{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N4CGYDDUJ5I2Y4ISHAHVB7KZST","short_pith_number":"pith:N4CGYDDU","canonical_record":{"source":{"id":"2503.01491","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T12:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"917f49a5a0f0fabd246234e660e917a9f936d7d0a5fbe1bddb6d95892d1cc83a","abstract_canon_sha256":"6bcdfab7ba3f13d8f4f9784d819a0dcda2d5dbbea9a92ca4acc4653badf59766"},"schema_version":"1.0"},"canonical_sha256":"6f046c0c744f51ac7112380f50fd5994eb24e195bbc1b96c2ce74cc1daf03369","source":{"kind":"arxiv","id":"2503.01491","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01491","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01491v1","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01491","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"N4CGYDDUJ5I2","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"N4CGYDDUJ5I2Y4IS","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"N4CGYDDU","created_at":"2026-07-05T10:23:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N4CGYDDUJ5I2Y4ISHAHVB7KZST","target":"record","payload":{"canonical_record":{"source":{"id":"2503.01491","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T12:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"917f49a5a0f0fabd246234e660e917a9f936d7d0a5fbe1bddb6d95892d1cc83a","abstract_canon_sha256":"6bcdfab7ba3f13d8f4f9784d819a0dcda2d5dbbea9a92ca4acc4653badf59766"},"schema_version":"1.0"},"canonical_sha256":"6f046c0c744f51ac7112380f50fd5994eb24e195bbc1b96c2ce74cc1daf03369","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:08.333696Z","signature_b64":"iXeHKXZ0UFgXkC3LOFVqM+YPZCNHXnkFe9k0yRVP29fo4jVgBQHxKaPoI/mLpdlkg34ZwtBmCczNcTiAkjW4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f046c0c744f51ac7112380f50fd5994eb24e195bbc1b96c2ce74cc1daf03369","last_reissued_at":"2026-07-05T10:23:08.332938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:08.332938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.01491","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:23:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DEWlTG8h4VxxlYx5DdgtJWWy5UElGhVuaR2DmGdoPCy/OeWoD96fcSjbQqeaPJuXtdGSdVLQeyr2nFpZhZQABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T21:54:56.177144Z"},"content_sha256":"6efe940687b5e9c221150c4f47552de56cc03b5fb99218a33c56735b86613379","schema_version":"1.0","event_id":"sha256:6efe940687b5e9c221150c4f47552de56cc03b5fb99218a33c56735b86613379"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N4CGYDDUJ5I2Y4ISHAHVB7KZST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lin Yan, Ruofei Zhu, Tiantian Fan, Yufeng Yuan, Yu Yue","submitted_at":"2025-03-03T12:59:25Z","abstract_excerpt":"Reinforcement learning (RL) is pivotal for enabling large language models (LLMs) to generate long chains of thought (CoT) for complex tasks like math and reasoning. However, Proximal Policy Optimization (PPO), effective in many RL scenarios, fails in long CoT tasks. This paper identifies that value initialization bias and reward signal decay are the root causes of PPO's failure. We propose Value-Calibrated PPO (VC-PPO) to address these issues. In VC-PPO, the value model is pretrained to tackle initialization bias, and the Generalized Advantage Estimation (GAE) computation is decoupled between "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01491","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.01491/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:23:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IU/mUK7iY+Zcdm7B5HoB7zwetIEIlq10qyjJ6QSN/BLZLpUMo/dVYa46MR9i3oim+gwC167BiyrB8v1QvzGOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T21:54:56.177536Z"},"content_sha256":"7975abbf6245003846366281b9e15c515d10c78ba7e794e284cf895654e93c1f","schema_version":"1.0","event_id":"sha256:7975abbf6245003846366281b9e15c515d10c78ba7e794e284cf895654e93c1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N4CGYDDUJ5I2Y4ISHAHVB7KZST/bundle.json","state_url":"https://pith.science/pith/N4CGYDDUJ5I2Y4ISHAHVB7KZST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N4CGYDDUJ5I2Y4ISHAHVB7KZST/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-23T21:54:56Z","links":{"resolver":"https://pith.science/pith/N4CGYDDUJ5I2Y4ISHAHVB7KZST","bundle":"https://pith.science/pith/N4CGYDDUJ5I2Y4ISHAHVB7KZST/bundle.json","state":"https://pith.science/pith/N4CGYDDUJ5I2Y4ISHAHVB7KZST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N4CGYDDUJ5I2Y4ISHAHVB7KZST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N4CGYDDUJ5I2Y4ISHAHVB7KZST","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":"6bcdfab7ba3f13d8f4f9784d819a0dcda2d5dbbea9a92ca4acc4653badf59766","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T12:59:25Z","title_canon_sha256":"917f49a5a0f0fabd246234e660e917a9f936d7d0a5fbe1bddb6d95892d1cc83a"},"schema_version":"1.0","source":{"id":"2503.01491","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01491","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01491v1","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01491","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"N4CGYDDUJ5I2","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"N4CGYDDUJ5I2Y4IS","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"N4CGYDDU","created_at":"2026-07-05T10:23:08Z"}],"graph_snapshots":[{"event_id":"sha256:7975abbf6245003846366281b9e15c515d10c78ba7e794e284cf895654e93c1f","target":"graph","created_at":"2026-07-05T10:23:08Z","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/2503.01491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is pivotal for enabling large language models (LLMs) to generate long chains of thought (CoT) for complex tasks like math and reasoning. However, Proximal Policy Optimization (PPO), effective in many RL scenarios, fails in long CoT tasks. This paper identifies that value initialization bias and reward signal decay are the root causes of PPO's failure. We propose Value-Calibrated PPO (VC-PPO) to address these issues. In VC-PPO, the value model is pretrained to tackle initialization bias, and the Generalized Advantage Estimation (GAE) computation is decoupled between ","authors_text":"Lin Yan, Ruofei Zhu, Tiantian Fan, Yufeng Yuan, Yu Yue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T12:59:25Z","title":"What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01491","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":"sha256:6efe940687b5e9c221150c4f47552de56cc03b5fb99218a33c56735b86613379","target":"record","created_at":"2026-07-05T10:23:08Z","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":"6bcdfab7ba3f13d8f4f9784d819a0dcda2d5dbbea9a92ca4acc4653badf59766","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T12:59:25Z","title_canon_sha256":"917f49a5a0f0fabd246234e660e917a9f936d7d0a5fbe1bddb6d95892d1cc83a"},"schema_version":"1.0","source":{"id":"2503.01491","kind":"arxiv","version":1}},"canonical_sha256":"6f046c0c744f51ac7112380f50fd5994eb24e195bbc1b96c2ce74cc1daf03369","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f046c0c744f51ac7112380f50fd5994eb24e195bbc1b96c2ce74cc1daf03369","first_computed_at":"2026-07-05T10:23:08.332938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:08.332938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iXeHKXZ0UFgXkC3LOFVqM+YPZCNHXnkFe9k0yRVP29fo4jVgBQHxKaPoI/mLpdlkg34ZwtBmCczNcTiAkjW4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:08.333696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01491","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6efe940687b5e9c221150c4f47552de56cc03b5fb99218a33c56735b86613379","sha256:7975abbf6245003846366281b9e15c515d10c78ba7e794e284cf895654e93c1f"],"state_sha256":"06a1a14b063914be75de77ea2a0031e38a8a7e79819552b62ddc2a8065f46577"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Usj3ZpIZ0j3VR0APwW4ZFlk4exj6lPFH41iuXs1sFLL93Oo0c8dggZx10llI+uM70nZgSJUWcJdSruUtt2GKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-23T21:54:56.180174Z","bundle_sha256":"ba3666e7b7f8e90a73cfb370e3fbecbc49e67f054e3103af859e98f4bb305013"}}