{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:TTD7YLZRYFUBWAUCUORJMVHQO7","short_pith_number":"pith:TTD7YLZR","schema_version":"1.0","canonical_sha256":"9cc7fc2f31c1681b0282a3a29654f077ddaf2c2b6f4a8f98404f09f69409a418","source":{"kind":"arxiv","id":"1204.2436","version":1},"attestation_state":"computed","paper":{"title":"Sparse and Unique Nonnegative Matrix Factorization Through Data Preprocessing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","math.OC"],"primary_cat":"stat.ML","authors_text":"Nicolas Gillis","submitted_at":"2012-04-11T13:03:26Z","abstract_excerpt":"Nonnegative matrix factorization (NMF) has become a very popular technique in machine learning because it automatically extracts meaningful features through a sparse and part-based representation. However, NMF has the drawback of being highly ill-posed, that is, there typically exist many different but equivalent factorizations. In this paper, we introduce a completely new way to obtaining more well-posed NMF problems whose solutions are sparser. Our technique is based on the preprocessing of the nonnegative input data matrix, and relies on the theory of M-matrices and the geometric interpreta"},"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":"1204.2436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-04-11T13:03:26Z","cross_cats_sorted":["math.NA","math.OC"],"title_canon_sha256":"6a3a1cd55c88026f3148ad04e8d65409ee0a84fb4bb7046081240655562ba958","abstract_canon_sha256":"b686dd977d1217ebc994cdfb73b524a6c1f8fbefba7f82f02d49b97d139806e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:39:05.144809Z","signature_b64":"SMFDj34oaByvNwcfKORpXMs+vVNchmuOYbAX/c/HyXToyRHgshunFxRn+jwEwJ/kwfP9m7178Of2vuyO5C91DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc7fc2f31c1681b0282a3a29654f077ddaf2c2b6f4a8f98404f09f69409a418","last_reissued_at":"2026-05-18T03:39:05.144221Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:39:05.144221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse and Unique Nonnegative Matrix Factorization Through Data Preprocessing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","math.OC"],"primary_cat":"stat.ML","authors_text":"Nicolas Gillis","submitted_at":"2012-04-11T13:03:26Z","abstract_excerpt":"Nonnegative matrix factorization (NMF) has become a very popular technique in machine learning because it automatically extracts meaningful features through a sparse and part-based representation. However, NMF has the drawback of being highly ill-posed, that is, there typically exist many different but equivalent factorizations. In this paper, we introduce a completely new way to obtaining more well-posed NMF problems whose solutions are sparser. Our technique is based on the preprocessing of the nonnegative input data matrix, and relies on the theory of M-matrices and the geometric interpreta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.2436","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":"1204.2436","created_at":"2026-05-18T03:39:05.144299+00:00"},{"alias_kind":"arxiv_version","alias_value":"1204.2436v1","created_at":"2026-05-18T03:39:05.144299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.2436","created_at":"2026-05-18T03:39:05.144299+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTD7YLZRYFUB","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTD7YLZRYFUBWAUC","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTD7YLZR","created_at":"2026-05-18T12:27:23.164592+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/TTD7YLZRYFUBWAUCUORJMVHQO7","json":"https://pith.science/pith/TTD7YLZRYFUBWAUCUORJMVHQO7.json","graph_json":"https://pith.science/api/pith-number/TTD7YLZRYFUBWAUCUORJMVHQO7/graph.json","events_json":"https://pith.science/api/pith-number/TTD7YLZRYFUBWAUCUORJMVHQO7/events.json","paper":"https://pith.science/paper/TTD7YLZR"},"agent_actions":{"view_html":"https://pith.science/pith/TTD7YLZRYFUBWAUCUORJMVHQO7","download_json":"https://pith.science/pith/TTD7YLZRYFUBWAUCUORJMVHQO7.json","view_paper":"https://pith.science/paper/TTD7YLZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1204.2436&json=true","fetch_graph":"https://pith.science/api/pith-number/TTD7YLZRYFUBWAUCUORJMVHQO7/graph.json","fetch_events":"https://pith.science/api/pith-number/TTD7YLZRYFUBWAUCUORJMVHQO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTD7YLZRYFUBWAUCUORJMVHQO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTD7YLZRYFUBWAUCUORJMVHQO7/action/storage_attestation","attest_author":"https://pith.science/pith/TTD7YLZRYFUBWAUCUORJMVHQO7/action/author_attestation","sign_citation":"https://pith.science/pith/TTD7YLZRYFUBWAUCUORJMVHQO7/action/citation_signature","submit_replication":"https://pith.science/pith/TTD7YLZRYFUBWAUCUORJMVHQO7/action/replication_record"}},"created_at":"2026-05-18T03:39:05.144299+00:00","updated_at":"2026-05-18T03:39:05.144299+00:00"}