{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:H5UEND4Q2XH3BJ4KTNB6UTN5HO","short_pith_number":"pith:H5UEND4Q","schema_version":"1.0","canonical_sha256":"3f68468f90d5cfb0a78a9b43ea4dbd3b881f52afa15704dc2c6b92667c811819","source":{"kind":"arxiv","id":"1912.10557","version":3},"attestation_state":"computed","paper":{"title":"Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.SP"],"primary_cat":"eess.IV","authors_text":"Vishal Monga, Yonina C. Eldar, Yuelong Li","submitted_at":"2019-12-22T23:02:18Z","abstract_excerpt":"Deep neural networks provide unprecedented performance gains in many real world problems in signal and image processing. Despite these gains, future development and practical deployment of deep networks is hindered by their blackbox nature, i.e., lack of interpretability, and by the need for very large training sets. An emerging technique called algorithm unrolling or unfolding offers promise in eliminating these issues by providing a concrete and systematic connection between iterative algorithms that are used widely in signal processing and deep neural networks. Unrolling methods were first "},"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":"1912.10557","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-12-22T23:02:18Z","cross_cats_sorted":["cs.CV","cs.LG","eess.SP"],"title_canon_sha256":"935de3df7507e0e0318c7b5d8bf0089d5054a81c1408075855b3b059236b8b20","abstract_canon_sha256":"01fc378ffd68f4cca7809eb2e8b5995141733da91e1bd5c548703b0192690d7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:24.040028Z","signature_b64":"+RPTe2l7WdLyLAAv20yH08HFT5ENK+4DH85Cr7dAXMOHnU/4UnpGP6KKo4a8VGbPcVFjiQO+TIKhr11sXJsBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f68468f90d5cfb0a78a9b43ea4dbd3b881f52afa15704dc2c6b92667c811819","last_reissued_at":"2026-07-05T01:25:24.039469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:24.039469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.SP"],"primary_cat":"eess.IV","authors_text":"Vishal Monga, Yonina C. Eldar, Yuelong Li","submitted_at":"2019-12-22T23:02:18Z","abstract_excerpt":"Deep neural networks provide unprecedented performance gains in many real world problems in signal and image processing. Despite these gains, future development and practical deployment of deep networks is hindered by their blackbox nature, i.e., lack of interpretability, and by the need for very large training sets. An emerging technique called algorithm unrolling or unfolding offers promise in eliminating these issues by providing a concrete and systematic connection between iterative algorithms that are used widely in signal processing and deep neural networks. Unrolling methods were first "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.10557","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/1912.10557/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":"1912.10557","created_at":"2026-07-05T01:25:24.039532+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.10557v3","created_at":"2026-07-05T01:25:24.039532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.10557","created_at":"2026-07-05T01:25:24.039532+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5UEND4Q2XH3","created_at":"2026-07-05T01:25:24.039532+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5UEND4Q2XH3BJ4K","created_at":"2026-07-05T01:25:24.039532+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5UEND4Q","created_at":"2026-07-05T01:25:24.039532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26745","citing_title":"Robust Model-Based Iteration for Passive Gamma Emission Tomography","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO","json":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO.json","graph_json":"https://pith.science/api/pith-number/H5UEND4Q2XH3BJ4KTNB6UTN5HO/graph.json","events_json":"https://pith.science/api/pith-number/H5UEND4Q2XH3BJ4KTNB6UTN5HO/events.json","paper":"https://pith.science/paper/H5UEND4Q"},"agent_actions":{"view_html":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO","download_json":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO.json","view_paper":"https://pith.science/paper/H5UEND4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.10557&json=true","fetch_graph":"https://pith.science/api/pith-number/H5UEND4Q2XH3BJ4KTNB6UTN5HO/graph.json","fetch_events":"https://pith.science/api/pith-number/H5UEND4Q2XH3BJ4KTNB6UTN5HO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO/action/storage_attestation","attest_author":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO/action/author_attestation","sign_citation":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO/action/citation_signature","submit_replication":"https://pith.science/pith/H5UEND4Q2XH3BJ4KTNB6UTN5HO/action/replication_record"}},"created_at":"2026-07-05T01:25:24.039532+00:00","updated_at":"2026-07-05T01:25:24.039532+00:00"}