{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LG3N3LLKSHI3FI2XNEKGEZVVPI","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":"60d9fabffe6190912b549e32da90c886a519ba2bfc67fbf989333e1deedc6b57","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T10:23:26Z","title_canon_sha256":"c2ae76746893512879215d5b8a38bca99b6acd567cdf841ee6e48757ee9af337"},"schema_version":"1.0","source":{"id":"2503.19523","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19523","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19523v2","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19523","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"LG3N3LLKSHI3","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"pith_short_16","alias_value":"LG3N3LLKSHI3FI2X","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"pith_short_8","alias_value":"LG3N3LLK","created_at":"2026-07-05T10:39:28Z"}],"graph_snapshots":[{"event_id":"sha256:0a533031e403b33ef686a5fc8692c2614cd8a8ea7ee5eaa0c96320462e0b2497","target":"graph","created_at":"2026-07-05T10:39:28Z","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/2503.19523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this article, we primarily examine a variety of RL-based and RL-free methods designed to address Reinforcement Learning from Human Feedback (RLHF) and Large Reasoning Models (LRMs). We begin with a concise overview of the typical steps involved in RLHF and LRMs. Next, we reinterpret several RL-based and RL-free algorithms through the perspective of neural structured bandit prediction, providing a clear conceptual framework that uncovers a deeper connection between these seemingly distinct approaches. Following this, we briefly review some core principles of reinforcement learning, drawing a","authors_text":"Xin Cai","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T10:23:26Z","title":"One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19523","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:c9534bea0f627d4353ea12d51379a9df0ffc7114ff99c19c87d999c2174003f7","target":"record","created_at":"2026-07-05T10:39:28Z","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":"60d9fabffe6190912b549e32da90c886a519ba2bfc67fbf989333e1deedc6b57","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T10:23:26Z","title_canon_sha256":"c2ae76746893512879215d5b8a38bca99b6acd567cdf841ee6e48757ee9af337"},"schema_version":"1.0","source":{"id":"2503.19523","kind":"arxiv","version":2}},"canonical_sha256":"59b6ddad6a91d1b2a35769146266b57a149719adf7c26119891706f3381bbe33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59b6ddad6a91d1b2a35769146266b57a149719adf7c26119891706f3381bbe33","first_computed_at":"2026-07-05T10:39:28.591018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:28.591018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"btcHanffL5b/C9lwY1nHbN4HPcws9OTPnBHYknrqcy0083EkRqc+7pg5qyn037IK0Y7WJ8AFXDa/dIIVT/iiAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:28.591496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19523","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9534bea0f627d4353ea12d51379a9df0ffc7114ff99c19c87d999c2174003f7","sha256:0a533031e403b33ef686a5fc8692c2614cd8a8ea7ee5eaa0c96320462e0b2497"],"state_sha256":"7d1748232e5dffccfd01c3b48751aa22e565d0e07b15f1dcbed6c6e48a8a6f97"}