{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QHAZD3H2D2I4ZJCBUBJRSKUBFX","short_pith_number":"pith:QHAZD3H2","schema_version":"1.0","canonical_sha256":"81c191ecfa1e91cca441a053192a812dc18d5e088b625fad67cca81be2c00f5d","source":{"kind":"arxiv","id":"2011.14048","version":2},"attestation_state":"computed","paper":{"title":"Is Support Set Diversity Necessary for Meta-Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amrith Setlur, Oscar Li, Virginia Smith","submitted_at":"2020-11-28T02:28:42Z","abstract_excerpt":"Meta-learning is a popular framework for learning with limited data in which an algorithm is produced by training over multiple few-shot learning tasks. For classification problems, these tasks are typically constructed by sampling a small number of support and query examples from a subset of the classes. While conventional wisdom is that task diversity should improve the performance of meta-learning, in this work we find evidence to the contrary: we propose a modification to traditional meta-learning approaches in which we keep the support sets fixed across tasks, thus reducing task diversity"},"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":"2011.14048","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-28T02:28:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"147fe158e5fd0c9a83b3f08ac4f14b610f1ff6ec9b5879ac076799020bb595ff","abstract_canon_sha256":"3335dc8e545664d0593279694fdccef2d7110fd1ef067d10e71b5fac215062ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:33.535154Z","signature_b64":"ab7MGLnxJh9sUKbf2dvyuVEKrzFfD/7S/Awd6s3rLQmEMtVEuPsB1863fQN9yt73ELxppTTNUOPa+KA5VPFlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81c191ecfa1e91cca441a053192a812dc18d5e088b625fad67cca81be2c00f5d","last_reissued_at":"2026-07-05T03:20:33.534674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:33.534674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Support Set Diversity Necessary for Meta-Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amrith Setlur, Oscar Li, Virginia Smith","submitted_at":"2020-11-28T02:28:42Z","abstract_excerpt":"Meta-learning is a popular framework for learning with limited data in which an algorithm is produced by training over multiple few-shot learning tasks. For classification problems, these tasks are typically constructed by sampling a small number of support and query examples from a subset of the classes. While conventional wisdom is that task diversity should improve the performance of meta-learning, in this work we find evidence to the contrary: we propose a modification to traditional meta-learning approaches in which we keep the support sets fixed across tasks, thus reducing task diversity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14048","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/2011.14048/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":"2011.14048","created_at":"2026-07-05T03:20:33.534730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14048v2","created_at":"2026-07-05T03:20:33.534730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14048","created_at":"2026-07-05T03:20:33.534730+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHAZD3H2D2I4","created_at":"2026-07-05T03:20:33.534730+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHAZD3H2D2I4ZJCB","created_at":"2026-07-05T03:20:33.534730+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHAZD3H2","created_at":"2026-07-05T03:20:33.534730+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/QHAZD3H2D2I4ZJCBUBJRSKUBFX","json":"https://pith.science/pith/QHAZD3H2D2I4ZJCBUBJRSKUBFX.json","graph_json":"https://pith.science/api/pith-number/QHAZD3H2D2I4ZJCBUBJRSKUBFX/graph.json","events_json":"https://pith.science/api/pith-number/QHAZD3H2D2I4ZJCBUBJRSKUBFX/events.json","paper":"https://pith.science/paper/QHAZD3H2"},"agent_actions":{"view_html":"https://pith.science/pith/QHAZD3H2D2I4ZJCBUBJRSKUBFX","download_json":"https://pith.science/pith/QHAZD3H2D2I4ZJCBUBJRSKUBFX.json","view_paper":"https://pith.science/paper/QHAZD3H2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14048&json=true","fetch_graph":"https://pith.science/api/pith-number/QHAZD3H2D2I4ZJCBUBJRSKUBFX/graph.json","fetch_events":"https://pith.science/api/pith-number/QHAZD3H2D2I4ZJCBUBJRSKUBFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHAZD3H2D2I4ZJCBUBJRSKUBFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHAZD3H2D2I4ZJCBUBJRSKUBFX/action/storage_attestation","attest_author":"https://pith.science/pith/QHAZD3H2D2I4ZJCBUBJRSKUBFX/action/author_attestation","sign_citation":"https://pith.science/pith/QHAZD3H2D2I4ZJCBUBJRSKUBFX/action/citation_signature","submit_replication":"https://pith.science/pith/QHAZD3H2D2I4ZJCBUBJRSKUBFX/action/replication_record"}},"created_at":"2026-07-05T03:20:33.534730+00:00","updated_at":"2026-07-05T03:20:33.534730+00:00"}