{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U5GXUTDM33C2YL3KFARH32XJFR","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":"1c6e6620c1ff6e52cf1bb3893f133d4b8d2d3e0d70d67085602c21d7686b8f0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T08:27:34Z","title_canon_sha256":"5fd3876233f5714091a8125f44f4f690f1f84e9e0742f1857a75b9712f8d1148"},"schema_version":"1.0","source":{"id":"2506.04746","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04746","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04746v1","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04746","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"U5GXUTDM33C2","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"U5GXUTDM33C2YL3K","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"U5GXUTDM","created_at":"2026-07-05T11:16:19Z"}],"graph_snapshots":[{"event_id":"sha256:8a71286c31827ed0882896e5743c74cf497b6ee4f1a915cac580c4cdef934722","target":"graph","created_at":"2026-07-05T11:16:19Z","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/2506.04746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Group Relative Policy Optimization (GRPO) algorithm has demonstrated considerable success in enhancing the reasoning capabilities of large language models (LLMs), as evidenced by DeepSeek-R1. However, the absence of intermediate supervision in GRPO frequently leads to inefficient exploration dynamics. A single error in a complex reasoning chain can invalidate the entire solution, resulting in abrupt reward vanishing and compromising training stability.To address these challenges, we propose MGRPO (Multi-layer GRPO). MGRPO operates in two layers: the first layer employs standard GRPO to gen","authors_text":"Baiqiao Wang, Fei Ding, youwei wang, Zijian Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T08:27:34Z","title":"Multi-Layer GRPO: Enhancing Reasoning and Self-Correction in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04746","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":"sha256:098be68992eb85bb1e9d3de2ce02b66d3845ea433bbdf58bade6a94a8d589dcf","target":"record","created_at":"2026-07-05T11:16:19Z","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":"1c6e6620c1ff6e52cf1bb3893f133d4b8d2d3e0d70d67085602c21d7686b8f0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T08:27:34Z","title_canon_sha256":"5fd3876233f5714091a8125f44f4f690f1f84e9e0742f1857a75b9712f8d1148"},"schema_version":"1.0","source":{"id":"2506.04746","kind":"arxiv","version":1}},"canonical_sha256":"a74d7a4c6cdec5ac2f6a28227deae92c545de5fdc76e38e01cb04edcba532430","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a74d7a4c6cdec5ac2f6a28227deae92c545de5fdc76e38e01cb04edcba532430","first_computed_at":"2026-07-05T11:16:19.668358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:19.668358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dVlueJWY3JEADJicPUuN8VfgOIJvAvj+bHtc3ZexBn7ncN6z5DXW94ev/IwfrDThRHWLWToHkB2krB+IeD6PCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:19.668805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04746","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:098be68992eb85bb1e9d3de2ce02b66d3845ea433bbdf58bade6a94a8d589dcf","sha256:8a71286c31827ed0882896e5743c74cf497b6ee4f1a915cac580c4cdef934722"],"state_sha256":"7a392c305c872d2fc15835180e1ef6c28da77623a04b42f6e625bcb13671258d"}