAPEVb/X4KQDSldc4Qe3hTfMjfOyEu7UMVD8ylW5LwqDOTCTqA0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e98b236f3305a22296ed2f430d651aeb092e91ee04aec2b1991cd37c52152929","last_reissued_at":"2026-07-05T03:56:51.149768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:51.149768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Primal-Dual Deep Unrolling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC"],"primary_cat":"eess.IV","authors_text":"Carola-Bibiane Sch\\\"onlieb, Junqi Tang, Subhadip Mukherjee","submitted_at":"2021-10-19T16:46:03Z","abstract_excerpt":"We propose a new type of efficient deep-unrolling networks for solving imaging inverse problems. Conventional deep-unrolling methods require full forward operator and its adjoint across each layer, and hence can be significantly more expensive computationally as compared with other end-to-end methods that are based on post-processing of model-based reconstructions, especially for 3D image reconstruction tasks. We develop a stochastic (ordered-subsets) variant of the classical learned primal-dual (LPD), which is a state-of-the-art unrolling network for tomographic image reconstruction. The prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10093","kind":"arxiv","version":4},"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/2110.10093/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":"2110.10093","created_at":"2026-07-05T03:56:51.149828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10093v4","created_at":"2026-07-05T03:56:51.149828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10093","created_at":"2026-07-05T03:56:51.149828+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GFSG3ZTAWRC","created_at":"2026-07-05T03:56:51.149828+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GFSG3ZTAWRCFFXN","created_at":"2026-07-05T03:56:51.149828+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GFSG3ZT","created_at":"2026-07-05T03:56:51.149828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11732","citing_title":"Data-driven approaches to inverse problems","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M","json":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M.json","graph_json":"https://pith.science/api/pith-number/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/graph.json","events_json":"https://pith.science/api/pith-number/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/events.json","paper":"https://pith.science/paper/5GFSG3ZT"},"agent_actions":{"view_html":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M","download_json":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M.json","view_paper":"https://pith.science/paper/5GFSG3ZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10093&json=true","fetch_graph":"https://pith.science/api/pith-number/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/graph.json","fetch_events":"https://pith.science/api/pith-number/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/action/storage_attestation","attest_author":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/action/author_attestation","sign_citation":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/action/citation_signature","submit_replication":"https://pith.science/pith/5GFSG3ZTAWRCFFXNF5BQ2ZI25M/action/replication_record"}},"created_at":"2026-07-05T03:56:51.149828+00:00","updated_at":"2026-07-05T03:56:51.149828+00:00"}