{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OHHQ2XTR6254YJFUOZYXM4TFND","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":"a537643ed34f35265a8ce2d9ad6a1e649e6c0b1c0fa78d3f19951782d0e83e53","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T14:52:11Z","title_canon_sha256":"8b357b7795e76241955f62a7d7b64b7329669151c11d1fe1851be1d2c5a2b2ca"},"schema_version":"1.0","source":{"id":"2510.00977","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.00977","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.00977v3","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00977","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"OHHQ2XTR6254","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"OHHQ2XTR6254YJFU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"OHHQ2XTR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5d4332200bd865f47aab91d10bbab02ca47ea050a11de6d26b7ca96bbfc7a83b","target":"graph","created_at":"2026-05-17T23:39:17Z","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"},"paper":{"abstract_excerpt":"GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages by estimating the \\emph{value baselines} from group-level statistics, eliminating the need for a critic network. Consequently, the prevailing view emphasizes the necessity of large group sizes, which are assumed to yield more accurate statistical estimates. In this paper, we propose a different view that the efficacy of GRPO stems from its implicit contrastive objective in the optimization, which helps reduce variance via the control variate method. Thi","authors_text":"Chenyang Huang, Jian-Yun Nie, Kejia Chen, Lei Ding, Liheng Ma, Mark Coates, Muzhi Li, Xinyu Wang, Yihong Wu, Yingxue Zhang, Zhanguang Zhang, Zhan Su","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T14:52:11Z","title":"It Takes Two: Your GRPO Is Secretly DPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00977","kind":"arxiv","version":3},"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":"sha256:97bc4d0e8c3a4cf49b0d573d39aa88ae74392274ee0ef2630de31989796a34d1","target":"record","created_at":"2026-05-17T23:39:17Z","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":"a537643ed34f35265a8ce2d9ad6a1e649e6c0b1c0fa78d3f19951782d0e83e53","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T14:52:11Z","title_canon_sha256":"8b357b7795e76241955f62a7d7b64b7329669151c11d1fe1851be1d2c5a2b2ca"},"schema_version":"1.0","source":{"id":"2510.00977","kind":"arxiv","version":3}},"canonical_sha256":"71cf0d5e71f6bbcc24b4767176726568fb0f8d0a8031e731fa8e54c4e1654ca9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71cf0d5e71f6bbcc24b4767176726568fb0f8d0a8031e731fa8e54c4e1654ca9","first_computed_at":"2026-05-17T23:39:17.355423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:17.355423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yOaL+GEznuu2jmH03hSy0T/445oXqcFk0paUdLjeQ+3lvHU3wpjoiwRGJGrzqKPllSem/qLOQiugi1G5BvAxCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:17.355952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.00977","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97bc4d0e8c3a4cf49b0d573d39aa88ae74392274ee0ef2630de31989796a34d1","sha256:5d4332200bd865f47aab91d10bbab02ca47ea050a11de6d26b7ca96bbfc7a83b"],"state_sha256":"a3afc4db5781f908dfd09a250c616988ab7aff9102c6d6b09c79239b1dced5eb"}