{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AVTCXNBDPZQISE4EUZQOGUZ33L","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":"be9c73548f9809473bf4ee8956632a097fae515bc8c85356b121bfd0a5534f7b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T09:12:09Z","title_canon_sha256":"431a30181d6d15ef5b1191220937b0ffc36ca9ea08ca5f5878d4c7600941240c"},"schema_version":"1.0","source":{"id":"2501.12735","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12735","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12735v3","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12735","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"AVTCXNBDPZQI","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"AVTCXNBDPZQISE4E","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"AVTCXNBD","created_at":"2026-07-05T10:10:48Z"}],"graph_snapshots":[{"event_id":"sha256:755ac16f97930ce8b93e67441cd9f9bbacb596791f32004ed47e7ebb68492b3b","target":"graph","created_at":"2026-07-05T10:10:48Z","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/2501.12735/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 shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform preference alignment from a fixed dataset, which can be limited in data coverage, and the resulting reward model is hard to generalize in out-of-distribution responses. Thus, online RLHF is more desirable to empower the LLM to explore outside the support of the initial dataset by iteratively collecting the prompt-response pairs. In this paper, we study the fundamental problem in online RLHF, i.e. \\emph{how to explore} ","authors_text":"Chenjia Bai, Kang Xu, Qiaosheng Zhang, Shuang Qiu, Xuelong Li, Yang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T09:12:09Z","title":"Online Preference Alignment for Language Models via Count-based Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12735","kind":"arxiv","version":3},"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":"sha256:0cd7008eef6534532d96c1d6ea31db4b77c3c124827937b0da4884ac0580aa2e","target":"record","created_at":"2026-07-05T10:10:48Z","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":"be9c73548f9809473bf4ee8956632a097fae515bc8c85356b121bfd0a5534f7b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T09:12:09Z","title_canon_sha256":"431a30181d6d15ef5b1191220937b0ffc36ca9ea08ca5f5878d4c7600941240c"},"schema_version":"1.0","source":{"id":"2501.12735","kind":"arxiv","version":3}},"canonical_sha256":"05662bb4237e60891384a660e3533bdaecae3d085ec519627651a61451b86686","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05662bb4237e60891384a660e3533bdaecae3d085ec519627651a61451b86686","first_computed_at":"2026-07-05T10:10:48.098897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:48.098897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l0niKyVG5KX3P3rT1AcilDQSjtfBITjSyXlRSjc6G0/Wyor6yIQqh4hq5D+anrpoARLHRZWAxEs2fWGD7oRuDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:48.099384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12735","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cd7008eef6534532d96c1d6ea31db4b77c3c124827937b0da4884ac0580aa2e","sha256:755ac16f97930ce8b93e67441cd9f9bbacb596791f32004ed47e7ebb68492b3b"],"state_sha256":"4ea960e81ee3e52a9b5a9baa7dbce8b07d82c493832158b99276078d2f28168a"}