{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PZHY3DFOVJEVTBQ75UHNBME2R6","short_pith_number":"pith:PZHY3DFO","schema_version":"1.0","canonical_sha256":"7e4f8d8caeaa4959861fed0ed0b09a8fb7abec94a03e0aa8229df67355512be5","source":{"kind":"arxiv","id":"2102.00127","version":1},"attestation_state":"computed","paper":{"title":"On Data Efficiency of Meta-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, Eric Xing, Liam Li, Maruan Al-Shedivat","submitted_at":"2021-01-30T01:44:12Z","abstract_excerpt":"Meta-learning has enabled learning statistical models that can be quickly adapted to new prediction tasks. Motivated by use-cases in personalized federated learning, we study the often overlooked aspect of the modern meta-learning algorithms -- their data efficiency. To shed more light on which methods are more efficient, we use techniques from algorithmic stability to derive bounds on the transfer risk that have important practical implications, indicating how much supervision is needed and how it must be allocated for each method to attain the desired level of generalization. Further, we int"},"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":"2102.00127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-30T01:44:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d5175b3047a2b45972e6ed9d8d0b0b4af005b9c503fd9b4a567801acc510b5c8","abstract_canon_sha256":"718eff19fde37427171b467bb1698f38d532426eac8ea3aa0f56127dea907197"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:50.466023Z","signature_b64":"5Efz2SfdgvCfrlak9kC7eRuc/EY2Mk1NOJI/Cz+QbBa24tNd98wTRAPRmNRoO0dLlrRCM/oqyFE2SxoZy+cbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e4f8d8caeaa4959861fed0ed0b09a8fb7abec94a03e0aa8229df67355512be5","last_reissued_at":"2026-07-05T02:10:50.465569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:50.465569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Data Efficiency of Meta-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, Eric Xing, Liam Li, Maruan Al-Shedivat","submitted_at":"2021-01-30T01:44:12Z","abstract_excerpt":"Meta-learning has enabled learning statistical models that can be quickly adapted to new prediction tasks. Motivated by use-cases in personalized federated learning, we study the often overlooked aspect of the modern meta-learning algorithms -- their data efficiency. To shed more light on which methods are more efficient, we use techniques from algorithmic stability to derive bounds on the transfer risk that have important practical implications, indicating how much supervision is needed and how it must be allocated for each method to attain the desired level of generalization. Further, we int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00127","kind":"arxiv","version":1},"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/2102.00127/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":"2102.00127","created_at":"2026-07-05T02:10:50.465630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.00127v1","created_at":"2026-07-05T02:10:50.465630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00127","created_at":"2026-07-05T02:10:50.465630+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZHY3DFOVJEV","created_at":"2026-07-05T02:10:50.465630+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZHY3DFOVJEVTBQ7","created_at":"2026-07-05T02:10:50.465630+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZHY3DFO","created_at":"2026-07-05T02:10:50.465630+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/PZHY3DFOVJEVTBQ75UHNBME2R6","json":"https://pith.science/pith/PZHY3DFOVJEVTBQ75UHNBME2R6.json","graph_json":"https://pith.science/api/pith-number/PZHY3DFOVJEVTBQ75UHNBME2R6/graph.json","events_json":"https://pith.science/api/pith-number/PZHY3DFOVJEVTBQ75UHNBME2R6/events.json","paper":"https://pith.science/paper/PZHY3DFO"},"agent_actions":{"view_html":"https://pith.science/pith/PZHY3DFOVJEVTBQ75UHNBME2R6","download_json":"https://pith.science/pith/PZHY3DFOVJEVTBQ75UHNBME2R6.json","view_paper":"https://pith.science/paper/PZHY3DFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.00127&json=true","fetch_graph":"https://pith.science/api/pith-number/PZHY3DFOVJEVTBQ75UHNBME2R6/graph.json","fetch_events":"https://pith.science/api/pith-number/PZHY3DFOVJEVTBQ75UHNBME2R6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZHY3DFOVJEVTBQ75UHNBME2R6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZHY3DFOVJEVTBQ75UHNBME2R6/action/storage_attestation","attest_author":"https://pith.science/pith/PZHY3DFOVJEVTBQ75UHNBME2R6/action/author_attestation","sign_citation":"https://pith.science/pith/PZHY3DFOVJEVTBQ75UHNBME2R6/action/citation_signature","submit_replication":"https://pith.science/pith/PZHY3DFOVJEVTBQ75UHNBME2R6/action/replication_record"}},"created_at":"2026-07-05T02:10:50.465630+00:00","updated_at":"2026-07-05T02:10:50.465630+00:00"}