{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RPEVMU65XT6AOMPXUH5YGRB3CB","short_pith_number":"pith:RPEVMU65","schema_version":"1.0","canonical_sha256":"8bc95653ddbcfc0731f7a1fb83443b107d9a97d6a8095b2ac6df7924adb6a7f6","source":{"kind":"arxiv","id":"2312.13978","version":2},"attestation_state":"computed","paper":{"title":"Metalearning with Very Few Samples Per Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Adam Smith, Gavin Brown, Jonathan Ullman, Konstantina Bairaktari, Maryam Aliakbarpour, Nathan Srebro","submitted_at":"2023-12-21T16:06:44Z","abstract_excerpt":"Metalearning and multitask learning are two frameworks for solving a group of related learning tasks more efficiently than we could hope to solve each of the individual tasks on their own. In multitask learning, we are given a fixed set of related learning tasks and need to output one accurate model per task, whereas in metalearning we are given tasks that are drawn i.i.d. from a metadistribution and need to output some common information that can be easily specialized to new tasks from the metadistribution.\n  We consider a binary classification setting where tasks are related by a shared repr"},"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":"2312.13978","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T16:06:44Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"fe613bf9fb92b29799a82dd01e9c08f6a663544bf4f9325ac4a45a99742bd747","abstract_canon_sha256":"1dc05c7669e687f4ad7ab065579499a939e9c098ede898c8e168ac4a321e79d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:49.615133Z","signature_b64":"aMlKsvRPYInaZ81trHNIJ6dO10ADu7BsH3Ra74qJO12JqXAOz1Zs5ATFXIYbjVVcojkS9tRd7s15ErdKc6uDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bc95653ddbcfc0731f7a1fb83443b107d9a97d6a8095b2ac6df7924adb6a7f6","last_reissued_at":"2026-07-05T08:02:49.614661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:49.614661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metalearning with Very Few Samples Per Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Adam Smith, Gavin Brown, Jonathan Ullman, Konstantina Bairaktari, Maryam Aliakbarpour, Nathan Srebro","submitted_at":"2023-12-21T16:06:44Z","abstract_excerpt":"Metalearning and multitask learning are two frameworks for solving a group of related learning tasks more efficiently than we could hope to solve each of the individual tasks on their own. In multitask learning, we are given a fixed set of related learning tasks and need to output one accurate model per task, whereas in metalearning we are given tasks that are drawn i.i.d. from a metadistribution and need to output some common information that can be easily specialized to new tasks from the metadistribution.\n  We consider a binary classification setting where tasks are related by a shared repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13978","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/2312.13978/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":"2312.13978","created_at":"2026-07-05T08:02:49.614714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13978v2","created_at":"2026-07-05T08:02:49.614714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13978","created_at":"2026-07-05T08:02:49.614714+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPEVMU65XT6A","created_at":"2026-07-05T08:02:49.614714+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPEVMU65XT6AOMPX","created_at":"2026-07-05T08:02:49.614714+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPEVMU65","created_at":"2026-07-05T08:02:49.614714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17898","citing_title":"On the ERM Principle in Meta-Learning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB","json":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB.json","graph_json":"https://pith.science/api/pith-number/RPEVMU65XT6AOMPXUH5YGRB3CB/graph.json","events_json":"https://pith.science/api/pith-number/RPEVMU65XT6AOMPXUH5YGRB3CB/events.json","paper":"https://pith.science/paper/RPEVMU65"},"agent_actions":{"view_html":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB","download_json":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB.json","view_paper":"https://pith.science/paper/RPEVMU65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13978&json=true","fetch_graph":"https://pith.science/api/pith-number/RPEVMU65XT6AOMPXUH5YGRB3CB/graph.json","fetch_events":"https://pith.science/api/pith-number/RPEVMU65XT6AOMPXUH5YGRB3CB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB/action/storage_attestation","attest_author":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB/action/author_attestation","sign_citation":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB/action/citation_signature","submit_replication":"https://pith.science/pith/RPEVMU65XT6AOMPXUH5YGRB3CB/action/replication_record"}},"created_at":"2026-07-05T08:02:49.614714+00:00","updated_at":"2026-07-05T08:02:49.614714+00:00"}