{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FIDH2UG4FCD55X7FYO4T3DF3BY","short_pith_number":"pith:FIDH2UG4","schema_version":"1.0","canonical_sha256":"2a067d50dc2887dedfe5c3b93d8cbb0e385b2ce47034b49ef45d0c79b77bdb70","source":{"kind":"arxiv","id":"2503.10993","version":1},"attestation_state":"computed","paper":{"title":"Riemannian Geometric-based Meta Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jang-Hwan Choi, Juneyoung Park, Tae-Joon Kim, YuMi Lee","submitted_at":"2025-03-14T01:34:55Z","abstract_excerpt":"Meta-learning, or \"learning to learn,\" aims to enable models to quickly adapt to new tasks with minimal data. While traditional methods like Model-Agnostic Meta-Learning (MAML) optimize parameters in Euclidean space, they often struggle to capture complex learning dynamics, particularly in few-shot learning scenarios. To address this limitation, we propose Stiefel-MAML, which integrates Riemannian geometry by optimizing within the Stiefel manifold, a space that naturally enforces orthogonality constraints. By leveraging the geometric structure of the Stiefel manifold, we improve parameter expr"},"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":"2503.10993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-14T01:34:55Z","cross_cats_sorted":[],"title_canon_sha256":"522a00785eec771ae95e1e9a2e1378c399943fb837bd4e3e2ba2f1249336ea2f","abstract_canon_sha256":"85dcab112993c6dbe986140e96b8bde9c8cc0e5c911a71dfa228bf86be276ce8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:09.722696Z","signature_b64":"DUEAPXeROCmnOGVrK1/FEtHSJEiiTAZj6rZg+XWwKfggwU+j3V0j21fxg+Xz+FZqe8dnShl51nVGqQ87SqCeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a067d50dc2887dedfe5c3b93d8cbb0e385b2ce47034b49ef45d0c79b77bdb70","last_reissued_at":"2026-07-05T10:31:09.721855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:09.721855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Riemannian Geometric-based Meta Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jang-Hwan Choi, Juneyoung Park, Tae-Joon Kim, YuMi Lee","submitted_at":"2025-03-14T01:34:55Z","abstract_excerpt":"Meta-learning, or \"learning to learn,\" aims to enable models to quickly adapt to new tasks with minimal data. While traditional methods like Model-Agnostic Meta-Learning (MAML) optimize parameters in Euclidean space, they often struggle to capture complex learning dynamics, particularly in few-shot learning scenarios. To address this limitation, we propose Stiefel-MAML, which integrates Riemannian geometry by optimizing within the Stiefel manifold, a space that naturally enforces orthogonality constraints. By leveraging the geometric structure of the Stiefel manifold, we improve parameter expr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10993","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.10993/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2503.10993","created_at":"2026-07-05T10:31:09.721954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10993v1","created_at":"2026-07-05T10:31:09.721954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10993","created_at":"2026-07-05T10:31:09.721954+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIDH2UG4FCD5","created_at":"2026-07-05T10:31:09.721954+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIDH2UG4FCD55X7F","created_at":"2026-07-05T10:31:09.721954+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIDH2UG4","created_at":"2026-07-05T10:31:09.721954+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/FIDH2UG4FCD55X7FYO4T3DF3BY","json":"https://pith.science/pith/FIDH2UG4FCD55X7FYO4T3DF3BY.json","graph_json":"https://pith.science/api/pith-number/FIDH2UG4FCD55X7FYO4T3DF3BY/graph.json","events_json":"https://pith.science/api/pith-number/FIDH2UG4FCD55X7FYO4T3DF3BY/events.json","paper":"https://pith.science/paper/FIDH2UG4"},"agent_actions":{"view_html":"https://pith.science/pith/FIDH2UG4FCD55X7FYO4T3DF3BY","download_json":"https://pith.science/pith/FIDH2UG4FCD55X7FYO4T3DF3BY.json","view_paper":"https://pith.science/paper/FIDH2UG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10993&json=true","fetch_graph":"https://pith.science/api/pith-number/FIDH2UG4FCD55X7FYO4T3DF3BY/graph.json","fetch_events":"https://pith.science/api/pith-number/FIDH2UG4FCD55X7FYO4T3DF3BY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIDH2UG4FCD55X7FYO4T3DF3BY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIDH2UG4FCD55X7FYO4T3DF3BY/action/storage_attestation","attest_author":"https://pith.science/pith/FIDH2UG4FCD55X7FYO4T3DF3BY/action/author_attestation","sign_citation":"https://pith.science/pith/FIDH2UG4FCD55X7FYO4T3DF3BY/action/citation_signature","submit_replication":"https://pith.science/pith/FIDH2UG4FCD55X7FYO4T3DF3BY/action/replication_record"}},"created_at":"2026-07-05T10:31:09.721954+00:00","updated_at":"2026-07-05T10:31:09.721954+00:00"}