{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZDLKFQVTMPXF6QOKRWL34DDDBH","short_pith_number":"pith:ZDLKFQVT","schema_version":"1.0","canonical_sha256":"c8d6a2c2b363ee5f41ca8d97be0c6309ca38f51187cb10a96e19ce94f74415f2","source":{"kind":"arxiv","id":"1811.03604","version":2},"attestation_state":"computed","paper":{"title":"Federated Learning for Mobile Keyboard Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Hard, Chlo\\'e Kiddon, Daniel Ramage, Fran\\c{c}oise Beaufays, Hubert Eichner, Kanishka Rao, Rajiv Mathews, Sean Augenstein, Swaroop Ramaswamy","submitted_at":"2018-11-08T18:37:03Z","abstract_excerpt":"We train a recurrent neural network language model using a distributed, on-device learning framework called federated learning for the purpose of next-word prediction in a virtual keyboard for smartphones. Server-based training using stochastic gradient descent is compared with training on client devices using the Federated Averaging algorithm. The federated algorithm, which enables training on a higher-quality dataset for this use case, is shown to achieve better prediction recall. This work demonstrates the feasibility and benefit of training language models on client devices without exporti"},"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":"1811.03604","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-11-08T18:37:03Z","cross_cats_sorted":[],"title_canon_sha256":"7f7bdef9f6d2b7dc76962f6b39d7a49487f37dc9df6c192cbed92aef42699c60","abstract_canon_sha256":"6716efb0b90b8f544f8816164414217841fa92f7a93bc76c83a74547e55556c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:21.787992Z","signature_b64":"r/xQ3ecA/WWSAN8ftHKgVvm8zo5/hHDQJDtA2qVsoh18aS0KjgZYXPoEkJuTTdYuQK3moZdKw6X9T6b9KA4GBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8d6a2c2b363ee5f41ca8d97be0c6309ca38f51187cb10a96e19ce94f74415f2","last_reissued_at":"2026-05-17T23:52:21.787540Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:21.787540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning for Mobile Keyboard Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Hard, Chlo\\'e Kiddon, Daniel Ramage, Fran\\c{c}oise Beaufays, Hubert Eichner, Kanishka Rao, Rajiv Mathews, Sean Augenstein, Swaroop Ramaswamy","submitted_at":"2018-11-08T18:37:03Z","abstract_excerpt":"We train a recurrent neural network language model using a distributed, on-device learning framework called federated learning for the purpose of next-word prediction in a virtual keyboard for smartphones. Server-based training using stochastic gradient descent is compared with training on client devices using the Federated Averaging algorithm. The federated algorithm, which enables training on a higher-quality dataset for this use case, is shown to achieve better prediction recall. This work demonstrates the feasibility and benefit of training language models on client devices without exporti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03604","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":""},"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":"1811.03604","created_at":"2026-05-17T23:52:21.787606+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.03604v2","created_at":"2026-05-17T23:52:21.787606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03604","created_at":"2026-05-17T23:52:21.787606+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDLKFQVTMPXF","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDLKFQVTMPXF6QOK","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDLKFQVT","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":15,"sample":[{"citing_arxiv_id":"2302.05545","citing_title":"Privacy Against Agnostic Inference Attacks in Vertical Federated Learning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2407.09658","citing_title":"BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2410.15368","citing_title":"Tighter Performance Theory of FedExProx","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13647","citing_title":"REVERB-FL: Server-Side Adversarial and Reserve-Enhanced Federated Learning for Robust Audio Classification","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15885","citing_title":"FedEDAuth -- Federated Embedding Distribution Authentication for Counterfeit IC Detection","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18020","citing_title":"Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19291","citing_title":"Factor Augmented High-Dimensional SGD","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2506.06742","citing_title":"LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2510.25372","citing_title":"Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2601.15127","citing_title":"DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2602.06489","citing_title":"Simulating Word Suggestion Usage in Mobile Typing to Guide Intelligent Text Entry Design","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00011","citing_title":"FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14159","citing_title":"HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29328","citing_title":"Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26741","citing_title":"Analytically Characterized Optimal Power Control for Signal-Level-Integrated Sensing, Computing and Communication in Federated Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08992","citing_title":"When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00970","citing_title":"Split and Aggregation Learning for Foundation Models Over Mobile Embodied AI Network (MEAN): A Comprehensive Survey","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10615","citing_title":"Unified Compression Algorithm for Distributed Nonconvex Optimization: Generalized to 1-Bit, Saturation, and Bounded Noise","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09489","citing_title":"XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09276","citing_title":"Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH","json":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH.json","graph_json":"https://pith.science/api/pith-number/ZDLKFQVTMPXF6QOKRWL34DDDBH/graph.json","events_json":"https://pith.science/api/pith-number/ZDLKFQVTMPXF6QOKRWL34DDDBH/events.json","paper":"https://pith.science/paper/ZDLKFQVT"},"agent_actions":{"view_html":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH","download_json":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH.json","view_paper":"https://pith.science/paper/ZDLKFQVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.03604&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDLKFQVTMPXF6QOKRWL34DDDBH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDLKFQVTMPXF6QOKRWL34DDDBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH/action/storage_attestation","attest_author":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH/action/author_attestation","sign_citation":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH/action/citation_signature","submit_replication":"https://pith.science/pith/ZDLKFQVTMPXF6QOKRWL34DDDBH/action/replication_record"}},"created_at":"2026-05-17T23:52:21.787606+00:00","updated_at":"2026-05-17T23:52:21.787606+00:00"}