{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XEFLY7S2QND6PUP2QQ5CVZAU5L","short_pith_number":"pith:XEFLY7S2","canonical_record":{"source":{"id":"2506.03557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:21:01Z","cross_cats_sorted":[],"title_canon_sha256":"62f8a5b6cce7072fc103518a92d7bbf36c502319c1ac1e8832b2856197490771","abstract_canon_sha256":"8a0f15c0fdb01a601f053484f5ed6b688be5c3b6bc79e2b5097be75ea2155f04"},"schema_version":"1.0"},"canonical_sha256":"b90abc7e5a8347e7d1fa843a2ae414ead878cf0cd02d4566a990b0fb45b986dd","source":{"kind":"arxiv","id":"2506.03557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03557","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03557v1","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03557","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"XEFLY7S2QND6","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"XEFLY7S2QND6PUP2","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"XEFLY7S2","created_at":"2026-07-05T11:15:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XEFLY7S2QND6PUP2QQ5CVZAU5L","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:21:01Z","cross_cats_sorted":[],"title_canon_sha256":"62f8a5b6cce7072fc103518a92d7bbf36c502319c1ac1e8832b2856197490771","abstract_canon_sha256":"8a0f15c0fdb01a601f053484f5ed6b688be5c3b6bc79e2b5097be75ea2155f04"},"schema_version":"1.0"},"canonical_sha256":"b90abc7e5a8347e7d1fa843a2ae414ead878cf0cd02d4566a990b0fb45b986dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:29.767736Z","signature_b64":"6H7QSRVwafWlnDvf/LmAz/BKexgfKluvHo28YoBBnQC2PdSvbTycLCz/6f9xCDlYRhQkldMymKflnPVmXJywDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b90abc7e5a8347e7d1fa843a2ae414ead878cf0cd02d4566a990b0fb45b986dd","last_reissued_at":"2026-07-05T11:15:29.767161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:29.767161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03557","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":"2026-07-05T11:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxknFBkGvyeuISOmbs+yuHigsh6oj+zEvggn5gsLJB10IfcLLXDCEjxoX3m5h4zSFHDq87c227vV7rCCDWPBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:31:58.384183Z"},"content_sha256":"22260baeb533a9ceb124d155ed8ef9e816fc27ba235ee7d30798ee63ec945644","schema_version":"1.0","event_id":"sha256:22260baeb533a9ceb124d155ed8ef9e816fc27ba235ee7d30798ee63ec945644"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XEFLY7S2QND6PUP2QQ5CVZAU5L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BPO: Revisiting Preference Modeling in Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingyang Li, Chuang Liu, Lin Sun, Ning Wu, Peng Liu, Weijia Lu","submitted_at":"2025-06-04T04:21:01Z","abstract_excerpt":"Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative ordering between chosen and rejected responses through pairwise ranking losses, it often neglects absolute reward magnitudes. This oversight can decrease the likelihood of chosen responses and increase the risk of generating out-of-distribution responses, leading to poor performance. We term this issue Degraded Chosen Responses (DCR).To address this issue, we propose Balanced Preference Optimization (BPO), a novel f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03557","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/2506.03557/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":"2026-07-05T11:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8XNAGmv6xwKjVPsHrukbXq93elaizL26hD1xH9uaetxtuzn9vsnL7L/F7FH0t9i8xSC5/nAXfDyB9QXHnYdSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:31:58.384726Z"},"content_sha256":"3d9f26f333bee3975c9299be366850f7644cfaaaba7a4201f994fcc3881806be","schema_version":"1.0","event_id":"sha256:3d9f26f333bee3975c9299be366850f7644cfaaaba7a4201f994fcc3881806be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XEFLY7S2QND6PUP2QQ5CVZAU5L/bundle.json","state_url":"https://pith.science/pith/XEFLY7S2QND6PUP2QQ5CVZAU5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XEFLY7S2QND6PUP2QQ5CVZAU5L/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":"2026-08-14T14:31:58Z","links":{"resolver":"https://pith.science/pith/XEFLY7S2QND6PUP2QQ5CVZAU5L","bundle":"https://pith.science/pith/XEFLY7S2QND6PUP2QQ5CVZAU5L/bundle.json","state":"https://pith.science/pith/XEFLY7S2QND6PUP2QQ5CVZAU5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XEFLY7S2QND6PUP2QQ5CVZAU5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XEFLY7S2QND6PUP2QQ5CVZAU5L","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":"8a0f15c0fdb01a601f053484f5ed6b688be5c3b6bc79e2b5097be75ea2155f04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:21:01Z","title_canon_sha256":"62f8a5b6cce7072fc103518a92d7bbf36c502319c1ac1e8832b2856197490771"},"schema_version":"1.0","source":{"id":"2506.03557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03557","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03557v1","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03557","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"XEFLY7S2QND6","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"XEFLY7S2QND6PUP2","created_at":"2026-07-05T11:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"XEFLY7S2","created_at":"2026-07-05T11:15:29Z"}],"graph_snapshots":[{"event_id":"sha256:3d9f26f333bee3975c9299be366850f7644cfaaaba7a4201f994fcc3881806be","target":"graph","created_at":"2026-07-05T11:15:29Z","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/2506.03557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative ordering between chosen and rejected responses through pairwise ranking losses, it often neglects absolute reward magnitudes. This oversight can decrease the likelihood of chosen responses and increase the risk of generating out-of-distribution responses, leading to poor performance. We term this issue Degraded Chosen Responses (DCR).To address this issue, we propose Balanced Preference Optimization (BPO), a novel f","authors_text":"Bingyang Li, Chuang Liu, Lin Sun, Ning Wu, Peng Liu, Weijia Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:21:01Z","title":"BPO: Revisiting Preference Modeling in Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03557","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":"sha256:22260baeb533a9ceb124d155ed8ef9e816fc27ba235ee7d30798ee63ec945644","target":"record","created_at":"2026-07-05T11:15:29Z","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":"8a0f15c0fdb01a601f053484f5ed6b688be5c3b6bc79e2b5097be75ea2155f04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:21:01Z","title_canon_sha256":"62f8a5b6cce7072fc103518a92d7bbf36c502319c1ac1e8832b2856197490771"},"schema_version":"1.0","source":{"id":"2506.03557","kind":"arxiv","version":1}},"canonical_sha256":"b90abc7e5a8347e7d1fa843a2ae414ead878cf0cd02d4566a990b0fb45b986dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b90abc7e5a8347e7d1fa843a2ae414ead878cf0cd02d4566a990b0fb45b986dd","first_computed_at":"2026-07-05T11:15:29.767161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:29.767161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6H7QSRVwafWlnDvf/LmAz/BKexgfKluvHo28YoBBnQC2PdSvbTycLCz/6f9xCDlYRhQkldMymKflnPVmXJywDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:29.767736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22260baeb533a9ceb124d155ed8ef9e816fc27ba235ee7d30798ee63ec945644","sha256:3d9f26f333bee3975c9299be366850f7644cfaaaba7a4201f994fcc3881806be"],"state_sha256":"73e8c48f3ed36a463c8b0949f681b22b5df1d158c73d3385d55240f023cfa33c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UiawbCD+zdzQ9t3qWaMRVo1QsC17+rHZprtV0pYMD1SlM4AmgyeWdjZqoOKLehibzbv05XST2jWxs7xqKNY7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:31:58.390804Z","bundle_sha256":"3cd666ddbb0584ec9426abc87bc1318b8453303da4be509232d2798518c746db"}}