{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PEDOHQUVII2HU5SNFXCIXLGTOK","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":"12856dad416e61d51a39dd018080245ba9ebe1346b5018e39f7d3ed5ec5f1109","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T16:15:02Z","title_canon_sha256":"b9614bf8c6c1274359ef5d71e92d0659f929406ea8ec25e8942f69d6cbdaf043"},"schema_version":"1.0","source":{"id":"2504.11343","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11343","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11343v2","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11343","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"PEDOHQUVII2H","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"PEDOHQUVII2HU5SN","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"PEDOHQUV","created_at":"2026-07-05T11:20:11Z"}],"graph_snapshots":[{"event_id":"sha256:2aad2d06eccbdec275f6657be662608912f809ff53ef5d68fa80506ac737fa43","target":"graph","created_at":"2026-07-05T11:20:11Z","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/2504.11343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its empirical success in training models such as DeepSeek-R1, yet the sources of its effectiveness remain poorly understood. In this work, we revisit GRPO from a reinforce-like algorithm perspective and analyze its core components. Surprisingly, we find that a simple rejection sampling baseline, RAFT, which trains only on positively rewarded samples, yields competitive performance than GRPO and PPO. Our ablation studies ","authors_text":"Bo Pang, Caiming Xiong, Doyen Sahoo, HanZe Dong, Jiarui Yao, Junnan Li, Lei Wang, Nan Jiang, Tong Zhang, Wei Xiong, Yuhui Xu","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T16:15:02Z","title":"A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11343","kind":"arxiv","version":2},"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:cae3f43a95582bb1c50e820e06505ff692dd1edeaaa2ec69c1328cd9b3e35cf3","target":"record","created_at":"2026-07-05T11:20:11Z","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":"12856dad416e61d51a39dd018080245ba9ebe1346b5018e39f7d3ed5ec5f1109","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T16:15:02Z","title_canon_sha256":"b9614bf8c6c1274359ef5d71e92d0659f929406ea8ec25e8942f69d6cbdaf043"},"schema_version":"1.0","source":{"id":"2504.11343","kind":"arxiv","version":2}},"canonical_sha256":"7906e3c29542347a764d2dc48bacd3729be76ac3039d9399da5726f6a41b6208","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7906e3c29542347a764d2dc48bacd3729be76ac3039d9399da5726f6a41b6208","first_computed_at":"2026-07-05T11:20:11.362227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:11.362227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xMi4E7da4aR+ekmUgfAb2mmxyj1KmF2Rs2gQZq6XqosNcBTHniymYLK8zctC/WspGn/OuMx/JliMBNi7oNCYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:11.363503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11343","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cae3f43a95582bb1c50e820e06505ff692dd1edeaaa2ec69c1328cd9b3e35cf3","sha256:2aad2d06eccbdec275f6657be662608912f809ff53ef5d68fa80506ac737fa43"],"state_sha256":"de4c11282edc9cb2cb1c3d16cd386a54c61c058ba6c4a6f0291c323266aac837"}