{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K3TXS2NUENFRU7RW3M55AZC6CR","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":"653691fd06638cfddc9af3c1b977575066a797867de976736c7a612ea76b80cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T22:34:42Z","title_canon_sha256":"14ef1f6ad76ec6f3225103f6b3cb2135b44e6f53123697cbd363a543eb3d02f7"},"schema_version":"1.0","source":{"id":"2505.20556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20556","created_at":"2026-07-05T11:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20556v1","created_at":"2026-07-05T11:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20556","created_at":"2026-07-05T11:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"K3TXS2NUENFR","created_at":"2026-07-05T11:10:14Z"},{"alias_kind":"pith_short_16","alias_value":"K3TXS2NUENFRU7RW","created_at":"2026-07-05T11:10:14Z"},{"alias_kind":"pith_short_8","alias_value":"K3TXS2NU","created_at":"2026-07-05T11:10:14Z"}],"graph_snapshots":[{"event_id":"sha256:b387cde16c3383834b596d3c7c8056a5351a5dd87a2780ff95dce346dd0fdaed","target":"graph","created_at":"2026-07-05T11:10:14Z","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/2505.20556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work proposes `PET', a novel pessimistic reward fine-tuning method, to learn a pessimistic reward model robust against reward hacking in offline reinforcement learning from human feedback (RLHF). Traditional reward modeling techniques in RLHF train an imperfect reward model, on which a KL regularization plays a pivotal role in mitigating reward hacking when optimizing a policy. Such an intuition-based method still suffers from reward hacking, and the policies with large KL divergence from the dataset distribution are excluded during learning. In contrast, we show that when optimizing a po","authors_text":"Gagandeep Singh, Hangoo Kang, Tarun Suresh, Yinglun Xu, Yuxuan Wan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T22:34:42Z","title":"Learning a Pessimistic Reward Model in RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20556","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":"sha256:4e943d370ddfd3008367677a637a5ecc05d3cb3921805044bc9871351fbe6f59","target":"record","created_at":"2026-07-05T11:10:14Z","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":"653691fd06638cfddc9af3c1b977575066a797867de976736c7a612ea76b80cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T22:34:42Z","title_canon_sha256":"14ef1f6ad76ec6f3225103f6b3cb2135b44e6f53123697cbd363a543eb3d02f7"},"schema_version":"1.0","source":{"id":"2505.20556","kind":"arxiv","version":1}},"canonical_sha256":"56e77969b4234b1a7e36db3bd0645e147c3c3d15248b36f4a5d0ac6ff1888435","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56e77969b4234b1a7e36db3bd0645e147c3c3d15248b36f4a5d0ac6ff1888435","first_computed_at":"2026-07-05T11:10:14.517527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:14.517527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LeN9UiSQYF3dLNh+ZFkJ9B2qbXe5dH4XSkjePLsLe03FuztFuPAVj91Xi2yqIGd5efIUhUwxjIjGLFub3eIBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:14.518180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e943d370ddfd3008367677a637a5ecc05d3cb3921805044bc9871351fbe6f59","sha256:b387cde16c3383834b596d3c7c8056a5351a5dd87a2780ff95dce346dd0fdaed"],"state_sha256":"b0ba82b94971255878be8d049d7c440e149df0974fdb5568c3fbb1f02d056599"}