{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CNBJEBWDOTPYWKMZHCH7342REZ","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":"ae1f4f81ff3c7b4565c9476929a47461f47fef4227fb9b67e48b521972d0d21c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T10:44:49Z","title_canon_sha256":"e914683c59e5b35ebaac46db24e43828bb1f44a23fa11eabe8de21239dcea4e8"},"schema_version":"1.0","source":{"id":"2505.12951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12951","created_at":"2026-07-05T11:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12951v1","created_at":"2026-07-05T11:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12951","created_at":"2026-07-05T11:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"CNBJEBWDOTPY","created_at":"2026-07-05T11:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"CNBJEBWDOTPYWKMZ","created_at":"2026-07-05T11:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"CNBJEBWD","created_at":"2026-07-05T11:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:5ea0e111487469f170027e3d1b2aa1b023b3f10bcfdff136fc55509fcc521ad5","target":"graph","created_at":"2026-07-05T11:05:12Z","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/2505.12951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inference scaling further accelerates Large Language Models (LLMs) toward Artificial General Intelligence (AGI), with large-scale Reinforcement Learning (RL) to unleash long Chain-of-Thought reasoning. Most contemporary reasoning approaches usually rely on handcrafted rule-based reward functions. However, the tarde-offs of exploration and exploitation in RL algorithms involves multiple complex considerations, and the theoretical and empirical impacts of manually designed reward functions remain insufficiently explored. In this paper, we propose Decoupled Group Reward Optimization (DGRO), a gen","authors_text":"Liya Guo, Xuerui Su, Yi Zhu, Yue Wang, Yuting Liu, Zhiming Ma, Zun Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T10:44:49Z","title":"DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12951","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":"sha256:5ff2e425ae35dabe261f63f3aded07970845515b52d80ad382a3421efad84d14","target":"record","created_at":"2026-07-05T11:05:12Z","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":"ae1f4f81ff3c7b4565c9476929a47461f47fef4227fb9b67e48b521972d0d21c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T10:44:49Z","title_canon_sha256":"e914683c59e5b35ebaac46db24e43828bb1f44a23fa11eabe8de21239dcea4e8"},"schema_version":"1.0","source":{"id":"2505.12951","kind":"arxiv","version":1}},"canonical_sha256":"13429206c374df8b2999388ffdf351265b1ec65b1dfb9947aa4567028fbc6a7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13429206c374df8b2999388ffdf351265b1ec65b1dfb9947aa4567028fbc6a7d","first_computed_at":"2026-07-05T11:05:12.460343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:12.460343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gHV0tMFar1UK+u709KCBhaqLYsuP0KL+gDgqc5/kWTUuLX8PcxwP0YcRFpQAYLx05uzuttgw4sosOkJVPS5sCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:12.460819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ff2e425ae35dabe261f63f3aded07970845515b52d80ad382a3421efad84d14","sha256:5ea0e111487469f170027e3d1b2aa1b023b3f10bcfdff136fc55509fcc521ad5"],"state_sha256":"4067060c20d6978ed1fae36cb14bc36c3e9503201bd01a21f537398c431a6584"}