{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TVQ6NI7HK5VX53IWS7ER7LUEDO","short_pith_number":"pith:TVQ6NI7H","canonical_record":{"source":{"id":"2404.04626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T13:24:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"111eb93ae73dd3c1977fce5fc8a4ec2157ae3f4eed30156a30f2f4cd3fdfbbb5","abstract_canon_sha256":"aa566c110326665fbf1fb4aac9b6bada89c16cc412e5f163aa36a2881822bcd7"},"schema_version":"1.0"},"canonical_sha256":"9d61e6a3e7576b7eed1697c91fae841bb7d7c24c32e3d923c735375ba46b91fd","source":{"kind":"arxiv","id":"2404.04626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04626","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04626v1","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04626","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"TVQ6NI7HK5VX","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"TVQ6NI7HK5VX53IW","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"TVQ6NI7H","created_at":"2026-07-05T08:05:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TVQ6NI7HK5VX53IWS7ER7LUEDO","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T13:24:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"111eb93ae73dd3c1977fce5fc8a4ec2157ae3f4eed30156a30f2f4cd3fdfbbb5","abstract_canon_sha256":"aa566c110326665fbf1fb4aac9b6bada89c16cc412e5f163aa36a2881822bcd7"},"schema_version":"1.0"},"canonical_sha256":"9d61e6a3e7576b7eed1697c91fae841bb7d7c24c32e3d923c735375ba46b91fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:19.293827Z","signature_b64":"Ed+m+Rb35IZXNPqvX6VWFhXVYYMpaDbngBHDhfTmIyJ4S3K6lUVcYaMZWp3Oxv/tW9bs4Sspc2aEFmU/oBDVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d61e6a3e7576b7eed1697c91fae841bb7d7c24c32e3d923c735375ba46b91fd","last_reissued_at":"2026-07-05T08:05:19.293479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:19.293479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04626","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":"2026-07-05T08:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SNJ4Vbji/xUaGrENJnktxr6+t9JtvuikKO7aX2Ot7Q8fAaook7jQ7aEyh+1p8bGRxdZj6shpKf2bubgEYHHNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:12:32.918157Z"},"content_sha256":"bb4ba11803a2beb9643acb77ed0347aeedc31a2e32709c08aa8dd250cc1fec3f","schema_version":"1.0","event_id":"sha256:bb4ba11803a2beb9643acb77ed0347aeedc31a2e32709c08aa8dd250cc1fec3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TVQ6NI7HK5VX53IWS7ER7LUEDO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowen Qin, Chen Huang, Duanyu Feng, Wenqiang Lei, Zheng Zhang","submitted_at":"2024-04-06T13:24:37Z","abstract_excerpt":"Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across various tasks, DPO has been criticized for its sensitivity to the SFT's effectiveness and its hindrance to the learning capacity towards human-preferred responses, leading to less satisfactory performance. To overcome those limitations, the theoretical understanding of DPO are indispensable but still lacking. To this end, we take a step towards theoretically analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04626","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/2404.04626/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":"2026-07-05T08:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Er7QbqM0McUnw5vf8DohWY74wkxahMoZJXObEr2JVosprfDWbekUHiKQTvyUpgb4Q4VKdG3SZsXWBPQlYZYCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:12:32.918675Z"},"content_sha256":"2150441250c38e616b1a921e24bbbe2fa4b030c4332710b390e2bbce7833775a","schema_version":"1.0","event_id":"sha256:2150441250c38e616b1a921e24bbbe2fa4b030c4332710b390e2bbce7833775a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TVQ6NI7HK5VX53IWS7ER7LUEDO/bundle.json","state_url":"https://pith.science/pith/TVQ6NI7HK5VX53IWS7ER7LUEDO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TVQ6NI7HK5VX53IWS7ER7LUEDO/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":"2026-08-09T00:12:32Z","links":{"resolver":"https://pith.science/pith/TVQ6NI7HK5VX53IWS7ER7LUEDO","bundle":"https://pith.science/pith/TVQ6NI7HK5VX53IWS7ER7LUEDO/bundle.json","state":"https://pith.science/pith/TVQ6NI7HK5VX53IWS7ER7LUEDO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TVQ6NI7HK5VX53IWS7ER7LUEDO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TVQ6NI7HK5VX53IWS7ER7LUEDO","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":"aa566c110326665fbf1fb4aac9b6bada89c16cc412e5f163aa36a2881822bcd7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T13:24:37Z","title_canon_sha256":"111eb93ae73dd3c1977fce5fc8a4ec2157ae3f4eed30156a30f2f4cd3fdfbbb5"},"schema_version":"1.0","source":{"id":"2404.04626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04626","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04626v1","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04626","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"TVQ6NI7HK5VX","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"TVQ6NI7HK5VX53IW","created_at":"2026-07-05T08:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"TVQ6NI7H","created_at":"2026-07-05T08:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:2150441250c38e616b1a921e24bbbe2fa4b030c4332710b390e2bbce7833775a","target":"graph","created_at":"2026-07-05T08:05:19Z","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/2404.04626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across various tasks, DPO has been criticized for its sensitivity to the SFT's effectiveness and its hindrance to the learning capacity towards human-preferred responses, leading to less satisfactory performance. To overcome those limitations, the theoretical understanding of DPO are indispensable but still lacking. To this end, we take a step towards theoretically analy","authors_text":"Bowen Qin, Chen Huang, Duanyu Feng, Wenqiang Lei, Zheng Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T13:24:37Z","title":"Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04626","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:bb4ba11803a2beb9643acb77ed0347aeedc31a2e32709c08aa8dd250cc1fec3f","target":"record","created_at":"2026-07-05T08:05:19Z","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":"aa566c110326665fbf1fb4aac9b6bada89c16cc412e5f163aa36a2881822bcd7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T13:24:37Z","title_canon_sha256":"111eb93ae73dd3c1977fce5fc8a4ec2157ae3f4eed30156a30f2f4cd3fdfbbb5"},"schema_version":"1.0","source":{"id":"2404.04626","kind":"arxiv","version":1}},"canonical_sha256":"9d61e6a3e7576b7eed1697c91fae841bb7d7c24c32e3d923c735375ba46b91fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d61e6a3e7576b7eed1697c91fae841bb7d7c24c32e3d923c735375ba46b91fd","first_computed_at":"2026-07-05T08:05:19.293479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:19.293479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ed+m+Rb35IZXNPqvX6VWFhXVYYMpaDbngBHDhfTmIyJ4S3K6lUVcYaMZWp3Oxv/tW9bs4Sspc2aEFmU/oBDVAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:19.293827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb4ba11803a2beb9643acb77ed0347aeedc31a2e32709c08aa8dd250cc1fec3f","sha256:2150441250c38e616b1a921e24bbbe2fa4b030c4332710b390e2bbce7833775a"],"state_sha256":"2e4e4577412e90b8f7d8289a6a61271c84a56071c1f052e12fd6ec651197b87f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fTJAu3QXStocdZVSYdvNaKNv0TAylZjHUlUvq3kQOoh9+r/3DWSM88YbzYOEsTk76nEMl9WGuA8lYDu1ouUpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:12:32.928177Z","bundle_sha256":"c3224a36e45c90d3c5abb5bac8231c85fb887feef572d345583a665941b04fde"}}