{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F6NTZIRU7IPX5OPRTYXQ6JO7W3","short_pith_number":"pith:F6NTZIRU","canonical_record":{"source":{"id":"2502.03095","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T11:41:43Z","cross_cats_sorted":[],"title_canon_sha256":"85828a9b965dd7870fb8cba8ca3906d2834f131a7d4f288f7b0ca116beff7440","abstract_canon_sha256":"db8e2fe46b16fde28a247f5d22843cd9c95ab713300766039ae6d3074205dace"},"schema_version":"1.0"},"canonical_sha256":"2f9b3ca234fa1f7eb9f19e2f0f25dfb6df3e2db0211913f93ee30122410e6566","source":{"kind":"arxiv","id":"2502.03095","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03095","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03095v1","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03095","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"F6NTZIRU7IPX","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"F6NTZIRU7IPX5OPR","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"F6NTZIRU","created_at":"2026-07-05T10:09:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F6NTZIRU7IPX5OPRTYXQ6JO7W3","target":"record","payload":{"canonical_record":{"source":{"id":"2502.03095","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T11:41:43Z","cross_cats_sorted":[],"title_canon_sha256":"85828a9b965dd7870fb8cba8ca3906d2834f131a7d4f288f7b0ca116beff7440","abstract_canon_sha256":"db8e2fe46b16fde28a247f5d22843cd9c95ab713300766039ae6d3074205dace"},"schema_version":"1.0"},"canonical_sha256":"2f9b3ca234fa1f7eb9f19e2f0f25dfb6df3e2db0211913f93ee30122410e6566","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:59.575845Z","signature_b64":"+OysnPZhtr/XU66Oh7iSaNbsBE87eQ3NhdYo+79FD3BoBHiLOMMM03JWjXj5XPzIsLU/7rrVUVc3TBF7jhl7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f9b3ca234fa1f7eb9f19e2f0f25dfb6df3e2db0211913f93ee30122410e6566","last_reissued_at":"2026-07-05T10:09:59.575299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:59.575299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.03095","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":"2026-07-05T10:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xr1O2Bs8mXnDIcnBPlefbZnMyxvavrfuQ6v5lQ+iBGDtDhUps8M0v6PvMKBiRarqiMJLA+N3bKWRMRyWKrIEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T00:06:10.896985Z"},"content_sha256":"aacd93f32ff0ac197678768699ce85af11c78e5f568c4d8236252e01401d1c60","schema_version":"1.0","event_id":"sha256:aacd93f32ff0ac197678768699ce85af11c78e5f568c4d8236252e01401d1c60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F6NTZIRU7IPX5OPRTYXQ6JO7W3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feng Xu, Jinhua Zhu, Mingyang Yi, Xuerui Su, Yue Wang, Yuting Liu, Zhiming Ma","submitted_at":"2025-02-05T11:41:43Z","abstract_excerpt":"With the rapid development of Large Language Models (LLMs), numerous Reinforcement Learning from Human Feedback (RLHF) algorithms have been introduced to improve model safety and alignment with human preferences. These algorithms can be divided into two main frameworks based on whether they require an explicit reward (or value) function for training: actor-critic-based Proximal Policy Optimization (PPO) and alignment-based Direct Preference Optimization (DPO). The mismatch between DPO and PPO, such as DPO's use of a classification loss driven by human-preferred data, has raised confusion about"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03095","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/2502.03095/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":"2026-07-05T10:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVFVios9kBMCpZ7ObGEFU7WJS7VO6qsndVhSjWUw/WRx64pIgSzvXUD2sGnPeQJyC2qRtwjn+Tsjsj8mPuNQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T00:06:10.897595Z"},"content_sha256":"70d20fc85c08c323135cb3f2114bc0acc1b40af4eebd843a85dd4513f21d8f3b","schema_version":"1.0","event_id":"sha256:70d20fc85c08c323135cb3f2114bc0acc1b40af4eebd843a85dd4513f21d8f3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F6NTZIRU7IPX5OPRTYXQ6JO7W3/bundle.json","state_url":"https://pith