{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HQ6DIQYZ3C6VW5POVW3SA2CKPH","short_pith_number":"pith:HQ6DIQYZ","schema_version":"1.0","canonical_sha256":"3c3c344319d8bd5b75eeadb720684a79cbe26d0971167b6c5bc98cb3e8ffe9d1","source":{"kind":"arxiv","id":"1801.05558","version":3},"attestation_state":"computed","paper":{"title":"Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Seungjin Choi, Yoonho Lee","submitted_at":"2018-01-17T05:34:08Z","abstract_excerpt":"Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during meta-testing. Our primary contribution is the {\\em MT-net}, which enables the meta-learner to learn on each layer's activation space a subspace that the task-specific learner performs gradient descent on. Additionally, a task-specific learner of an {\\em MT-net} performs gradient descent with respect to a meta-learned distance metric, which warps the activation space t"},"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":"1801.05558","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-17T05:34:08Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"a5588b9138b55855f099d561d0670c1181a2e3b30d4a22067226918b4cd06b07","abstract_canon_sha256":"dad0dad8ad79e746e9f2b1547cb13dd2b5dee91a8c0a2ece48948fa9135ff849"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:15.430069Z","signature_b64":"PQm8S8HT4U7ZAHjQNBQRa6nfp/WNWIVUMpAoyQCfMfhYXo2vUa+THyBefd3uxrsSu9jnq7plV6xaLtLJMc49Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c3c344319d8bd5b75eeadb720684a79cbe26d0971167b6c5bc98cb3e8ffe9d1","last_reissued_at":"2026-05-18T00:13:15.429280Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:15.429280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Seungjin Choi, Yoonho Lee","submitted_at":"2018-01-17T05:34:08Z","abstract_excerpt":"Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during meta-testing. Our primary contribution is the {\\em MT-net}, which enables the meta-learner to learn on each layer's activation space a subspace that the task-specific learner performs gradient descent on. Additionally, a task-specific learner of an {\\em MT-net} performs gradient descent with respect to a meta-learned distance metric, which warps the activation space t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05558","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":"1801.05558","created_at":"2026-05-18T00:13:15.429412+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.05558v3","created_at":"2026-05-18T00:13:15.429412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05558","created_at":"2026-05-18T00:13:15.429412+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQ6DIQYZ3C6V","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQ6DIQYZ3C6VW5PO","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQ6DIQYZ","created_at":"2026-05-18T12:32:28.185984+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/HQ6DIQYZ3C6VW5POVW3SA2CKPH","json":"https://pith.science/pith/HQ6DIQYZ3C6VW5POVW3SA2CKPH.json","graph_json":"https://pith.science/api/pith-number/HQ6DIQYZ3C6VW5POVW3SA2CKPH/graph.json","events_json":"https://pith.science/api/pith-number/HQ6DIQYZ3C6VW5POVW3SA2CKPH/events.json","paper":"https://pith.science/paper/HQ6DIQYZ"},"agent_actions":{"view_html":"https://pith.science/pith/HQ6DIQYZ3C6VW5POVW3SA2CKPH","download_json":"https://pith.science/pith/HQ6DIQYZ3C6VW5POVW3SA2CKPH.json","view_paper":"https://pith.science/paper/HQ6DIQYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.05558&json=true","fetch_graph":"https://pith.science/api/pith-number/HQ6DIQYZ3C6VW5POVW3SA2CKPH/graph.json","fetch_events":"https://pith.science/api/pith-number/HQ6DIQYZ3C6VW5POVW3SA2CKPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQ6DIQYZ3C6VW5POVW3SA2CKPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQ6DIQYZ3C6VW5POVW3SA2CKPH/action/storage_attestation","attest_author":"https://pith.science/pith/HQ6DIQYZ3C6VW5POVW3SA2CKPH/action/author_attestation","sign_citation":"https://pith.science/pith/HQ6DIQYZ3C6VW5POVW3SA2CKPH/action/citation_signature","submit_replication":"https://pith.science/pith/HQ6DIQYZ3C6VW5POVW3SA2CKPH/action/replication_record"}},"created_at":"2026-05-18T00:13:15.429412+00:00","updated_at":"2026-05-18T00:13:15.429412+00:00"}