{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G4F5OO4YXFUCNXVAQRTIGUDQAC","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":"d94d6465d99fa3adb141f952e9a72fcf97f44cee182aa975873790cc219214f2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T08:20:41Z","title_canon_sha256":"6c73c6288d7418e1629c69ea6e0ab32845916f08a5dc94c6bfbc9d1ffe94bad6"},"schema_version":"1.0","source":{"id":"2606.21943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21943","created_at":"2026-06-23T02:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21943v1","created_at":"2026-06-23T02:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21943","created_at":"2026-06-23T02:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"G4F5OO4YXFUC","created_at":"2026-06-23T02:13:03Z"},{"alias_kind":"pith_short_16","alias_value":"G4F5OO4YXFUCNXVA","created_at":"2026-06-23T02:13:03Z"},{"alias_kind":"pith_short_8","alias_value":"G4F5OO4Y","created_at":"2026-06-23T02:13:03Z"}],"graph_snapshots":[{"event_id":"sha256:01713f5de67c6180679d4bcfd9f3234785cb85d17f2b2f6dcb0642baf2f04aee","target":"graph","created_at":"2026-06-23T02:13:03Z","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/2606.21943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate current pipelines, PPO and GRPO, represent only a narrow slice of what RL offers. Understanding why these methods prevail, and what alternatives exist, requires a principled examination of the design decisions that underlie any RL algorithm.\n  This survey organizes that examination around three stages of algorithm construction. We begin with MDP creation: how the reward function, state space, action space, termination condition, and discount factor are, or could be, defined for LLM training. We t","authors_text":"Annie Wong, Aske Plaat, Chao Gao, Filip Ilievski, Hengyuan Zhang, Jacob E. Kooi, Jiayang Shi, Kevin Qiu, Lincen Yang, Mark Hoogendoorn, Ngai Wong, Qi Huang, Shiping Yang, Shujian Yu, Ting-Chih Chen, Vincent Fran\\c{c}ois-Lavet, Xinrui Zu, Yuxuan Jiang, Zhaochun Ren, Zhao Yang, Zhong Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T08:20:41Z","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21943","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:f6a1a12521c2db601aefd1595714be8d03e5d9d5031ce9114391fb41cdbe64ef","target":"record","created_at":"2026-06-23T02:13:03Z","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":"d94d6465d99fa3adb141f952e9a72fcf97f44cee182aa975873790cc219214f2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T08:20:41Z","title_canon_sha256":"6c73c6288d7418e1629c69ea6e0ab32845916f08a5dc94c6bfbc9d1ffe94bad6"},"schema_version":"1.0","source":{"id":"2606.21943","kind":"arxiv","version":1}},"canonical_sha256":"370bd73b98b96826dea0846683507000bc7f2b6f936ecb3b0903cddde45723cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"370bd73b98b96826dea0846683507000bc7f2b6f936ecb3b0903cddde45723cf","first_computed_at":"2026-06-23T02:13:03.789242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:03.789242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F2Gv9TOk4J7XDTMrn4pC+8NrjYV4S9kC0Rh4r3lZD8yOj3jbXkmfHTVIb1YxwnK+Lx2U4YlN58G7uGEF6mIvDQ==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:03.789659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6a1a12521c2db601aefd1595714be8d03e5d9d5031ce9114391fb41cdbe64ef","sha256:01713f5de67c6180679d4bcfd9f3234785cb85d17f2b2f6dcb0642baf2f04aee"],"state_sha256":"c8431b03dc285100016d2bac59ad45659309e795bde9b6d366b8229b3e80b30c"}