{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZEVSCJFXC3UD4O6RPU66X7GL4Q","short_pith_number":"pith:ZEVSCJFX","canonical_record":{"source":{"id":"2410.01679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T15:49:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0de23e876e2e3b01639995888a94a28e5037a8e7e4dd84851122fe6e1d59f340","abstract_canon_sha256":"3cce013654c15c55fc0af6e9a8751056231adf9e953e894eba76530a6a5b6a42"},"schema_version":"1.0"},"canonical_sha256":"c92b2124b716e83e3bd17d3debfccbe41f91b99321963f6fc0b76f59b6a38064","source":{"kind":"arxiv","id":"2410.01679","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01679","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01679v2","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01679","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZEVSCJFXC3UD","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZEVSCJFXC3UD4O6R","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZEVSCJFX","created_at":"2026-07-05T11:15:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZEVSCJFXC3UD4O6RPU66X7GL4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T15:49:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0de23e876e2e3b01639995888a94a28e5037a8e7e4dd84851122fe6e1d59f340","abstract_canon_sha256":"3cce013654c15c55fc0af6e9a8751056231adf9e953e894eba76530a6a5b6a42"},"schema_version":"1.0"},"canonical_sha256":"c92b2124b716e83e3bd17d3debfccbe41f91b99321963f6fc0b76f59b6a38064","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:17.722397Z","signature_b64":"GSmbkacmQFHD4be8acrPnkfBkGZWB/NTVqja96ABU/z+XCcfd3+jD3Kgz/BYOK3Y2RG3vbDngFKlrxMAOLPTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c92b2124b716e83e3bd17d3debfccbe41f91b99321963f6fc0b76f59b6a38064","last_reissued_at":"2026-07-05T11:15:17.721862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:17.721862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01679","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lG1rFRhO3g0EnTi5PncrDgNjWwJRngZkDkYalb2oDkVXtSYrV9wH0hd8tbAKvfdt2ytLunuYIzsP1pHuN6jICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T18:35:13.326820Z"},"content_sha256":"6d71219675d79361864cfdb3bb4a441b46b95fcb392e05a02f2c5e4e591a7f01","schema_version":"1.0","event_id":"sha256:6d71219675d79361864cfdb3bb4a441b46b95fcb392e05a02f2c5e4e591a7f01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZEVSCJFXC3UD4O6RPU66X7GL4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VinePPO: Refining Credit Assignment in RL Training of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Alessandro Sordoni, Amirhossein Kazemnejad, Eva Portelance, Milad Aghajohari, Nicolas Le Roux, Siva Reddy","submitted_at":"2024-10-02T15:49:30Z","abstract_excerpt":"Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit to these steps is essential for enhancing model performance. Proximal Policy Optimization (PPO), a common reinforcement learning (RL) algorithm used for LLM finetuning, employs value networks to tackle credit assignment. However, recent approaches achieve strong results without it, raising questions about the efficacy of value networks in practice. In this work, we systematically evaluate the efficacy of value netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01679","kind":"arxiv","version":2},"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/2410.01679/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":"2026-07-05T11:15:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qx0y5b0KpZjv4VVkrEbwm6JrNtdehCAeRezjJgVPNr0RRnH+q3xmmhXE9UCPtEKjd3OHmCqPHqDv5bq938eoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T18:35:13.327191Z"},"content_sha256":"4e4b9c03a2ca423f46145293a82b2279f04396d86aaf933c7b3730d3e0c4c338","schema_version":"1.0","event_id":"sha256:4e4b9c03a2ca423f46145293a82b2279f04396d86aaf933c7b3730d3e0c4c338"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZEVSCJFXC3UD4O6RPU66X7GL4Q/bundle.json","state_url":"https://pith.science/pith/ZEVSCJFXC3UD4O6RPU66X7GL4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZEVSCJFXC3UD4O6RPU66X7GL4Q/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":"2026-07-11T18:35:13Z","links":{"resolver":"https://pith.science/pith/ZEVSCJFXC3UD4O6RPU66X7GL4Q","bundle":"https://pith.science/pith/ZEVSCJFXC3UD4O6RPU66X7GL4Q/bundle.json","state":"https://pith.science/pith/ZEVSCJFXC3UD4O6RPU66X7GL4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZEVSCJFXC3UD4O6RPU66X7GL4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZEVSCJFXC3UD4O6RPU66X7GL4Q","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":"3cce013654c15c55fc0af6e9a8751056231adf9e953e894eba76530a6a5b6a42","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T15:49:30Z","title_canon_sha256":"0de23e876e2e3b01639995888a94a28e5037a8e7e4dd84851122fe6e1d59f340"},"schema_version":"1.0","source":{"id":"2410.01679","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01679","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01679v2","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01679","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZEVSCJFXC3UD","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZEVSCJFXC3UD4O6R","created_at":"2026-07-05T11:15:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZEVSCJFX","created_at":"2026-07-05T11:15:17Z"}],"graph_snapshots":[{"event_id":"sha256:4e4b9c03a2ca423f46145293a82b2279f04396d86aaf933c7b3730d3e0c4c338","target":"graph","created_at":"2026-07-05T11:15:17Z","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/2410.01679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit to these steps is essential for enhancing model performance. Proximal Policy Optimization (PPO), a common reinforcement learning (RL) algorithm used for LLM finetuning, employs value networks to tackle credit assignment. However, recent approaches achieve strong results without it, raising questions about the efficacy of value networks in practice. In this work, we systematically evaluate the efficacy of value netwo","authors_text":"Aaron Courville, Alessandro Sordoni, Amirhossein Kazemnejad, Eva Portelance, Milad Aghajohari, Nicolas Le Roux, Siva Reddy","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T15:49:30Z","title":"VinePPO: Refining Credit Assignment in RL Training of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01679","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":"sha256:6d71219675d79361864cfdb3bb4a441b46b95fcb392e05a02f2c5e4e591a7f01","target":"record","created_at":"2026-07-05T11:15:17Z","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":"3cce013654c15c55fc0af6e9a8751056231adf9e953e894eba76530a6a5b6a42","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T15:49:30Z","title_canon_sha256":"0de23e876e2e3b01639995888a94a28e5037a8e7e4dd84851122fe6e1d59f340"},"schema_version":"1.0","source":{"id":"2410.01679","kind":"arxiv","version":2}},"canonical_sha256":"c92b2124b716e83e3bd17d3debfccbe41f91b99321963f6fc0b76f59b6a38064","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c92b2124b716e83e3bd17d3debfccbe41f91b99321963f6fc0b76f59b6a38064","first_computed_at":"2026-07-05T11:15:17.721862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:17.721862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GSmbkacmQFHD4be8acrPnkfBkGZWB/NTVqja96ABU/z+XCcfd3+jD3Kgz/BYOK3Y2RG3vbDngFKlrxMAOLPTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:17.722397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01679","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d71219675d79361864cfdb3bb4a441b46b95fcb392e05a02f2c5e4e591a7f01","sha256:4e4b9c03a2ca423f46145293a82b2279f04396d86aaf933c7b3730d3e0c4c338"],"state_sha256":"a05cabeca5519ff79f5eaa992148e7be56d244e89e9d8e2cb62b9dee133da50f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRfyvHJ9mM8LMHIIuS5ZCvGjm2zTCYB4BPzHR3oFeBHlmnuT+5P85N6FIqu0VYhv7pQARKbgCVZMKALH5B8KCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T18:35:13.329620Z","bundle_sha256":"ebe90b7f8f82d6f3148bef8b35d4aff518d1119c0a442e1d4b7611c5d1a728ca"}}