{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6KBFRPFV3DDRIGHRMIKZSSROED","short_pith_number":"pith:6KBFRPFV","schema_version":"1.0","canonical_sha256":"f28258bcb5d8c71418f16215994a2e20e210bd5a554732260b8bb4d6dd73ddef","source":{"kind":"arxiv","id":"1710.06963","version":3},"attestation_state":"computed","paper":{"title":"Learning Differentially Private Recurrent Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Ramage, H. Brendan McMahan, Kunal Talwar, Li Zhang","submitted_at":"2017-10-18T23:46:57Z","abstract_excerpt":"We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep networks on user-partitioned data and privacy accounting for stochastic gradient descent. In particular, we add user-level privacy protection to the federated averaging algorithm, which makes \"large step\" updates from user-level data. Our work demonstrates that given a dataset with a sufficiently large number of users (a requirement easily met by even small inter"},"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":"1710.06963","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-18T23:46:57Z","cross_cats_sorted":[],"title_canon_sha256":"80339ee51a64ef234c6665554bce3729842336f878d1833e6da762f5c4707c24","abstract_canon_sha256":"bbc393b3fae6e71179131380b7ce262db432f59239dc60f7422a95b636314b64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.379792Z","signature_b64":"peJoPyFXZpmPmjNKEGGuQW6icMtcXzjCUL75GW03FUHoBTwK6/gCSjcITAdnuugbOawasfvuEOP2BjHepz1GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f28258bcb5d8c71418f16215994a2e20e210bd5a554732260b8bb4d6dd73ddef","last_reissued_at":"2026-05-18T00:22:39.379419Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.379419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Differentially Private Recurrent Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Ramage, H. Brendan McMahan, Kunal Talwar, Li Zhang","submitted_at":"2017-10-18T23:46:57Z","abstract_excerpt":"We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep networks on user-partitioned data and privacy accounting for stochastic gradient descent. In particular, we add user-level privacy protection to the federated averaging algorithm, which makes \"large step\" updates from user-level data. Our work demonstrates that given a dataset with a sufficiently large number of users (a requirement easily met by even small inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06963","kind":"arxiv","version":3},"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":"1710.06963","created_at":"2026-05-18T00:22:39.379483+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.06963v3","created_at":"2026-05-18T00:22:39.379483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06963","created_at":"2026-05-18T00:22:39.379483+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KBFRPFV3DDR","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KBFRPFV3DDRIGHR","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KBFRPFV","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"1906.09679","citing_title":"The Value of Collaboration in Convex Machine Learning with Differential Privacy","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23131","citing_title":"When Determinants Are Not Enough: Private Rare Switching","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":105,"is_internal_anchor":true},{"citing_arxiv_id":"2411.03926","citing_title":"Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learning","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2601.00418","citing_title":"Secure, Verifiable, and Scalable Multi-Client Data Sharing via Consensus-Based Privacy-Preserving Data Distribution","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15573","citing_title":"Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18656","citing_title":"Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2603.03853","citing_title":"Practical Quantum Federated Learning for Privacy-Sensitive Healthcare: Communication Efficiency and Noise Resilience","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10272","citing_title":"DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23426","citing_title":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED","json":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED.json","graph_json":"https://pith.science/api/pith-number/6KBFRPFV3DDRIGHRMIKZSSROED/graph.json","events_json":"https://pith.science/api/pith-number/6KBFRPFV3DDRIGHRMIKZSSROED/events.json","paper":"https://pith.science/paper/6KBFRPFV"},"agent_actions":{"view_html":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED","download_json":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED.json","view_paper":"https://pith.science/paper/6KBFRPFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.06963&json=true","fetch_graph":"https://pith.science/api/pith-number/6KBFRPFV3DDRIGHRMIKZSSROED/graph.json","fetch_events":"https://pith.science/api/pith-number/6KBFRPFV3DDRIGHRMIKZSSROED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED/action/storage_attestation","attest_author":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED/action/author_attestation","sign_citation":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED/action/citation_signature","submit_replication":"https://pith.science/pith/6KBFRPFV3DDRIGHRMIKZSSROED/action/replication_record"}},"created_at":"2026-05-18T00:22:39.379483+00:00","updated_at":"2026-05-18T00:22:39.379483+00:00"}