{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LLEWARJRKY2K7UVNKZDU556HEW","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":"a40ad3433cc6a2d6032e7eda88fff3aa74e409dc702b056230cf62e27b8d42fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T05:56:11Z","title_canon_sha256":"a0d5368683101b468cb2ce4f94c2cc0a5b691a46e4c141bae1f3d0d70d9c1034"},"schema_version":"1.0","source":{"id":"2505.16265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16265","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16265v1","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16265","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_12","alias_value":"LLEWARJRKY2K","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_16","alias_value":"LLEWARJRKY2K7UVN","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_8","alias_value":"LLEWARJR","created_at":"2026-07-05T11:07:32Z"}],"graph_snapshots":[{"event_id":"sha256:23462eb5c3b0a61c44084885beff36b8de59e40cbffe76be9e0c5182c16a1bb0","target":"graph","created_at":"2026-07-05T11:07:32Z","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/2505.16265/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 become a powerful post-training paradigm for aligning large language models with human preferences. A core challenge in RLHF is constructing accurate reward signals, where the conventional Bradley-Terry reward models (BT RMs) often suffer from sensitivity to data size and coverage, as well as vulnerability to reward hacking. Generative reward models (GenRMs) offer a more robust alternative by generating chain-of-thought (CoT) rationales followed by a final reward. However, existing GenRMs rely on shallow, vertically scaled reasoning, limiti","authors_text":"Changlong Yu, Chao Zhang, Haoming Jiang, Ilgee Hong, Liang Qiu, Qingru Zhang, Qin Lu, Tuo Zhao, Weixiang Yan, Xin Liu, Zhenghao Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T05:56:11Z","title":"Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16265","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":"sha256:1b3874fa6bfde7399b78df339ae4745965c7ae4780a7dac645d495ac8a5a9a3a","target":"record","created_at":"2026-07-05T11:07:32Z","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":"a40ad3433cc6a2d6032e7eda88fff3aa74e409dc702b056230cf62e27b8d42fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T05:56:11Z","title_canon_sha256":"a0d5368683101b468cb2ce4f94c2cc0a5b691a46e4c141bae1f3d0d70d9c1034"},"schema_version":"1.0","source":{"id":"2505.16265","kind":"arxiv","version":1}},"canonical_sha256":"5ac96045315634afd2ad56474ef7c725b451da32112f12cc9dea1344d2b2b884","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ac96045315634afd2ad56474ef7c725b451da32112f12cc9dea1344d2b2b884","first_computed_at":"2026-07-05T11:07:32.431513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:32.431513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E6G/H3XAkalB9g78WG61eWFW6rpBl1YUBz824hNG9ANHBGGhOtRPy7B5XspivbPpzqcELjZ1bOmzFCDB4PJOBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:32.431929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b3874fa6bfde7399b78df339ae4745965c7ae4780a7dac645d495ac8a5a9a3a","sha256:23462eb5c3b0a61c44084885beff36b8de59e40cbffe76be9e0c5182c16a1bb0"],"state_sha256":"32c587cc073fbfd505431f3f94d7c264a7b3381bd51bfa4291c7431246b96c9a"}