{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YHYIC63GLBFJEHXFKO3D22TK4G","short_pith_number":"pith:YHYIC63G","canonical_record":{"source":{"id":"2506.12725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-15T05:32:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4d9d826855aa937517cc709492cfbfb9913092a5de7c3ef09a0f46ed3e77d061","abstract_canon_sha256":"3c812a18e70708a8477f10c1fc5f7077d158dca66a070e49d945e780ba730b9a"},"schema_version":"1.0"},"canonical_sha256":"c1f0817b66584a921ee553b63d6a6ae1a397f164b02fc5329a2aa4359d967386","source":{"kind":"arxiv","id":"2506.12725","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12725","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12725v1","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12725","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"YHYIC63GLBFJ","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"YHYIC63GLBFJEHXF","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"YHYIC63G","created_at":"2026-07-05T11:21:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YHYIC63GLBFJEHXFKO3D22TK4G","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-15T05:32:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4d9d826855aa937517cc709492cfbfb9913092a5de7c3ef09a0f46ed3e77d061","abstract_canon_sha256":"3c812a18e70708a8477f10c1fc5f7077d158dca66a070e49d945e780ba730b9a"},"schema_version":"1.0"},"canonical_sha256":"c1f0817b66584a921ee553b63d6a6ae1a397f164b02fc5329a2aa4359d967386","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:58.387219Z","signature_b64":"Veg90MxdjhVbOJUPkIptq4uHcD/VMDumVamNdxog9ctM4X5+8k2HVFhwYcPmEfgtMzA35xZYF0rwws7E3VNnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1f0817b66584a921ee553b63d6a6ae1a397f164b02fc5329a2aa4359d967386","last_reissued_at":"2026-07-05T11:21:58.386726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:58.386726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12725","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":"2026-07-05T11:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BoEZ4YHXtnHikwL3oQP1mUCvp+uEezgXm76D/L6For1l8Xdgn7awFnSQrPbr6VI82LECip9SybQUiECKP4fzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:30:35.374797Z"},"content_sha256":"23744f0cf79505b2d4b3654d0eecbf38b4afc668ba69163305a0f9e25b4966c7","schema_version":"1.0","event_id":"sha256:23744f0cf79505b2d4b3654d0eecbf38b4afc668ba69163305a0f9e25b4966c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YHYIC63GLBFJEHXFKO3D22TK4G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking DPO: The Role of Rejected Responses in Preference Misalignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Byung-Jun Lee, Jay Hyeon Cho, JunHyeok Oh, Myunsoo Kim","submitted_at":"2025-06-15T05:32:07Z","abstract_excerpt":"Direct Preference Optimization (DPO) is a simple and efficient framework that has attracted substantial attention. However, it often struggles to meet its primary objectives -- increasing the generation probability of chosen responses while reducing that of rejected responses -- due to the dominant influence of rejected responses on the loss function. This imbalance leads to suboptimal performance in promoting preferred responses. In this work, we systematically analyze the limitations of DPO and existing algorithms designed to achieve the objectives stated above. To address these limitations,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12725","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/2506.12725/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":"2026-07-05T11:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fhsnTGUShMmyUA+bOHxD1QGza1PaLMxpjHEIHV0wk63f7iYNx180wGi42uhcigSJQLaHm68hzP09xdlVAjRPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:30:35.376255Z"},"content_sha256":"d4e51c18379906c298a8e760ec9d38aaa832985333955d0a4a305182b5018ff0","schema_version":"1.0","event_id":"sha256:d4e51c18379906c298a8e760ec9d38aaa832985333955d0a4a305182b5018ff0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YHYIC63GLBFJEHXFKO3D22TK4G/bundle.json","state_url":"https://pith.science/pith/YHYIC63GLBFJEHXFKO3D22TK4G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YHYIC63GLBFJEHXFKO3D22TK4G/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":"2026-08-09T13:30:35Z","links":{"resolver":"https://pith.science/pith/YHYIC63GLBFJEHXFKO3D22TK4G","bundle":"https://pith.science/pith/YHYIC63GLBFJEHXFKO3D22TK4G/bundle.json","state":"https://pith.science/pith/YHYIC63GLBFJEHXFKO3D22TK4G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YHYIC63GLBFJEHXFKO3D22TK4G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YHYIC63GLBFJEHXFKO3D22TK4G","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":"3c812a18e70708a8477f10c1fc5f7077d158dca66a070e49d945e780ba730b9a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-15T05:32:07Z","title_canon_sha256":"4d9d826855aa937517cc709492cfbfb9913092a5de7c3ef09a0f46ed3e77d061"},"schema_version":"1.0","source":{"id":"2506.12725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12725","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12725v1","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12725","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"YHYIC63GLBFJ","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"YHYIC63GLBFJEHXF","created_at":"2026-07-05T11:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"YHYIC63G","created_at":"2026-07-05T11:21:58Z"}],"graph_snapshots":[{"event_id":"sha256:d4e51c18379906c298a8e760ec9d38aaa832985333955d0a4a305182b5018ff0","target":"graph","created_at":"2026-07-05T11:21:58Z","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/2506.12725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) is a simple and efficient framework that has attracted substantial attention. However, it often struggles to meet its primary objectives -- increasing the generation probability of chosen responses while reducing that of rejected responses -- due to the dominant influence of rejected responses on the loss function. This imbalance leads to suboptimal performance in promoting preferred responses. In this work, we systematically analyze the limitations of DPO and existing algorithms designed to achieve the objectives stated above. To address these limitations,","authors_text":"Byung-Jun Lee, Jay Hyeon Cho, JunHyeok Oh, Myunsoo Kim","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-15T05:32:07Z","title":"Rethinking DPO: The Role of Rejected Responses in Preference Misalignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12725","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":"sha256:23744f0cf79505b2d4b3654d0eecbf38b4afc668ba69163305a0f9e25b4966c7","target":"record","created_at":"2026-07-05T11:21:58Z","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":"3c812a18e70708a8477f10c1fc5f7077d158dca66a070e49d945e780ba730b9a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-15T05:32:07Z","title_canon_sha256":"4d9d826855aa937517cc709492cfbfb9913092a5de7c3ef09a0f46ed3e77d061"},"schema_version":"1.0","source":{"id":"2506.12725","kind":"arxiv","version":1}},"canonical_sha256":"c1f0817b66584a921ee553b63d6a6ae1a397f164b02fc5329a2aa4359d967386","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1f0817b66584a921ee553b63d6a6ae1a397f164b02fc5329a2aa4359d967386","first_computed_at":"2026-07-05T11:21:58.386726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:58.386726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Veg90MxdjhVbOJUPkIptq4uHcD/VMDumVamNdxog9ctM4X5+8k2HVFhwYcPmEfgtMzA35xZYF0rwws7E3VNnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:58.387219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23744f0cf79505b2d4b3654d0eecbf38b4afc668ba69163305a0f9e25b4966c7","sha256:d4e51c18379906c298a8e760ec9d38aaa832985333955d0a4a305182b5018ff0"],"state_sha256":"47c6153d15a623ea7997c41342fa923478fbc4c6f06bcdb5979bf8885021b918"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LwQLajfjvM9dwGLgPO6uk5LSlgeAGYqXvmasA3NC8AwpR96TmtEDnMCDE+KZ7je3VPIile5cM+ONEA2HjTEzDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:30:35.382578Z","bundle_sha256":"8097d7d35d1d8355fd51b8cbf2c71d39a80cd0b462d60b2f9a66b978056f2cf1"}}