{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PD73GQUSRZLEXF5CKJUEMGJJPM","short_pith_number":"pith:PD73GQUS","schema_version":"1.0","canonical_sha256":"78ffb342928e564b97a252684619297b1c66522a47d17222b5e9e6465410b2d3","source":{"kind":"arxiv","id":"1703.03208","version":1},"attestation_state":"computed","paper":{"title":"Compressed Sensing using Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Ajil Jalal, Alexandros G. Dimakis, Ashish Bora, Eric Price","submitted_at":"2017-03-09T10:11:03Z","abstract_excerpt":"The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain. For almost all results in this literature, the structure is represented by sparsity in a well-chosen basis. We show how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all. Instead, we suppose that vectors lie near the range of a generative model $G: \\mathbb{R}^k \\to \\mathbb{R}^n$. Our main theorem is that, if $G$ is $L$-Lipschitz, then roughly $O(k "},"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":"1703.03208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-09T10:11:03Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"6e80106378b46a7bd7693c84f1819f51d9cd5fcb26792ac58160ae68e93f5a20","abstract_canon_sha256":"2b805d36ab80f5480e81e934bf8203de28db3b87d408669e38177403e5d4e2f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:01.103619Z","signature_b64":"LK4vZEDiSQNjhJRKp8CuT+MY9EMMqeWOe3l5zCaCoKBpclZsYjJ5qahC8evLObTRm2GQt3dhSxVpNie/91GKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78ffb342928e564b97a252684619297b1c66522a47d17222b5e9e6465410b2d3","last_reissued_at":"2026-05-18T00:49:01.102790Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:01.102790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressed Sensing using Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Ajil Jalal, Alexandros G. Dimakis, Ashish Bora, Eric Price","submitted_at":"2017-03-09T10:11:03Z","abstract_excerpt":"The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain. For almost all results in this literature, the structure is represented by sparsity in a well-chosen basis. We show how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all. Instead, we suppose that vectors lie near the range of a generative model $G: \\mathbb{R}^k \\to \\mathbb{R}^n$. Our main theorem is that, if $G$ is $L$-Lipschitz, then roughly $O(k "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03208","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":""},"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":"1703.03208","created_at":"2026-05-18T00:49:01.102924+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.03208v1","created_at":"2026-05-18T00:49:01.102924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03208","created_at":"2026-05-18T00:49:01.102924+00:00"},{"alias_kind":"pith_short_12","alias_value":"PD73GQUSRZLE","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PD73GQUSRZLEXF5C","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PD73GQUS","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07513","citing_title":"Tessellations of Semi-Discrete Flow Matching","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM","json":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM.json","graph_json":"https://pith.science/api/pith-number/PD73GQUSRZLEXF5CKJUEMGJJPM/graph.json","events_json":"https://pith.science/api/pith-number/PD73GQUSRZLEXF5CKJUEMGJJPM/events.json","paper":"https://pith.science/paper/PD73GQUS"},"agent_actions":{"view_html":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM","download_json":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM.json","view_paper":"https://pith.science/paper/PD73GQUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.03208&json=true","fetch_graph":"https://pith.science/api/pith-number/PD73GQUSRZLEXF5CKJUEMGJJPM/graph.json","fetch_events":"https://pith.science/api/pith-number/PD73GQUSRZLEXF5CKJUEMGJJPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM/action/storage_attestation","attest_author":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM/action/author_attestation","sign_citation":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM/action/citation_signature","submit_replication":"https://pith.science/pith/PD73GQUSRZLEXF5CKJUEMGJJPM/action/replication_record"}},"created_at":"2026-05-18T00:49:01.102924+00:00","updated_at":"2026-05-18T00:49:01.102924+00:00"}