{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5W7QFDKBCIUGKV3M53UEH34YL5","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":"264451c50ee1994d76c3ea7a5a451727631efe973f3d180cf2913f1d156e0f35","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T12:51:40Z","title_canon_sha256":"65c87b34a2b3129cd72a5b340d565d81c6cf5e49fae578d4c525f95cf6986bf6"},"schema_version":"1.0","source":{"id":"2501.11463","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11463","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11463v2","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11463","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"5W7QFDKBCIUG","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"5W7QFDKBCIUGKV3M","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"5W7QFDKB","created_at":"2026-07-05T11:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:bd0c2df658ba19a669c733142afb9352526dc219431f1e3a498f06e624556119","target":"graph","created_at":"2026-07-05T11:13:18Z","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/2501.11463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but often at the cost of reduced output diversity. This trade-off between diversity and alignment quality remains a significant challenge. Drawing inspiration from curiosity-driven exploration in reinforcement learning, we introduce curiosity-driven RLHF (CD-RLHF), a framework that incorporates intrinsic rewards for novel states, alongside traditional sparse extrinsic rewards, to optimize both output diversity and alignment quality. We demonstrate the effectiv","authors_text":"HaiFeng Wang, Haoran Sun, Hua Wu, Shuohuan Wang, Yekun Chai, Yu Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T12:51:40Z","title":"Curiosity-Driven Reinforcement Learning from Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11463","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":"sha256:515d2d3fb4862049693b7d1106e60fb1ec28d0929d8f1a9d86618f8261b771fe","target":"record","created_at":"2026-07-05T11:13:18Z","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":"264451c50ee1994d76c3ea7a5a451727631efe973f3d180cf2913f1d156e0f35","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T12:51:40Z","title_canon_sha256":"65c87b34a2b3129cd72a5b340d565d81c6cf5e49fae578d4c525f95cf6986bf6"},"schema_version":"1.0","source":{"id":"2501.11463","kind":"arxiv","version":2}},"canonical_sha256":"edbf028d41122865576ceee843ef985f58600d46ca32c2b920f1994a29d7e6b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edbf028d41122865576ceee843ef985f58600d46ca32c2b920f1994a29d7e6b8","first_computed_at":"2026-07-05T11:13:18.840409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:18.840409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U2JEWMZcyELsb0YyOuOjfhb86F9XjpTrZr/fTyFcaQ56iE2E5d4trs7UOYtv/HRscrHFcHzw/srfIiygwRO/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:18.840910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11463","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:515d2d3fb4862049693b7d1106e60fb1ec28d0929d8f1a9d86618f8261b771fe","sha256:bd0c2df658ba19a669c733142afb9352526dc219431f1e3a498f06e624556119"],"state_sha256":"e342efbb08df5ac4823aada48e6e85ecf4df01ab112e8cb19941116848b80719"}