{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:NNXE5HN677CC45LLQXLGSSG33L","short_pith_number":"pith:NNXE5HN6","schema_version":"1.0","canonical_sha256":"6b6e4e9dbeffc42e756b85d66948dbdae44d97d156c160faa40983fcee8ae896","source":{"kind":"arxiv","id":"1309.1952","version":2},"attestation_state":"computed","paper":{"title":"A Clustering Approach to Learn Sparsely-Used Overcomplete Dictionaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Alekh Agarwal, Animashree Anandkumar, Praneeth Netrapalli","submitted_at":"2013-09-08T12:55:39Z","abstract_excerpt":"We consider the problem of learning overcomplete dictionaries in the context of sparse coding, where each sample selects a sparse subset of dictionary elements. Our main result is a strategy to approximately recover the unknown dictionary using an efficient algorithm. Our algorithm is a clustering-style procedure, where each cluster is used to estimate a dictionary element. The resulting solution can often be further cleaned up to obtain a high accuracy estimate, and we provide one simple scenario where $\\ell_1$-regularized regression can be used for such a second stage."},"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":"1309.1952","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-09-08T12:55:39Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"febcb4c06d21415d50e1b6b34a1b8e1b760b1838f6765e368b283e3bbf3de7b3","abstract_canon_sha256":"536803449cd1302217756c2634eae7cbf28f650546df2143f7e04acbd61d103e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:48:17.632399Z","signature_b64":"5h0cNCyWcgE0Jujh2UbPq81A0jmTiDDxzvBxuVSnF6k0814sZ+Uk5LYSUGhqDIXtfSEAVwvf9wPwZsUA0hsRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b6e4e9dbeffc42e756b85d66948dbdae44d97d156c160faa40983fcee8ae896","last_reissued_at":"2026-05-18T02:48:17.631937Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:48:17.631937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Clustering Approach to Learn Sparsely-Used Overcomplete Dictionaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Alekh Agarwal, Animashree Anandkumar, Praneeth Netrapalli","submitted_at":"2013-09-08T12:55:39Z","abstract_excerpt":"We consider the problem of learning overcomplete dictionaries in the context of sparse coding, where each sample selects a sparse subset of dictionary elements. Our main result is a strategy to approximately recover the unknown dictionary using an efficient algorithm. Our algorithm is a clustering-style procedure, where each cluster is used to estimate a dictionary element. The resulting solution can often be further cleaned up to obtain a high accuracy estimate, and we provide one simple scenario where $\\ell_1$-regularized regression can be used for such a second stage."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1309.1952","kind":"arxiv","version":2},"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":"1309.1952","created_at":"2026-05-18T02:48:17.632010+00:00"},{"alias_kind":"arxiv_version","alias_value":"1309.1952v2","created_at":"2026-05-18T02:48:17.632010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1309.1952","created_at":"2026-05-18T02:48:17.632010+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNXE5HN677CC","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNXE5HN677CC45LL","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNXE5HN6","created_at":"2026-05-18T12:27:52.871228+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/NNXE5HN677CC45LLQXLGSSG33L","json":"https://pith.science/pith/NNXE5HN677CC45LLQXLGSSG33L.json","graph_json":"https://pith.science/api/pith-number/NNXE5HN677CC45LLQXLGSSG33L/graph.json","events_json":"https://pith.science/api/pith-number/NNXE5HN677CC45LLQXLGSSG33L/events.json","paper":"https://pith.science/paper/NNXE5HN6"},"agent_actions":{"view_html":"https://pith.science/pith/NNXE5HN677CC45LLQXLGSSG33L","download_json":"https://pith.science/pith/NNXE5HN677CC45LLQXLGSSG33L.json","view_paper":"https://pith.science/paper/NNXE5HN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1309.1952&json=true","fetch_graph":"https://pith.science/api/pith-number/NNXE5HN677CC45LLQXLGSSG33L/graph.json","fetch_events":"https://pith.science/api/pith-number/NNXE5HN677CC45LLQXLGSSG33L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNXE5HN677CC45LLQXLGSSG33L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNXE5HN677CC45LLQXLGSSG33L/action/storage_attestation","attest_author":"https://pith.science/pith/NNXE5HN677CC45LLQXLGSSG33L/action/author_attestation","sign_citation":"https://pith.science/pith/NNXE5HN677CC45LLQXLGSSG33L/action/citation_signature","submit_replication":"https://pith.science/pith/NNXE5HN677CC45LLQXLGSSG33L/action/replication_record"}},"created_at":"2026-05-18T02:48:17.632010+00:00","updated_at":"2026-05-18T02:48:17.632010+00:00"}