{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FDDXSKF6SAA3EEKD3RVOOZHJEP","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":"ae23b7e43999a8cf40ef16971c81022045485c4d134871e69566ede0e1083866","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T02:44:10Z","title_canon_sha256":"935258b1e806958e8c467395dcf5c9001b51e807ae7a4367b84f2d60b0a7c17b"},"schema_version":"1.0","source":{"id":"2506.09340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09340","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09340v1","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09340","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"pith_short_12","alias_value":"FDDXSKF6SAA3","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"pith_short_16","alias_value":"FDDXSKF6SAA3EEKD","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"pith_short_8","alias_value":"FDDXSKF6","created_at":"2026-07-05T11:19:35Z"}],"graph_snapshots":[{"event_id":"sha256:e12b6989accd0c47f477d5260214174263e2565070ce75bca1b36c9854c082aa","target":"graph","created_at":"2026-07-05T11:19:35Z","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/2506.09340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low data efficiency. To address this, we introduce Replay-Enhanced Policy Optimization (RePO), which leverages diverse replay strategies to retrieve off-policy samples from a replay buffer, allowing policy optimization based on a broader and more diverse set of samples for each prompt. Experiments on five LLMs across seven mathematical reasoning benchmarks demo","authors_text":"Chaochao Lu, Chao Yang, Siheng Li, Wai Lam, Zhanhui Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T02:44:10Z","title":"RePO: Replay-Enhanced Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09340","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":"sha256:64e53ec120e5d4069ea66a635784ba81ed4f9b68fc67cf3717b8ce7440c5fd30","target":"record","created_at":"2026-07-05T11:19:35Z","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":"ae23b7e43999a8cf40ef16971c81022045485c4d134871e69566ede0e1083866","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T02:44:10Z","title_canon_sha256":"935258b1e806958e8c467395dcf5c9001b51e807ae7a4367b84f2d60b0a7c17b"},"schema_version":"1.0","source":{"id":"2506.09340","kind":"arxiv","version":1}},"canonical_sha256":"28c77928be9001b21143dc6ae764e923eaaf67fc6c9ecaca73c562ac467e0d13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28c77928be9001b21143dc6ae764e923eaaf67fc6c9ecaca73c562ac467e0d13","first_computed_at":"2026-07-05T11:19:35.058788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:35.058788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wymrpj4do9yIQlZxgLmD/3UP1LpsesamkmmQQPTzMroza/6B4qX8aIwzcdHYs/NcnDdS9bq9PLayHg1JfuT/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:35.059252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64e53ec120e5d4069ea66a635784ba81ed4f9b68fc67cf3717b8ce7440c5fd30","sha256:e12b6989accd0c47f477d5260214174263e2565070ce75bca1b36c9854c082aa"],"state_sha256":"e690e344a401dca6ac3c2867a8da1a649dba5eba672c4428cad5133849cfbf61"}