{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:THNIIJVDYARBIPKE43WDFRABKJ","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":"2e0110fd82976635f3b1d57e35702ed8dec1b235ba1dc21d254910ae36c79328","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T16:42:39Z","title_canon_sha256":"83b939843503faf333b4973cf30dd279e638c19d49a89633a7068973a6de6a5f"},"schema_version":"1.0","source":{"id":"2506.03066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03066","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03066v1","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03066","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"THNIIJVDYARB","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"THNIIJVDYARBIPKE","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"THNIIJVD","created_at":"2026-07-05T11:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:01b974a9547a8ca497fb10622b8b832973e930b6a1ebaa738c3dcdc3a785aa0f","target":"graph","created_at":"2026-07-05T11:15:14Z","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/2506.03066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Link functions, which characterize how human preferences are generated from the value function of an RL problem, are a crucial component in designing RLHF algorithms. Almost all RLHF algorithms, including state-of-the-art ones in empirical studies such as DPO and PPO, assume the link function is known to the agent (e.g., a logistic function according to the Bradley-Terry model), which is arguably unrealistic considering the complex nature of human preferences. To avoid link function mis-specification, this paper studies general RLHF problems with unknown link functions. We propose a novel poli","authors_text":"Lei Ying, Qining Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T16:42:39Z","title":"Provable Reinforcement Learning from Human Feedback with an Unknown Link Function"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03066","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":"sha256:143d7b0ba6fe6a4e2469c0de2bd3986ce64bc336cfccbc3a23bf89128d3473ae","target":"record","created_at":"2026-07-05T11:15:14Z","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":"2e0110fd82976635f3b1d57e35702ed8dec1b235ba1dc21d254910ae36c79328","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T16:42:39Z","title_canon_sha256":"83b939843503faf333b4973cf30dd279e638c19d49a89633a7068973a6de6a5f"},"schema_version":"1.0","source":{"id":"2506.03066","kind":"arxiv","version":1}},"canonical_sha256":"99da8426a3c022143d44e6ec32c401524cdfd966aff2ebae6e00333bc92aa5c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99da8426a3c022143d44e6ec32c401524cdfd966aff2ebae6e00333bc92aa5c9","first_computed_at":"2026-07-05T11:15:14.294996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:14.294996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ds9sUzgtnmhi9T3j4zHYRRle3Qdkl/lLkdqZPgxkrodUhIyK/tN6TExLWRM7o5qfvCGgGN7f8ZM+/YMXMzCtBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:14.295481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:143d7b0ba6fe6a4e2469c0de2bd3986ce64bc336cfccbc3a23bf89128d3473ae","sha256:01b974a9547a8ca497fb10622b8b832973e930b6a1ebaa738c3dcdc3a785aa0f"],"state_sha256":"413d68f684cf1d1e64a5540175f95f36d4b98e8939e34995d6e491876c117e25"}