{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DAKY2JHEPGFAD44OBQYUBC6PMM","short_pith_number":"pith:DAKY2JHE","canonical_record":{"source":{"id":"2411.05875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T23:03:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"902778af8ee6c89fdf978dc1971d859ddb79c2357916cf1e74d03077f7f4b665","abstract_canon_sha256":"2eb5403d88ef7cbe6e1c95c2b4eea1c12bf0c056a1fcd4f6809f994a3db55d75"},"schema_version":"1.0"},"canonical_sha256":"18158d24e4798a01f38e0c31408bcf631508e4a6e1d670b5ed99dfc59e6fc7b4","source":{"kind":"arxiv","id":"2411.05875","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05875","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05875v1","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05875","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_12","alias_value":"DAKY2JHEPGFA","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"DAKY2JHEPGFAD44O","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"DAKY2JHE","created_at":"2026-07-05T09:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DAKY2JHEPGFAD44OBQYUBC6PMM","target":"record","payload":{"canonical_record":{"source":{"id":"2411.05875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T23:03:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"902778af8ee6c89fdf978dc1971d859ddb79c2357916cf1e74d03077f7f4b665","abstract_canon_sha256":"2eb5403d88ef7cbe6e1c95c2b4eea1c12bf0c056a1fcd4f6809f994a3db55d75"},"schema_version":"1.0"},"canonical_sha256":"18158d24e4798a01f38e0c31408bcf631508e4a6e1d670b5ed99dfc59e6fc7b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:12.454630Z","signature_b64":"NQl98nP992kAyPLn+llSEEh/Jzly7Cy5Y1BJlK1HZ4pV+rJewpIhlJ4+Hv7e+x+Jtzxj5wkjExAlNxyCn3EKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18158d24e4798a01f38e0c31408bcf631508e4a6e1d670b5ed99dfc59e6fc7b4","last_reissued_at":"2026-07-05T09:33:12.454110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:12.454110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.05875","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":"2026-07-05T09:33:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6k6MfheZVZBNMxF9IrLh1lTAUbfDiH58wzpTAuwLzmObXPjiMbp7OsKxtCNeSLJ1sZyW+HvpQZmF7akuewgjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T09:02:05.478672Z"},"content_sha256":"cea45f6dd0bb0780d698632d2c2ebcd3dce17e36cc4c35712d08b361ccc5edaf","schema_version":"1.0","event_id":"sha256:cea45f6dd0bb0780d698632d2c2ebcd3dce17e36cc4c35712d08b361ccc5edaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DAKY2JHEPGFAD44OBQYUBC6PMM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Fang Liu, Jennifer Zhu, Wanyu Du, Yanjun Qi, Zhuotong Chen","submitted_at":"2024-11-07T23:03:11Z","abstract_excerpt":"Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from unstable preference optimization. In this work, we aim to improve the preference optimization pipeline by taking a closer look at preference data generation and training regularization techniques. For preference data generation, we demonstrate that existing scoring-based reward models produce unsatisfactory preference data and perform poorly on out-of-distr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05875","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/2411.05875/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":"2026-07-05T09:33:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FkWamFaukSb0xn7atp1tYCceLrJSC4TdQ3QsPPW56qFE+rEsU47vEx9NrvIcHHGN9rkiMkRGR0Kpp70jG0myCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T09:02:05.479045Z"},"content_sha256":"e3b13c7527a57d67a713af85421d8d3194e0966869466895e7a2fa7f364cb085","schema_version":"1.0","event_id":"sha256:e3b13c7527a57d67a713af85421d8d3194e0966869466895e7a2fa7f364cb085"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAKY2JHEPGFAD44OBQYUBC6PMM/bundle.json","state_url":"https://pith.science/pith/DAKY2JHEPGFAD44OBQYUBC6PMM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAKY2JHEPGFAD44OBQYUBC6PMM/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":"2026-07-27T09:02:05Z","links":{"resolver":"https://pith.science/pith/DAKY2JHEPGFAD44OBQYUBC6PMM","bundle":"https://pith.science/pith/DAKY2JHEPGFAD44OBQYUBC6PMM/bundle.json","state":"https://pith.science/pith/DAKY2JHEPGFAD44OBQYUBC6PMM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAKY2JHEPGFAD44OBQYUBC6PMM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DAKY2JHEPGFAD44OBQYUBC6PMM","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":"2eb5403d88ef7cbe6e1c95c2b4eea1c12bf0c056a1fcd4f6809f994a3db55d75","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T23:03:11Z","title_canon_sha256":"902778af8ee6c89fdf978dc1971d859ddb79c2357916cf1e74d03077f7f4b665"},"schema_version":"1.0","source":{"id":"2411.05875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05875","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05875v1","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05875","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_12","alias_value":"DAKY2JHEPGFA","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"DAKY2JHEPGFAD44O","created_at":"2026-07-05T09:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"DAKY2JHE","created_at":"2026-07-05T09:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:e3b13c7527a57d67a713af85421d8d3194e0966869466895e7a2fa7f364cb085","target":"graph","created_at":"2026-07-05T09:33:12Z","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/2411.05875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from unstable preference optimization. In this work, we aim to improve the preference optimization pipeline by taking a closer look at preference data generation and training regularization techniques. For preference data generation, we demonstrate that existing scoring-based reward models produce unsatisfactory preference data and perform poorly on out-of-distr","authors_text":"Fang Liu, Jennifer Zhu, Wanyu Du, Yanjun Qi, Zhuotong Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T23:03:11Z","title":"Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05875","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:cea45f6dd0bb0780d698632d2c2ebcd3dce17e36cc4c35712d08b361ccc5edaf","target":"record","created_at":"2026-07-05T09:33:12Z","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":"2eb5403d88ef7cbe6e1c95c2b4eea1c12bf0c056a1fcd4f6809f994a3db55d75","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T23:03:11Z","title_canon_sha256":"902778af8ee6c89fdf978dc1971d859ddb79c2357916cf1e74d03077f7f4b665"},"schema_version":"1.0","source":{"id":"2411.05875","kind":"arxiv","version":1}},"canonical_sha256":"18158d24e4798a01f38e0c31408bcf631508e4a6e1d670b5ed99dfc59e6fc7b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18158d24e4798a01f38e0c31408bcf631508e4a6e1d670b5ed99dfc59e6fc7b4","first_computed_at":"2026-07-05T09:33:12.454110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:12.454110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NQl98nP992kAyPLn+llSEEh/Jzly7Cy5Y1BJlK1HZ4pV+rJewpIhlJ4+Hv7e+x+Jtzxj5wkjExAlNxyCn3EKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:12.454630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cea45f6dd0bb0780d698632d2c2ebcd3dce17e36cc4c35712d08b361ccc5edaf","sha256:e3b13c7527a57d67a713af85421d8d3194e0966869466895e7a2fa7f364cb085"],"state_sha256":"65ec12dcc6ab9d8a17f7ed233d255947e1eadc7063359ba7bfb4059cae6b1f32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jl8HJewm9NExXLDjf7AHCS1diPJRp/rAZMIKj0I+tCqesatzYoUfYwULjJyoPdqQ9i5ymKrB4s8bSS/55qslBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T09:02:05.481533Z","bundle_sha256":"fdb9ef9ccb5c35c5c27f5ae85606b8965bd3956bf00a2e463777fa84b6489e86"}}