{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LW6VXZEY5LUVYDN43URBPTONTS","short_pith_number":"pith:LW6VXZEY","schema_version":"1.0","canonical_sha256":"5dbd5be498eae95c0dbcdd2217cdcd9c89a646b2190b0f80894ebdd83dc2cc33","source":{"kind":"arxiv","id":"1805.00184","version":1},"attestation_state":"computed","paper":{"title":"Compact Factorization of Matrices Using Generalized Round-Rank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Carlos Guestrin, Pouya Pezeshkpour, Sameer Singh","submitted_at":"2018-05-01T04:41:58Z","abstract_excerpt":"Matrix factorization is a well-studied task in machine learning for compactly representing large, noisy data. In our approach, instead of using the traditional concept of matrix rank, we define a new notion of link-rank based on a non-linear link function used within factorization. In particular, by applying the round function on a factorization to obtain ordinal-valued matrices, we introduce generalized round-rank (GRR). We show that not only are there many full-rank matrices that are low GRR, but further, that these matrices cannot be approximated well by low-rank linear factorization. We pr"},"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":"1805.00184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-01T04:41:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"028f09cbf58d8a187e9e41aeef11730f0702835b19bf87e3a271b68f65ef63a3","abstract_canon_sha256":"afafa33964bfb52b1b7bfae69c654c68db9cd856c37cd6b6a804bd1af53b7e41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:10.356982Z","signature_b64":"NtawwDHgO/WhzlfSXGcGdmIbv4MjCYaEObrgmNUlhPUAVYrVyPZNyRIXo/kTM6U/+ebwVaQTT+KD/Thy40yCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dbd5be498eae95c0dbcdd2217cdcd9c89a646b2190b0f80894ebdd83dc2cc33","last_reissued_at":"2026-05-18T00:17:10.356082Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:10.356082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compact Factorization of Matrices Using Generalized Round-Rank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Carlos Guestrin, Pouya Pezeshkpour, Sameer Singh","submitted_at":"2018-05-01T04:41:58Z","abstract_excerpt":"Matrix factorization is a well-studied task in machine learning for compactly representing large, noisy data. In our approach, instead of using the traditional concept of matrix rank, we define a new notion of link-rank based on a non-linear link function used within factorization. In particular, by applying the round function on a factorization to obtain ordinal-valued matrices, we introduce generalized round-rank (GRR). We show that not only are there many full-rank matrices that are low GRR, but further, that these matrices cannot be approximated well by low-rank linear factorization. We pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00184","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":"1805.00184","created_at":"2026-05-18T00:17:10.356263+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.00184v1","created_at":"2026-05-18T00:17:10.356263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00184","created_at":"2026-05-18T00:17:10.356263+00:00"},{"alias_kind":"pith_short_12","alias_value":"LW6VXZEY5LUV","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LW6VXZEY5LUVYDN4","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LW6VXZEY","created_at":"2026-05-18T12:32:37.024351+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/LW6VXZEY5LUVYDN43URBPTONTS","json":"https://pith.science/pith/LW6VXZEY5LUVYDN43URBPTONTS.json","graph_json":"https://pith.science/api/pith-number/LW6VXZEY5LUVYDN43URBPTONTS/graph.json","events_json":"https://pith.science/api/pith-number/LW6VXZEY5LUVYDN43URBPTONTS/events.json","paper":"https://pith.science/paper/LW6VXZEY"},"agent_actions":{"view_html":"https://pith.science/pith/LW6VXZEY5LUVYDN43URBPTONTS","download_json":"https://pith.science/pith/LW6VXZEY5LUVYDN43URBPTONTS.json","view_paper":"https://pith.science/paper/LW6VXZEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.00184&json=true","fetch_graph":"https://pith.science/api/pith-number/LW6VXZEY5LUVYDN43URBPTONTS/graph.json","fetch_events":"https://pith.science/api/pith-number/LW6VXZEY5LUVYDN43URBPTONTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LW6VXZEY5LUVYDN43URBPTONTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LW6VXZEY5LUVYDN43URBPTONTS/action/storage_attestation","attest_author":"https://pith.science/pith/LW6VXZEY5LUVYDN43URBPTONTS/action/author_attestation","sign_citation":"https://pith.science/pith/LW6VXZEY5LUVYDN43URBPTONTS/action/citation_signature","submit_replication":"https://pith.science/pith/LW6VXZEY5LUVYDN43URBPTONTS/action/replication_record"}},"created_at":"2026-05-18T00:17:10.356263+00:00","updated_at":"2026-05-18T00:17:10.356263+00:00"}