{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KLWF6F24B3K7RY6QQG33YEO52C","short_pith_number":"pith:KLWF6F24","schema_version":"1.0","canonical_sha256":"52ec5f175c0ed5f8e3d081b7bc11ddd0849764bdae9948e8130cc8b3c2965b95","source":{"kind":"arxiv","id":"1703.02992","version":1},"attestation_state":"computed","paper":{"title":"A Manifold Approach to Learning Mutually Orthogonal Subspaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francisco Garcia, Sridhar Mahadevan, Stephen Giguere","submitted_at":"2017-03-08T19:08:28Z","abstract_excerpt":"Although many machine learning algorithms involve learning subspaces with particular characteristics, optimizing a parameter matrix that is constrained to represent a subspace can be challenging. One solution is to use Riemannian optimization methods that enforce such constraints implicitly, leveraging the fact that the feasible parameter values form a manifold. While Riemannian methods exist for some specific problems, such as learning a single subspace, there are more general subspace constraints that offer additional flexibility when setting up an optimization problem, but have not been for"},"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":"1703.02992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-08T19:08:28Z","cross_cats_sorted":[],"title_canon_sha256":"2750cbd2b065c1c6369e48099e9f90b845a4604d9a463e98b152f6269d0a8d4f","abstract_canon_sha256":"c532a52e0474491055b2763037ec7634c12c0f809eecd93894bbd1500134ffe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:05.104062Z","signature_b64":"KtEZ+yD9Jr/Yok4o7quS/JqOnKpAUAeJytdk7N7AeHpq9BFuzBxpfaF1JtbcddhoHnn51Tk/QMSTD7sYrCvPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52ec5f175c0ed5f8e3d081b7bc11ddd0849764bdae9948e8130cc8b3c2965b95","last_reissued_at":"2026-05-18T00:49:05.103590Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:05.103590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Manifold Approach to Learning Mutually Orthogonal Subspaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francisco Garcia, Sridhar Mahadevan, Stephen Giguere","submitted_at":"2017-03-08T19:08:28Z","abstract_excerpt":"Although many machine learning algorithms involve learning subspaces with particular characteristics, optimizing a parameter matrix that is constrained to represent a subspace can be challenging. One solution is to use Riemannian optimization methods that enforce such constraints implicitly, leveraging the fact that the feasible parameter values form a manifold. While Riemannian methods exist for some specific problems, such as learning a single subspace, there are more general subspace constraints that offer additional flexibility when setting up an optimization problem, but have not been for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02992","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":"1703.02992","created_at":"2026-05-18T00:49:05.103667+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.02992v1","created_at":"2026-05-18T00:49:05.103667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02992","created_at":"2026-05-18T00:49:05.103667+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLWF6F24B3K7","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLWF6F24B3K7RY6Q","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLWF6F24","created_at":"2026-05-18T12:31:24.725408+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/KLWF6F24B3K7RY6QQG33YEO52C","json":"https://pith.science/pith/KLWF6F24B3K7RY6QQG33YEO52C.json","graph_json":"https://pith.science/api/pith-number/KLWF6F24B3K7RY6QQG33YEO52C/graph.json","events_json":"https://pith.science/api/pith-number/KLWF6F24B3K7RY6QQG33YEO52C/events.json","paper":"https://pith.science/paper/KLWF6F24"},"agent_actions":{"view_html":"https://pith.science/pith/KLWF6F24B3K7RY6QQG33YEO52C","download_json":"https://pith.science/pith/KLWF6F24B3K7RY6QQG33YEO52C.json","view_paper":"https://pith.science/paper/KLWF6F24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.02992&json=true","fetch_graph":"https://pith.science/api/pith-number/KLWF6F24B3K7RY6QQG33YEO52C/graph.json","fetch_events":"https://pith.science/api/pith-number/KLWF6F24B3K7RY6QQG33YEO52C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLWF6F24B3K7RY6QQG33YEO52C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLWF6F24B3K7RY6QQG33YEO52C/action/storage_attestation","attest_author":"https://pith.science/pith/KLWF6F24B3K7RY6QQG33YEO52C/action/author_attestation","sign_citation":"https://pith.science/pith/KLWF6F24B3K7RY6QQG33YEO52C/action/citation_signature","submit_replication":"https://pith.science/pith/KLWF6F24B3K7RY6QQG33YEO52C/action/replication_record"}},"created_at":"2026-05-18T00:49:05.103667+00:00","updated_at":"2026-05-18T00:49:05.103667+00:00"}