{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7QAX6MQQFY2FFUALAECJQFTKW6","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":"5b070a769b213c7db098c30511e9ebd9fd74e4970fa79b5d7d23f005eab5a5b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T09:09:57Z","title_canon_sha256":"20e1dd1cdc863b927b565473864922746014e4df30cdfb49e40be546ee5b9359"},"schema_version":"1.0","source":{"id":"2607.18258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18258","created_at":"2026-07-22T00:22:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18258v1","created_at":"2026-07-22T00:22:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18258","created_at":"2026-07-22T00:22:38Z"},{"alias_kind":"pith_short_12","alias_value":"7QAX6MQQFY2F","created_at":"2026-07-22T00:22:38Z"},{"alias_kind":"pith_short_16","alias_value":"7QAX6MQQFY2FFUAL","created_at":"2026-07-22T00:22:38Z"},{"alias_kind":"pith_short_8","alias_value":"7QAX6MQQ","created_at":"2026-07-22T00:22:38Z"}],"graph_snapshots":[{"event_id":"sha256:43b9373e11a278842ef83314405fa4307ab4325f69d8ac95eb60c48097002bb4","target":"graph","created_at":"2026-07-22T00:22:38Z","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/2607.18258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) with preference-based reward models often exhibits unstable training dynamics. A key contributing factor is that standard RLHF relies on a single sequence-level scalar reward, which is propagated to token-level policy updates and leaves credit assignment within a response inherently ambiguous. Recent work has attempted to address this issue by refining rewards into denser token-level supervision, often relying on the implicit assumption that finer-grained credit assignment improves optimization. We argue that this assumption is incomplete: when","authors_text":"Guanghui Zhu, Limin Wang, Wei Chen, Yafei Li, Yihua Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T09:09:57Z","title":"S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18258","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":"sha256:050c38c50ab82b88054182c8708e0657f11fc6341ad3c8fb0b3092475339876a","target":"record","created_at":"2026-07-22T00:22:38Z","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":"5b070a769b213c7db098c30511e9ebd9fd74e4970fa79b5d7d23f005eab5a5b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T09:09:57Z","title_canon_sha256":"20e1dd1cdc863b927b565473864922746014e4df30cdfb49e40be546ee5b9359"},"schema_version":"1.0","source":{"id":"2607.18258","kind":"arxiv","version":1}},"canonical_sha256":"fc017f32102e3452d00b010498166ab78b6db10bf04e1c91c302f453b37de476","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc017f32102e3452d00b010498166ab78b6db10bf04e1c91c302f453b37de476","first_computed_at":"2026-07-22T00:22:38.986498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:38.986498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TDTqXjRizlHWQM/d7bIUbYA0vib1JbejwcaTtoc9umLdbQ2KEU3xIyOLiM+MYWlEAiZg+N5/qTu5CJ2cGUAQBw==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:38.987395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:050c38c50ab82b88054182c8708e0657f11fc6341ad3c8fb0b3092475339876a","sha256:43b9373e11a278842ef83314405fa4307ab4325f69d8ac95eb60c48097002bb4"],"state_sha256":"bf56a3d799e13da0346c70f97f8ca44bb113d2f0b51944161e1f175f1720bfea"}