{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FYEIGEVMUVBKMUL5ZAC2FLHDJG","short_pith_number":"pith:FYEIGEVM","schema_version":"1.0","canonical_sha256":"2e088312aca542a6517dc805a2ace3498375bad442d1b410d904df67d4c30c69","source":{"kind":"arxiv","id":"2412.12374","version":1},"attestation_state":"computed","paper":{"title":"Privacy in Metalearning and Multitask Learning: Modeling and Separations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Adam Smith, Jonathan Ullman, Konstantina Bairaktari, Marika Swanberg, Maryam Aliakbarpour","submitted_at":"2024-12-16T22:07:33Z","abstract_excerpt":"Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop individually. The goals of personalization are captured in a variety of formal frameworks, such as multitask learning and metalearning. Combining data for model personalization poses risks for privacy because the output of an individual's model can depend on the data of other individuals. In this work we undertake a systematic study of differentially private personalized learning. Our first main contribution is to constru"},"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":"2412.12374","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T22:07:33Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"ce33f4b73d052dd077c59e2c8bd4c216441a83fddca209113b5f69d6876391f0","abstract_canon_sha256":"176ce9ace7ed1e32653054a5f7c419b7b103cc1fd2fc66e513be8f99fe9af8f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:37.838828Z","signature_b64":"RYyoLDHNIqfAb8GYeLbNnDFgmF7dB4+C+H2zev6HCSGf/00rEFZy99tiV2dinQErwK3DjCstaspKEFAK0acwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e088312aca542a6517dc805a2ace3498375bad442d1b410d904df67d4c30c69","last_reissued_at":"2026-07-05T09:50:37.838332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:37.838332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy in Metalearning and Multitask Learning: Modeling and Separations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Adam Smith, Jonathan Ullman, Konstantina Bairaktari, Marika Swanberg, Maryam Aliakbarpour","submitted_at":"2024-12-16T22:07:33Z","abstract_excerpt":"Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop individually. The goals of personalization are captured in a variety of formal frameworks, such as multitask learning and metalearning. Combining data for model personalization poses risks for privacy because the output of an individual's model can depend on the data of other individuals. In this work we undertake a systematic study of differentially private personalized learning. Our first main contribution is to constru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12374","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/2412.12374/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":"2412.12374","created_at":"2026-07-05T09:50:37.838388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12374v1","created_at":"2026-07-05T09:50:37.838388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12374","created_at":"2026-07-05T09:50:37.838388+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYEIGEVMUVBK","created_at":"2026-07-05T09:50:37.838388+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYEIGEVMUVBKMUL5","created_at":"2026-07-05T09:50:37.838388+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYEIGEVM","created_at":"2026-07-05T09:50:37.838388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17895","citing_title":"Lower Bounds for Public-Private Learning under Distribution Shift","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG","json":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG.json","graph_json":"https://pith.science/api/pith-number/FYEIGEVMUVBKMUL5ZAC2FLHDJG/graph.json","events_json":"https://pith.science/api/pith-number/FYEIGEVMUVBKMUL5ZAC2FLHDJG/events.json","paper":"https://pith.science/paper/FYEIGEVM"},"agent_actions":{"view_html":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG","download_json":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG.json","view_paper":"https://pith.science/paper/FYEIGEVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12374&json=true","fetch_graph":"https://pith.science/api/pith-number/FYEIGEVMUVBKMUL5ZAC2FLHDJG/graph.json","fetch_events":"https://pith.science/api/pith-number/FYEIGEVMUVBKMUL5ZAC2FLHDJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG/action/storage_attestation","attest_author":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG/action/author_attestation","sign_citation":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG/action/citation_signature","submit_replication":"https://pith.science/pith/FYEIGEVMUVBKMUL5ZAC2FLHDJG/action/replication_record"}},"created_at":"2026-07-05T09:50:37.838388+00:00","updated_at":"2026-07-05T09:50:37.838388+00:00"}