{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TYK2OGEGBOLWX2D7E3JGHONR5P","short_pith_number":"pith:TYK2OGEG","canonical_record":{"source":{"id":"2410.06293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T18:51:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"db6d0f55d27d4516c1526ae20399beadfe1d8d90c0ef9d533291b9c2b6da9682","abstract_canon_sha256":"06803fbe586290439e3817e60c973948025ffa0a67e5029adf51a3166c271e7d"},"schema_version":"1.0"},"canonical_sha256":"9e15a718860b976be87f26d263b9b1ebca61826f7220aa1fe76c49aa41e9ef5d","source":{"kind":"arxiv","id":"2410.06293","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06293","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06293v1","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06293","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"TYK2OGEGBOLW","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"TYK2OGEGBOLWX2D7","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"TYK2OGEG","created_at":"2026-07-05T09:17:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TYK2OGEGBOLWX2D7E3JGHONR5P","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T18:51:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"db6d0f55d27d4516c1526ae20399beadfe1d8d90c0ef9d533291b9c2b6da9682","abstract_canon_sha256":"06803fbe586290439e3817e60c973948025ffa0a67e5029adf51a3166c271e7d"},"schema_version":"1.0"},"canonical_sha256":"9e15a718860b976be87f26d263b9b1ebca61826f7220aa1fe76c49aa41e9ef5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:59.447432Z","signature_b64":"miYvr38OF4lbb96C//0MwfE7xuuKaF064SGCU0hAPUoZHquZTJnTVTn2Ao4SAEctN3qIRwHlUs6+VmuZRrlGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e15a718860b976be87f26d263b9b1ebca61826f7220aa1fe76c49aa41e9ef5d","last_reissued_at":"2026-07-05T09:17:59.446887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:59.446887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06293","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":"2026-07-05T09:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SxL86QkDv5tMxaj0/ZsE8OorqP0oflp5zem1Xxo1k6uy9h+eLcqCiBMvnR4+uAch7VuKHEeAQH+DGPZVMmJADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:49:10.671738Z"},"content_sha256":"4390854dc0cd873aedba9682cd84f56e8d660524823ddf235361141706e2b2b3","schema_version":"1.0","event_id":"sha256:4390854dc0cd873aedba9682cd84f56e8d660524823ddf235361141706e2b2b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TYK2OGEGBOLWX2D7E3JGHONR5P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerated Preference Optimization for Large Language Model Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Huizhuo Yuan, Jiafan He, Quanquan Gu","submitted_at":"2024-10-08T18:51:01Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO), one of the most popular approaches, formulates RLHF as a policy optimization problem without explicitly estimating the reward function. It overcomes the stability and efficiency issues of two-step approaches, which typically involve first estimating the reward function and then optimizing the policy via proximal policy optimization (PPO). Since RLHF is essentially an optimization problem, and it is well-known tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06293","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/2410.06293/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":"2026-07-05T09:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5bP6hwQvuCotbUQ+e86zJVa5asvqKN35EScKI1uaws5KUivbyXTyAuseA83C4k8w0Ho5Y22D9xQrJadxZNRDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:49:10.672111Z"},"content_sha256":"3a69813c358613acb7c0425572ec875456d1b39b70fdedb16f46a941e49cd5b3","schema_version":"1.0","event_id":"sha256:3a69813c358613acb7c0425572ec875456d1b39b70fdedb16f46a941e49cd5b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYK2OGEGBOLWX2D7E3JGHONR5P/bundle.json","state_url":"https://pith.science/pith/TYK2OGEGBOLWX2D7E3JGHONR5P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYK2OGEGBOLWX2D7E3JGHONR5P/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":"2026-07-06T10:49:10Z","links":{"resolver":"https://pith.science/pith/TYK2OGEGBOLWX2D7E3JGHONR5P","bundle":"https://pith.science/pith/TYK2OGEGBOLWX2D7E3JGHONR5P/bundle.json","state":"https://pith.science/pith/TYK2OGEGBOLWX2D7E3JGHONR5P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYK2OGEGBOLWX2D7E3JGHONR5P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TYK2OGEGBOLWX2D7E3JGHONR5P","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":"06803fbe586290439e3817e60c973948025ffa0a67e5029adf51a3166c271e7d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T18:51:01Z","title_canon_sha256":"db6d0f55d27d4516c1526ae20399beadfe1d8d90c0ef9d533291b9c2b6da9682"},"schema_version":"1.0","source":{"id":"2410.06293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06293","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06293v1","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06293","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"TYK2OGEGBOLW","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"TYK2OGEGBOLWX2D7","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"TYK2OGEG","created_at":"2026-07-05T09:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:3a69813c358613acb7c0425572ec875456d1b39b70fdedb16f46a941e49cd5b3","target":"graph","created_at":"2026-07-05T09:17:59Z","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/2410.06293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO), one of the most popular approaches, formulates RLHF as a policy optimization problem without explicitly estimating the reward function. It overcomes the stability and efficiency issues of two-step approaches, which typically involve first estimating the reward function and then optimizing the policy via proximal policy optimization (PPO). Since RLHF is essentially an optimization problem, and it is well-known tha","authors_text":"Huizhuo Yuan, Jiafan He, Quanquan Gu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T18:51:01Z","title":"Accelerated Preference Optimization for Large Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06293","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":"sha256:4390854dc0cd873aedba9682cd84f56e8d660524823ddf235361141706e2b2b3","target":"record","created_at":"2026-07-05T09:17:59Z","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":"06803fbe586290439e3817e60c973948025ffa0a67e5029adf51a3166c271e7d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T18:51:01Z","title_canon_sha256":"db6d0f55d27d4516c1526ae20399beadfe1d8d90c0ef9d533291b9c2b6da9682"},"schema_version":"1.0","source":{"id":"2410.06293","kind":"arxiv","version":1}},"canonical_sha256":"9e15a718860b976be87f26d263b9b1ebca61826f7220aa1fe76c49aa41e9ef5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e15a718860b976be87f26d263b9b1ebca61826f7220aa1fe76c49aa41e9ef5d","first_computed_at":"2026-07-05T09:17:59.446887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:59.446887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"miYvr38OF4lbb96C//0MwfE7xuuKaF064SGCU0hAPUoZHquZTJnTVTn2Ao4SAEctN3qIRwHlUs6+VmuZRrlGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:59.447432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4390854dc0cd873aedba9682cd84f56e8d660524823ddf235361141706e2b2b3","sha256:3a69813c358613acb7c0425572ec875456d1b39b70fdedb16f46a941e49cd5b3"],"state_sha256":"58899c241b170e2c4f107c3385e38bd219798082e85a83ed4e74c334a2499e61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oiBu1pFK9c6jWjICPbzoENpBb/bng73LmlMhZB1nV9nzMFFiPKGAyxmKqulRRWcY2x21gQ1Hd2FocMlSZJGdAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:49:10.675014Z","bundle_sha256":"4931fbebf1670219ffff201ae3241073e8d78d78570a6b845ea4ce4df699de46"}}