{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U5JBDH66GJFILPHHDWXZ22UTW7","short_pith_number":"pith:U5JBDH66","schema_version":"1.0","canonical_sha256":"a752119fde324a85bce71daf9d6a93b7f3f4e3159faf940f2e8069506aeaf2af","source":{"kind":"arxiv","id":"1807.05960","version":3},"attestation_state":"computed","paper":{"title":"Meta-Learning with Latent Embedding Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Raia Hadsell, Razvan Pascanu, Simon Osindero","submitted_at":"2018-07-16T16:35:29Z","abstract_excerpt":"Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter spaces in extreme low-data regimes. We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space. The resulting approach, latent embedding optimization (LEO), decouples the gradient-based adaptation 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":"1807.05960","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T16:35:29Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"53e38baab80123c5d9625148ecfa2c5a26b4c4ed184a42afc0bfcf6bd66d0e1a","abstract_canon_sha256":"7dd20a7c97ea5b2d9cd7f57e3db60085deb5af1c76400ecf71f1d8e103346442"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:27.571083Z","signature_b64":"Ka2O9wjO560Czjw2gRL+LzjFS3HkZH28UG9JwT+7DXlL1PX0JEZKy54dMLn7ol10j1kXchooWIvBPKM+6cxyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a752119fde324a85bce71daf9d6a93b7f3f4e3159faf940f2e8069506aeaf2af","last_reissued_at":"2026-05-17T23:50:27.570423Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:27.570423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning with Latent Embedding Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Raia Hadsell, Razvan Pascanu, Simon Osindero","submitted_at":"2018-07-16T16:35:29Z","abstract_excerpt":"Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter spaces in extreme low-data regimes. We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space. The resulting approach, latent embedding optimization (LEO), decouples the gradient-based adaptation pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05960","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":"1807.05960","created_at":"2026-05-17T23:50:27.570512+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.05960v3","created_at":"2026-05-17T23:50:27.570512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05960","created_at":"2026-05-17T23:50:27.570512+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5JBDH66GJFI","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5JBDH66GJFILPHH","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5JBDH66","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.11415","citing_title":"Few-Shot Video Classification via Temporal Alignment","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05415","citing_title":"Learning to learn with quantum neural networks via classical neural networks","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14145","citing_title":"Rethinking the Good Enough Embedding for Easy Few-Shot Learning","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13672","citing_title":"SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18267","citing_title":"MARCO: Navigating the Unseen Space of Semantic Correspondence","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7","json":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7.json","graph_json":"https://pith.science/api/pith-number/U5JBDH66GJFILPHHDWXZ22UTW7/graph.json","events_json":"https://pith.science/api/pith-number/U5JBDH66GJFILPHHDWXZ22UTW7/events.json","paper":"https://pith.science/paper/U5JBDH66"},"agent_actions":{"view_html":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7","download_json":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7.json","view_paper":"https://pith.science/paper/U5JBDH66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.05960&json=true","fetch_graph":"https://pith.science/api/pith-number/U5JBDH66GJFILPHHDWXZ22UTW7/graph.json","fetch_events":"https://pith.science/api/pith-number/U5JBDH66GJFILPHHDWXZ22UTW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7/action/storage_attestation","attest_author":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7/action/author_attestation","sign_citation":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7/action/citation_signature","submit_replication":"https://pith.science/pith/U5JBDH66GJFILPHHDWXZ22UTW7/action/replication_record"}},"created_at":"2026-05-17T23:50:27.570512+00:00","updated_at":"2026-05-17T23:50:27.570512+00:00"}