{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VGZLWB457OX2AOR7TQ5WWASTJZ","short_pith_number":"pith:VGZLWB45","schema_version":"1.0","canonical_sha256":"a9b2bb079dfbafa03a3f9c3b6b02534e74b224ab26b0b23f9b48410420cba7aa","source":{"kind":"arxiv","id":"1910.10252","version":1},"attestation_state":"computed","paper":{"title":"Federated Evaluation of On-device Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chlo\\'e Kiddon, Daniel Ramage, Fran\\c{c}oise Beaufays, Hubert Eichner, Kangkang Wang, Rajiv Mathews","submitted_at":"2019-10-22T22:16:15Z","abstract_excerpt":"Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers. In this work, we describe methods to extend the federation framework to evaluate strategies for personalization of global models. We present tools to analyze the effects of personalization and evaluate conditions under which personalization yields desirable models. We report on our experiments personalizing a language model for a virtual keyboard for smartphones with a population of tens of millions of users. We show that a significant fract"},"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":"1910.10252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-22T22:16:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"293b91a9ba98956afde7abb265f5d5224dfff9068ee1ac4ab3cb7d152332580c","abstract_canon_sha256":"bdd3a9d6d9a695676099ba73e6806f56863bafd948053a6072e609607e4820ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:23.117074Z","signature_b64":"W9o+LIWGtkTNG1cabIJLRYehLV9v7dKobJSNT5wB4LRJrHfgYgDdVnQtFihBPwEytOnb8zoMm52fNqVxiL5NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9b2bb079dfbafa03a3f9c3b6b02534e74b224ab26b0b23f9b48410420cba7aa","last_reissued_at":"2026-07-05T00:14:23.116650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:23.116650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Evaluation of On-device Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chlo\\'e Kiddon, Daniel Ramage, Fran\\c{c}oise Beaufays, Hubert Eichner, Kangkang Wang, Rajiv Mathews","submitted_at":"2019-10-22T22:16:15Z","abstract_excerpt":"Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers. In this work, we describe methods to extend the federation framework to evaluate strategies for personalization of global models. We present tools to analyze the effects of personalization and evaluate conditions under which personalization yields desirable models. We report on our experiments personalizing a language model for a virtual keyboard for smartphones with a population of tens of millions of users. We show that a significant fract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10252","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/1910.10252/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":"1910.10252","created_at":"2026-07-05T00:14:23.116707+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.10252v1","created_at":"2026-07-05T00:14:23.116707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10252","created_at":"2026-07-05T00:14:23.116707+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGZLWB457OX2","created_at":"2026-07-05T00:14:23.116707+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGZLWB457OX2AOR7","created_at":"2026-07-05T00:14:23.116707+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGZLWB45","created_at":"2026-07-05T00:14:23.116707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10678","citing_title":"FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ","json":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ.json","graph_json":"https://pith.science/api/pith-number/VGZLWB457OX2AOR7TQ5WWASTJZ/graph.json","events_json":"https://pith.science/api/pith-number/VGZLWB457OX2AOR7TQ5WWASTJZ/events.json","paper":"https://pith.science/paper/VGZLWB45"},"agent_actions":{"view_html":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ","download_json":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ.json","view_paper":"https://pith.science/paper/VGZLWB45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.10252&json=true","fetch_graph":"https://pith.science/api/pith-number/VGZLWB457OX2AOR7TQ5WWASTJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VGZLWB457OX2AOR7TQ5WWASTJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ/action/storage_attestation","attest_author":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ/action/author_attestation","sign_citation":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ/action/citation_signature","submit_replication":"https://pith.science/pith/VGZLWB457OX2AOR7TQ5WWASTJZ/action/replication_record"}},"created_at":"2026-07-05T00:14:23.116707+00:00","updated_at":"2026-07-05T00:14:23.116707+00:00"}