{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:RB4PUUPKKVFAN3OV7S2NU4MMU3","short_pith_number":"pith:RB4PUUPK","schema_version":"1.0","canonical_sha256":"8878fa51ea554a06edd5fcb4da718ca6d5616a5fe5bd4f8d0cc6ab24ed24c82a","source":{"kind":"arxiv","id":"1410.7660","version":1},"attestation_state":"computed","paper":{"title":"Non-convex Robust PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Animashree Anandkumar, Praneeth Netrapalli, Prateek Jain, Sujay Sanghavi, U N Niranjan","submitted_at":"2014-10-28T15:33:13Z","abstract_excerpt":"We propose a new method for robust PCA -- the task of recovering a low-rank matrix from sparse corruptions that are of unknown value and support. Our method involves alternating between projecting appropriate residuals onto the set of low-rank matrices, and the set of sparse matrices; each projection is {\\em non-convex} but easy to compute. In spite of this non-convexity, we establish exact recovery of the low-rank matrix, under the same conditions that are required by existing methods (which are based on convex optimization). For an $m \\times n$ input matrix ($m \\leq n)$, our method has a run"},"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":"1410.7660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2014-10-28T15:33:13Z","cross_cats_sorted":["cs.LG","math.IT","stat.ML"],"title_canon_sha256":"ad81483201c8236df2b1a2890ee3a583fb5364061d904d1f4f552063d769fe45","abstract_canon_sha256":"8ad7ff3b28f7fd5bac6f7a896dbeb765809486d8d421344470191f794eea4bdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:39:09.752977Z","signature_b64":"H40vp9kpGKe2b1p8gsQKpaD0Z7h/k7z0L5dIFLNQ8sAgZkKzYbF3ph/IV/SM8bxQax3rPodjNpIZ73shtZAXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8878fa51ea554a06edd5fcb4da718ca6d5616a5fe5bd4f8d0cc6ab24ed24c82a","last_reissued_at":"2026-05-18T02:39:09.752332Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:39:09.752332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-convex Robust PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Animashree Anandkumar, Praneeth Netrapalli, Prateek Jain, Sujay Sanghavi, U N Niranjan","submitted_at":"2014-10-28T15:33:13Z","abstract_excerpt":"We propose a new method for robust PCA -- the task of recovering a low-rank matrix from sparse corruptions that are of unknown value and support. Our method involves alternating between projecting appropriate residuals onto the set of low-rank matrices, and the set of sparse matrices; each projection is {\\em non-convex} but easy to compute. In spite of this non-convexity, we establish exact recovery of the low-rank matrix, under the same conditions that are required by existing methods (which are based on convex optimization). For an $m \\times n$ input matrix ($m \\leq n)$, our method has a run"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.7660","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":"1410.7660","created_at":"2026-05-18T02:39:09.752424+00:00"},{"alias_kind":"arxiv_version","alias_value":"1410.7660v1","created_at":"2026-05-18T02:39:09.752424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.7660","created_at":"2026-05-18T02:39:09.752424+00:00"},{"alias_kind":"pith_short_12","alias_value":"RB4PUUPKKVFA","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_16","alias_value":"RB4PUUPKKVFAN3OV","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_8","alias_value":"RB4PUUPK","created_at":"2026-05-18T12:28:46.137349+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/RB4PUUPKKVFAN3OV7S2NU4MMU3","json":"https://pith.science/pith/RB4PUUPKKVFAN3OV7S2NU4MMU3.json","graph_json":"https://pith.science/api/pith-number/RB4PUUPKKVFAN3OV7S2NU4MMU3/graph.json","events_json":"https://pith.science/api/pith-number/RB4PUUPKKVFAN3OV7S2NU4MMU3/events.json","paper":"https://pith.science/paper/RB4PUUPK"},"agent_actions":{"view_html":"https://pith.science/pith/RB4PUUPKKVFAN3OV7S2NU4MMU3","download_json":"https://pith.science/pith/RB4PUUPKKVFAN3OV7S2NU4MMU3.json","view_paper":"https://pith.science/paper/RB4PUUPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1410.7660&json=true","fetch_graph":"https://pith.science/api/pith-number/RB4PUUPKKVFAN3OV7S2NU4MMU3/graph.json","fetch_events":"https://pith.science/api/pith-number/RB4PUUPKKVFAN3OV7S2NU4MMU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RB4PUUPKKVFAN3OV7S2NU4MMU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RB4PUUPKKVFAN3OV7S2NU4MMU3/action/storage_attestation","attest_author":"https://pith.science/pith/RB4PUUPKKVFAN3OV7S2NU4MMU3/action/author_attestation","sign_citation":"https://pith.science/pith/RB4PUUPKKVFAN3OV7S2NU4MMU3/action/citation_signature","submit_replication":"https://pith.science/pith/RB4PUUPKKVFAN3OV7S2NU4MMU3/action/replication_record"}},"created_at":"2026-05-18T02:39:09.752424+00:00","updated_at":"2026-05-18T02:39:09.752424+00:00"}