{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7DXGDARAJRBKZ7L5UVV3YRSS7H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"41fdbe0e2b4135e5f7dfb4f9cd887706b748a7cee1ed014f745ca5079a7029be","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T19:58:51Z","title_canon_sha256":"d1936a86a0bf80400f85ef73475830e1e4ea2300b511fecca00c7ac5a2cc4f1b"},"schema_version":"1.0","source":{"id":"2310.16960","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16960","created_at":"2026-07-05T08:14:51Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16960v2","created_at":"2026-07-05T08:14:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16960","created_at":"2026-07-05T08:14:51Z"},{"alias_kind":"pith_short_12","alias_value":"7DXGDARAJRBK","created_at":"2026-07-05T08:14:51Z"},{"alias_kind":"pith_short_16","alias_value":"7DXGDARAJRBKZ7L5","created_at":"2026-07-05T08:14:51Z"},{"alias_kind":"pith_short_8","alias_value":"7DXGDARA","created_at":"2026-07-05T08:14:51Z"}],"graph_snapshots":[{"event_id":"sha256:d179ef1199434a572d81f39790238bef0839d170340a8ae61bfa3fba5ac0f7b0","target":"graph","created_at":"2026-07-05T08:14:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.16960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we initiate the study of privacy-preserving alignment of LLMs through Differential Privacy (DP) in conjunction with RL. Following the influential work of Ziegler et al. (2020), we study two dominant paradigms: (i) alignment via RL without human in the loop (e.g., positive review generation) and (ii) alignment via RL from human feedback (RLHF) (e.g., summarizati","authors_text":"Arturs Backurs, Fan Wu, Huseyin A. Inan, Janardhan Kulkarni, Robert Sim, Varun Chandrasekaran","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T19:58:51Z","title":"Privately Aligning Language Models with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16960","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2e006a10ce31bda0e4672f5db32c6e6a79e4d9701195f7d24d355935721436f4","target":"record","created_at":"2026-07-05T08:14:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"41fdbe0e2b4135e5f7dfb4f9cd887706b748a7cee1ed014f745ca5079a7029be","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T19:58:51Z","title_canon_sha256":"d1936a86a0bf80400f85ef73475830e1e4ea2300b511fecca00c7ac5a2cc4f1b"},"schema_version":"1.0","source":{"id":"2310.16960","kind":"arxiv","version":2}},"canonical_sha256":"f8ee6182204c42acfd7da56bbc4652f9d7cee4cd90b2bff73d3f6482d1c80498","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8ee6182204c42acfd7da56bbc4652f9d7cee4cd90b2bff73d3f6482d1c80498","first_computed_at":"2026-07-05T08:14:51.210656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:51.210656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yeqyqCAe010VOVUiZPyAoq+/kmFCHp/2QJlGLbAxt6p6Oy0cQZlPDraYJUhkVV47WFoXWrqpJHZGP7+pcndQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:51.211122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16960","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e006a10ce31bda0e4672f5db32c6e6a79e4d9701195f7d24d355935721436f4","sha256:d179ef1199434a572d81f39790238bef0839d170340a8ae61bfa3fba5ac0f7b0"],"state_sha256":"2c10f5c44d62564c8f643e68f89bcf4207849a03d47b58dbdaf24b02f61241ee"}