{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LYQENBTYWA6NS7BAHOHCXOVAS6","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":"949b3fe2c25f9f21cf5ffaf7d298f94f250bd79127e51ad8a3b15902824b56aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T10:02:43Z","title_canon_sha256":"c20fec2ede04002d11726c0ccbe4c2b1d211f1dd49b11031a32ae76bb8c10e99"},"schema_version":"1.0","source":{"id":"2507.21645","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21645","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21645v1","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21645","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"LYQENBTYWA6N","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"LYQENBTYWA6NS7BA","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"LYQENBTY","created_at":"2026-07-05T11:45:03Z"}],"graph_snapshots":[{"event_id":"sha256:3d9896d0ba157f8e6dd6f52fe24648cf80da7f6681603011b16809c90fdd9191","target":"graph","created_at":"2026-07-05T11:45:03Z","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/2507.21645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based or reference-based rewards, which impose two critical limitations: 1) the dependence on finely annotated reference answer to attain rewards; and 2) the requirement for constrained output format. These limitations fundamentally hinder further RL data scaling and sustained enhancement of model reasoning performance. To address these limitations, we propose a co","authors_text":"Bei Li, Jiahao Liu, Jingang Wang, Meng Zhou, Rongxiang Weng, Xiaowen Shi, Xunliang Cai, Yang Bai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T10:02:43Z","title":"Libra: Assessing and Improving Reward Model by Learning to Think"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21645","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:f8d1fa1b6e47e88d0a13c7ead036d8ec79f24885095ae8eed52349edbb39474c","target":"record","created_at":"2026-07-05T11:45:03Z","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":"949b3fe2c25f9f21cf5ffaf7d298f94f250bd79127e51ad8a3b15902824b56aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T10:02:43Z","title_canon_sha256":"c20fec2ede04002d11726c0ccbe4c2b1d211f1dd49b11031a32ae76bb8c10e99"},"schema_version":"1.0","source":{"id":"2507.21645","kind":"arxiv","version":1}},"canonical_sha256":"5e20468678b03cd97c203b8e2bbaa097b141cf6218bff068e3c85408d2a10fb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e20468678b03cd97c203b8e2bbaa097b141cf6218bff068e3c85408d2a10fb6","first_computed_at":"2026-07-05T11:45:03.772387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:03.772387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TD39z1BNC9Y0IJWZt/PaNCHBd6iQmUEUzirnpTXzzkeody+xDMkC0q/BnQn+/vjA6luK9cZWQ+7E9pvU7aMNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:03.772981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21645","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8d1fa1b6e47e88d0a13c7ead036d8ec79f24885095ae8eed52349edbb39474c","sha256:3d9896d0ba157f8e6dd6f52fe24648cf80da7f6681603011b16809c90fdd9191"],"state_sha256":"b6c98b2619b07411cad08b5b8072b3cc3c66383e29ce3a870eba4c5dc73955ec"}