{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B57AAHQISPJ4FRMPEPJVB76UPE","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":"05b99844c63467869fbddf8c2741096fe74e12388a0d923eb9a41b299eb6d11e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-04T22:55:02Z","title_canon_sha256":"7751ce7530ec001add7f24a318630472faa7e2a3ab73f43664b49a4fc2d7ccc3"},"schema_version":"1.0","source":{"id":"2407.04181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04181","created_at":"2026-07-05T08:40:30Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04181v1","created_at":"2026-07-05T08:40:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04181","created_at":"2026-07-05T08:40:30Z"},{"alias_kind":"pith_short_12","alias_value":"B57AAHQISPJ4","created_at":"2026-07-05T08:40:30Z"},{"alias_kind":"pith_short_16","alias_value":"B57AAHQISPJ4FRMP","created_at":"2026-07-05T08:40:30Z"},{"alias_kind":"pith_short_8","alias_value":"B57AAHQI","created_at":"2026-07-05T08:40:30Z"}],"graph_snapshots":[{"event_id":"sha256:5a367e8bde19aa4378aa79088aaaafd0766535c10b6deb1a1a219454828b9469","target":"graph","created_at":"2026-07-05T08:40:30Z","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/2407.04181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a novel approach to aligning large language models (LLMs) with individual human preferences, sometimes referred to as Reinforcement Learning from \\textit{Personalized} Human Feedback (RLPHF). Given stated preferences along multiple dimensions, such as helpfulness, conciseness, or humor, the goal is to create an LLM without re-training that best adheres to this specification. Starting from specialized expert LLMs, each trained for one such particular preference dimension, we propose a black-box method that merges their outputs on a per-token level. We train a lightweight Pre","authors_text":"Jason Yuan, Jingwen Gu, Jin Peng Zhou, Katie Z Luo, Kilian Q. Weinberger, Wen Sun","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-04T22:55:02Z","title":"Orchestrating LLMs with Different Personalizations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04181","kind":"arxiv","version":1},"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":"sha256:7babbd84e6e13e623d502d07bc9679018f416d4e714ca01cb99611a0098774e6","target":"record","created_at":"2026-07-05T08:40:30Z","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":"05b99844c63467869fbddf8c2741096fe74e12388a0d923eb9a41b299eb6d11e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-04T22:55:02Z","title_canon_sha256":"7751ce7530ec001add7f24a318630472faa7e2a3ab73f43664b49a4fc2d7ccc3"},"schema_version":"1.0","source":{"id":"2407.04181","kind":"arxiv","version":1}},"canonical_sha256":"0f7e001e0893d3c2c58f23d350ffd479197ccb5c24805c0ac6f8e3d3f4194f59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f7e001e0893d3c2c58f23d350ffd479197ccb5c24805c0ac6f8e3d3f4194f59","first_computed_at":"2026-07-05T08:40:30.138347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:30.138347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pxH9nbo51qrz4djYou8JQKxXaR1eDXXMl9eHeIYnqq/FgZXxh0RVdtucIIMCx3UqcvXnENioktYWTAyxS14hBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:30.138808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7babbd84e6e13e623d502d07bc9679018f416d4e714ca01cb99611a0098774e6","sha256:5a367e8bde19aa4378aa79088aaaafd0766535c10b6deb1a1a219454828b9469"],"state_sha256":"6175268ef986dc46739d5cd29ab193106ffeceb37c2fa347d238f581535fa960"}