{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HORDPZCM7SHXUJ5XQN3I4VCMJP","short_pith_number":"pith:HORDPZCM","canonical_record":{"source":{"id":"2407.13709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:08:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b6293ff1914843898568a9b9985865f963f9de760a1c3a853047f7043375989f","abstract_canon_sha256":"8022f9380b4d5955594f2550c4b81a4cff2a5a2802a28c7835f0aa4c12dba7fd"},"schema_version":"1.0"},"canonical_sha256":"3ba237e44cfc8f7a27b783768e544c4be9eb181aafb73b132a3eae23d606eb43","source":{"kind":"arxiv","id":"2407.13709","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13709","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13709v2","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13709","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"pith_short_12","alias_value":"HORDPZCM7SHX","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"pith_short_16","alias_value":"HORDPZCM7SHXUJ5X","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"pith_short_8","alias_value":"HORDPZCM","created_at":"2026-07-05T08:58:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HORDPZCM7SHXUJ5XQN3I4VCMJP","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:08:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b6293ff1914843898568a9b9985865f963f9de760a1c3a853047f7043375989f","abstract_canon_sha256":"8022f9380b4d5955594f2550c4b81a4cff2a5a2802a28c7835f0aa4c12dba7fd"},"schema_version":"1.0"},"canonical_sha256":"3ba237e44cfc8f7a27b783768e544c4be9eb181aafb73b132a3eae23d606eb43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:16.399588Z","signature_b64":"Eacv1yquh61/FciF6YL7Zz+TXiaKlP7jxXDBIRG5eN/ZTLoruMt9siROqFXg+HKu2E8aOIv5d1u7rJfIM6FKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ba237e44cfc8f7a27b783768e544c4be9eb181aafb73b132a3eae23d606eb43","last_reissued_at":"2026-07-05T08:58:16.399024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:16.399024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13709","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":"2026-07-05T08:58:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aNqISYuhV80ZfyM9AQUYt7ndaCA51x6/1XQ2pV3mie4kEx8kFhgO8duuOrIQ0LGKP0l2dFA/yf6+p4ndrfejAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:38:32.369488Z"},"content_sha256":"4bce11fe28288055d50b283bf7f699e4853aa72d78f35c5be5a78104a3f8420b","schema_version":"1.0","event_id":"sha256:4bce11fe28288055d50b283bf7f699e4853aa72d78f35c5be5a78104a3f8420b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HORDPZCM7SHXUJ5XQN3I4VCMJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Reference Policies in Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Pengfei Liu, Yixin Liu","submitted_at":"2024-07-18T17:08:10Z","abstract_excerpt":"Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference model or policy. Such reference policies, typically instantiated as the model to be further fine-tuned, are important since they can impose an upper limit on DPO's effectiveness. Therefore, we address three related research questions in this work. First, we explore the optimal strength of the KL divergence constraint in DPO, which penalizes deviations from the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13709","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/2407.13709/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":"2026-07-05T08:58:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xwU5T6gI4iqbRx8S4nCoPH5A/E290Mi/Uc9sMA3uAp/+dwnV2gafCG2HBkVnrjFbQRzBh6dDTXgzI+m4kPAHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:38:32.370382Z"},"content_sha256":"80bc0042ca4a1de887b359133f0775a6b752d82f31fd4bad38b99a16edbee89b","schema_version":"1.0","event_id":"sha256:80bc0042ca4a1de887b359133f0775a6b752d82f31fd4bad38b99a16edbee89b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HORDPZCM7SHXUJ5XQN3I4VCMJP/bundle.json","state_url":"https://pith.science/pith/HORDPZCM7SHXUJ5XQN3I4VCMJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HORDPZCM7SHXUJ5XQN3I4VCMJP/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":"2026-08-08T10:38:32Z","links":{"resolver":"https://pith.science/pith/HORDPZCM7SHXUJ5XQN3I4VCMJP","bundle":"https://pith.science/pith/HORDPZCM7SHXUJ5XQN3I4VCMJP/bundle.json","state":"https://pith.science/pith/HORDPZCM7SHXUJ5XQN3I4VCMJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HORDPZCM7SHXUJ5XQN3I4VCMJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HORDPZCM7SHXUJ5XQN3I4VCMJP","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":"8022f9380b4d5955594f2550c4b81a4cff2a5a2802a28c7835f0aa4c12dba7fd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:08:10Z","title_canon_sha256":"b6293ff1914843898568a9b9985865f963f9de760a1c3a853047f7043375989f"},"schema_version":"1.0","source":{"id":"2407.13709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13709","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13709v2","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13709","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"pith_short_12","alias_value":"HORDPZCM7SHX","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"pith_short_16","alias_value":"HORDPZCM7SHXUJ5X","created_at":"2026-07-05T08:58:16Z"},{"alias_kind":"pith_short_8","alias_value":"HORDPZCM","created_at":"2026-07-05T08:58:16Z"}],"graph_snapshots":[{"event_id":"sha256:80bc0042ca4a1de887b359133f0775a6b752d82f31fd4bad38b99a16edbee89b","target":"graph","created_at":"2026-07-05T08:58:16Z","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/2407.13709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference model or policy. Such reference policies, typically instantiated as the model to be further fine-tuned, are important since they can impose an upper limit on DPO's effectiveness. Therefore, we address three related research questions in this work. First, we explore the optimal strength of the KL divergence constraint in DPO, which penalizes deviations from the","authors_text":"Arman Cohan, Pengfei Liu, Yixin Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:08:10Z","title":"Understanding Reference Policies in Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13709","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":"sha256:4bce11fe28288055d50b283bf7f699e4853aa72d78f35c5be5a78104a3f8420b","target":"record","created_at":"2026-07-05T08:58:16Z","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":"8022f9380b4d5955594f2550c4b81a4cff2a5a2802a28c7835f0aa4c12dba7fd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:08:10Z","title_canon_sha256":"b6293ff1914843898568a9b9985865f963f9de760a1c3a853047f7043375989f"},"schema_version":"1.0","source":{"id":"2407.13709","kind":"arxiv","version":2}},"canonical_sha256":"3ba237e44cfc8f7a27b783768e544c4be9eb181aafb73b132a3eae23d606eb43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ba237e44cfc8f7a27b783768e544c4be9eb181aafb73b132a3eae23d606eb43","first_computed_at":"2026-07-05T08:58:16.399024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:16.399024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eacv1yquh61/FciF6YL7Zz+TXiaKlP7jxXDBIRG5eN/ZTLoruMt9siROqFXg+HKu2E8aOIv5d1u7rJfIM6FKCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:16.399588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bce11fe28288055d50b283bf7f699e4853aa72d78f35c5be5a78104a3f8420b","sha256:80bc0042ca4a1de887b359133f0775a6b752d82f31fd4bad38b99a16edbee89b"],"state_sha256":"4c582880acaa0a4fa413682047e29e19cabc73615876f862f7eec729d1691997"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PRvMuhbKKXX9ksa2rsOhLOAUEPUPtoYOKgSkQ7PUZw+qs/5BMeShmIa0S66QCTpWwDdeZpRe3QcE0QFRiYZEAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:38:32.384919Z","bundle_sha256":"fc69d86b67bef69cf028cfe92e557cd9927b2624d1569b3b65235f4ff79684ed"}}