{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2AAQ3FVZYYMUYFMSQ4PJJ67SVN","short_pith_number":"pith:2AAQ3FVZ","schema_version":"1.0","canonical_sha256":"d0010d96b9c6194c1592871e94fbf2ab6d51bd2abecf5c72edd37da0d6687f5e","source":{"kind":"arxiv","id":"1905.05301","version":2},"attestation_state":"computed","paper":{"title":"Hierarchically Structured Meta-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huaxiu Yao, Junzhou Huang, Ying Wei, Zhenhui Li","submitted_at":"2019-05-13T21:56:37Z","abstract_excerpt":"In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally sharing knowledge among tasks. In this paper, based on gradient-based meta-learning, we propose a hierarchically structured meta-learning (HSML) algorithm that explicitly tailors the transferable knowledge to different clusters of tasks. Inspired by the way human beings organize knowledge, we resort to a hierarchical task clustering structure to cluster tasks. A"},"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":"1905.05301","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-13T21:56:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cb6ee43ed28b20c8d4dd265334a11dd3873179fce85ead90210c00803e415dac","abstract_canon_sha256":"6e9415b2d601dc93b608255eafeae029f04d3dfa0dd34fc9109fbb2c541be38c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:36.536746Z","signature_b64":"2aZvpoWQnumRfpX1dn9zuVuyjDuSF9I3BR2I4+FI9RTh6RFXA4qyKuzD8mbGnTiCy7vv5PucS2hopIoAt3MkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0010d96b9c6194c1592871e94fbf2ab6d51bd2abecf5c72edd37da0d6687f5e","last_reissued_at":"2026-07-05T00:19:36.536331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:36.536331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchically Structured Meta-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huaxiu Yao, Junzhou Huang, Ying Wei, Zhenhui Li","submitted_at":"2019-05-13T21:56:37Z","abstract_excerpt":"In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally sharing knowledge among tasks. In this paper, based on gradient-based meta-learning, we propose a hierarchically structured meta-learning (HSML) algorithm that explicitly tailors the transferable knowledge to different clusters of tasks. Inspired by the way human beings organize knowledge, we resort to a hierarchical task clustering structure to cluster tasks. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05301","kind":"arxiv","version":2},"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/1905.05301/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":"1905.05301","created_at":"2026-07-05T00:19:36.536393+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05301v2","created_at":"2026-07-05T00:19:36.536393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05301","created_at":"2026-07-05T00:19:36.536393+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AAQ3FVZYYMU","created_at":"2026-07-05T00:19:36.536393+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AAQ3FVZYYMUYFMS","created_at":"2026-07-05T00:19:36.536393+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AAQ3FVZ","created_at":"2026-07-05T00:19:36.536393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16325","citing_title":"Tailored Forecasting from Short Time Series via Meta-learning","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN","json":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN.json","graph_json":"https://pith.science/api/pith-number/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/graph.json","events_json":"https://pith.science/api/pith-number/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/events.json","paper":"https://pith.science/paper/2AAQ3FVZ"},"agent_actions":{"view_html":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN","download_json":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN.json","view_paper":"https://pith.science/paper/2AAQ3FVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05301&json=true","fetch_graph":"https://pith.science/api/pith-number/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/graph.json","fetch_events":"https://pith.science/api/pith-number/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/action/storage_attestation","attest_author":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/action/author_attestation","sign_citation":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/action/citation_signature","submit_replication":"https://pith.science/pith/2AAQ3FVZYYMUYFMSQ4PJJ67SVN/action/replication_record"}},"created_at":"2026-07-05T00:19:36.536393+00:00","updated_at":"2026-07-05T00:19:36.536393+00:00"}