{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W6C4I5ZPVE2TM5IKOJZMJR2OSF","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":"287a4ecbbe1d70520dd20cf3399742f619895faa9db06ddf0759bb10d0b177ef","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T15:03:41Z","title_canon_sha256":"d947de77251b5cdd2bc394be3117e8df1ccb9a43e5d1af0e16ffae9c0ce2ce96"},"schema_version":"1.0","source":{"id":"2505.17997","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17997","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17997v2","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17997","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_12","alias_value":"W6C4I5ZPVE2T","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_16","alias_value":"W6C4I5ZPVE2TM5IK","created_at":"2026-07-05T11:10:09Z"},{"alias_kind":"pith_short_8","alias_value":"W6C4I5ZP","created_at":"2026-07-05T11:10:09Z"}],"graph_snapshots":[{"event_id":"sha256:ffa29070e8bd1b2d55fdee63e0003fb2154e4193317f1143cff1f6247c473f80","target":"graph","created_at":"2026-07-05T11:10:09Z","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/2505.17997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The VAPO framework has demonstrated significant empirical success in enhancing the efficiency and reliability of reinforcement learning for long chain-of-thought (CoT) reasoning tasks with large language models (LLMs). By systematically addressing challenges such as value model bias, heterogeneous sequence lengths, and sparse reward signals, VAPO achieves state-of-the-art performance. While its practical benefits are evident, a deeper theoretical understanding of its underlying mechanisms and potential limitations is crucial for guiding future advancements. This paper aims to initiate such a d","authors_text":"Beiwen Zhang, Hongyi Huang, Jintian Shao, Mingkai Zheng, Yiming Cheng, You Shan, Zhiyu Wu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T15:03:41Z","title":"Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17997","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:e0c3ab86683159b8effbbbf15284411d2060c0052605b0015ba8e981a857a43f","target":"record","created_at":"2026-07-05T11:10:09Z","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":"287a4ecbbe1d70520dd20cf3399742f619895faa9db06ddf0759bb10d0b177ef","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T15:03:41Z","title_canon_sha256":"d947de77251b5cdd2bc394be3117e8df1ccb9a43e5d1af0e16ffae9c0ce2ce96"},"schema_version":"1.0","source":{"id":"2505.17997","kind":"arxiv","version":2}},"canonical_sha256":"b785c4772fa93536750a7272c4c74e915c1175091a94a95cc60d283764f7dd08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b785c4772fa93536750a7272c4c74e915c1175091a94a95cc60d283764f7dd08","first_computed_at":"2026-07-05T11:10:09.582103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:09.582103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RO4N/72a54k8N2ZjFzbcnwR8VyEMJs/4C/KFP0Nk9K/rFXRoLxTJoYwZS2SeygRRuYewJckopdLqdboMfMzTAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:09.582604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17997","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0c3ab86683159b8effbbbf15284411d2060c0052605b0015ba8e981a857a43f","sha256:ffa29070e8bd1b2d55fdee63e0003fb2154e4193317f1143cff1f6247c473f80"],"state_sha256":"3ec13ee75e3582fa36560c2b07f7388e50789a13020ca7c384c786c3d1f1212f"}