.science/pith/F6NTZIRU7IPX5OPRTYXQ6JO7W3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F6NTZIRU7IPX5OPRTYXQ6JO7W3/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":"2026-07-17T00:06:10Z","links":{"resolver":"https://pith.science/pith/F6NTZIRU7IPX5OPRTYXQ6JO7W3","bundle":"https://pith.science/pith/F6NTZIRU7IPX5OPRTYXQ6JO7W3/bundle.json","state":"https://pith.science/pith/F6NTZIRU7IPX5OPRTYXQ6JO7W3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F6NTZIRU7IPX5OPRTYXQ6JO7W3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F6NTZIRU7IPX5OPRTYXQ6JO7W3","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":"db8e2fe46b16fde28a247f5d22843cd9c95ab713300766039ae6d3074205dace","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T11:41:43Z","title_canon_sha256":"85828a9b965dd7870fb8cba8ca3906d2834f131a7d4f288f7b0ca116beff7440"},"schema_version":"1.0","source":{"id":"2502.03095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03095","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03095v1","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03095","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"F6NTZIRU7IPX","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"F6NTZIRU7IPX5OPR","created_at":"2026-07-05T10:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"F6NTZIRU","created_at":"2026-07-05T10:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:70d20fc85c08c323135cb3f2114bc0acc1b40af4eebd843a85dd4513f21d8f3b","target":"graph","created_at":"2026-07-05T10:09:59Z","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/2502.03095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid development of Large Language Models (LLMs), numerous Reinforcement Learning from Human Feedback (RLHF) algorithms have been introduced to improve model safety and alignment with human preferences. These algorithms can be divided into two main frameworks based on whether they require an explicit reward (or value) function for training: actor-critic-based Proximal Policy Optimization (PPO) and alignment-based Direct Preference Optimization (DPO). The mismatch between DPO and PPO, such as DPO's use of a classification loss driven by human-preferred data, has raised confusion about","authors_text":"Feng Xu, Jinhua Zhu, Mingyang Yi, Xuerui Su, Yue Wang, Yuting Liu, Zhiming Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T11:41:43Z","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03095","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:aacd93f32ff0ac197678768699ce85af11c78e5f568c4d8236252e01401d1c60","target":"record","created_at":"2026-07-05T10:09:59Z","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":"db8e2fe46b16fde28a247f5d22843cd9c95ab713300766039ae6d3074205dace","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T11:41:43Z","title_canon_sha256":"85828a9b965dd7870fb8cba8ca3906d2834f131a7d4f288f7b0ca116beff7440"},"schema_version":"1.0","source":{"id":"2502.03095","kind":"arxiv","version":1}},"canonical_sha256":"2f9b3ca234fa1f7eb9f19e2f0f25dfb6df3e2db0211913f93ee30122410e6566","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f9b3ca234fa1f7eb9f19e2f0f25dfb6df3e2db0211913f93ee30122410e6566","first_computed_at":"2026-07-05T10:09:59.575299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:59.575299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+OysnPZhtr/XU66Oh7iSaNbsBE87eQ3NhdYo+79FD3BoBHiLOMMM03JWjXj5XPzIsLU/7rrVUVc3TBF7jhl7AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:59.575845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aacd93f32ff0ac197678768699ce85af11c78e5f568c4d8236252e01401d1c60","sha256:70d20fc85c08c323135cb3f2114bc0acc1b40af4eebd843a85dd4513f21d8f3b"],"state_sha256":"73b40397fa1530149975db8b209c030a8c30e3b8cd87a139bdf4f54b1a41ca31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DgLUCj3jk2sFEQUIMUqgIK5wjRqzfSGMftpYq8C2R52K89Id/GWUZfRWmggtQ0/X3syDgOF6bqUtn8A1dS1qCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T00:06:10.900610Z","bundle_sha256":"227ec4bf6a2bddd771853fa2626b1f226fa05670eb936ca332b4091259b8d2ba"}}