{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TZ6Y5XR27ISH3N24TMXOFKPUEA","short_pith_number":"pith:TZ6Y5XR2","schema_version":"1.0","canonical_sha256":"9e7d8ede3afa247db75c9b2ee2a9f4201202cfb08170c7ace6fbc0a76ea9a834","source":{"kind":"arxiv","id":"1811.11088","version":3},"attestation_state":"computed","paper":{"title":"Bilinear Parameterization For Differentiable Rank-Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anders Heyden, Carl Olsson, Marcus Valtonen \\\"Ornhag","submitted_at":"2018-11-27T16:48:11Z","abstract_excerpt":"Low rank approximation is a commonly occurring problem in many computer vision and machine learning applications. There are two common ways of optimizing the resulting models. Either the set of matrices with a given rank can be explicitly parametrized using a bilinear factorization, or low rank can be implicitly enforced using regularization terms penalizing non-zero singular values. While the former approach results in differentiable problems that can be efficiently optimized using local quadratic approximation, the latter is typically not differentiable (sometimes even discontinuous) and req"},"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":"1811.11088","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T16:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"1a670e85882685893e6ae9b7b0be9122ed72663102bfc8e963c40c9a06985d6b","abstract_canon_sha256":"8d1374f5c320091b828b0af3528de55b920f08e2219ebde129b6500b950a7fe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:57.810839Z","signature_b64":"eun/9Ju/88zyTcDuwRBJcSGgYXwXzvqMqRevz2NVesyXZw2zoAydQdnjQ1JjSb1427zoSyBx2FFQVCJZNVIiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e7d8ede3afa247db75c9b2ee2a9f4201202cfb08170c7ace6fbc0a76ea9a834","last_reissued_at":"2026-05-17T23:39:57.810338Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:57.810338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilinear Parameterization For Differentiable Rank-Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anders Heyden, Carl Olsson, Marcus Valtonen \\\"Ornhag","submitted_at":"2018-11-27T16:48:11Z","abstract_excerpt":"Low rank approximation is a commonly occurring problem in many computer vision and machine learning applications. There are two common ways of optimizing the resulting models. Either the set of matrices with a given rank can be explicitly parametrized using a bilinear factorization, or low rank can be implicitly enforced using regularization terms penalizing non-zero singular values. While the former approach results in differentiable problems that can be efficiently optimized using local quadratic approximation, the latter is typically not differentiable (sometimes even discontinuous) and req"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11088","kind":"arxiv","version":3},"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":"1811.11088","created_at":"2026-05-17T23:39:57.810427+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11088v3","created_at":"2026-05-17T23:39:57.810427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11088","created_at":"2026-05-17T23:39:57.810427+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZ6Y5XR27ISH","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZ6Y5XR27ISH3N24","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZ6Y5XR2","created_at":"2026-05-18T12:32:56.356000+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/TZ6Y5XR27ISH3N24TMXOFKPUEA","json":"https://pith.science/pith/TZ6Y5XR27ISH3N24TMXOFKPUEA.json","graph_json":"https://pith.science/api/pith-number/TZ6Y5XR27ISH3N24TMXOFKPUEA/graph.json","events_json":"https://pith.science/api/pith-number/TZ6Y5XR27ISH3N24TMXOFKPUEA/events.json","paper":"https://pith.science/paper/TZ6Y5XR2"},"agent_actions":{"view_html":"https://pith.science/pith/TZ6Y5XR27ISH3N24TMXOFKPUEA","download_json":"https://pith.science/pith/TZ6Y5XR27ISH3N24TMXOFKPUEA.json","view_paper":"https://pith.science/paper/TZ6Y5XR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11088&json=true","fetch_graph":"https://pith.science/api/pith-number/TZ6Y5XR27ISH3N24TMXOFKPUEA/graph.json","fetch_events":"https://pith.science/api/pith-number/TZ6Y5XR27ISH3N24TMXOFKPUEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZ6Y5XR27ISH3N24TMXOFKPUEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZ6Y5XR27ISH3N24TMXOFKPUEA/action/storage_attestation","attest_author":"https://pith.science/pith/TZ6Y5XR27ISH3N24TMXOFKPUEA/action/author_attestation","sign_citation":"https://pith.science/pith/TZ6Y5XR27ISH3N24TMXOFKPUEA/action/citation_signature","submit_replication":"https://pith.science/pith/TZ6Y5XR27ISH3N24TMXOFKPUEA/action/replication_record"}},"created_at":"2026-05-17T23:39:57.810427+00:00","updated_at":"2026-05-17T23:39:57.810427+00:00"}