{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3UJ7O2U24XG3SM2OHOXXPFPWGP","short_pith_number":"pith:3UJ7O2U2","canonical_record":{"source":{"id":"2403.19270","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T09:56:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b528bb95cdefe528ab4cdb008a42d1c2337176e35c512942e859dd0c48dc9c24","abstract_canon_sha256":"7a1c22ec0f8d0783d7d7c5613c1091cd5b7381ec2b93bc3a9321d19a0cab1ebd"},"schema_version":"1.0"},"canonical_sha256":"dd13f76a9ae5cdb9334e3baf7795f633d088466550e6c35db8115d19b541cfef","source":{"kind":"arxiv","id":"2403.19270","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19270","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19270v2","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19270","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"pith_short_12","alias_value":"3UJ7O2U24XG3","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"pith_short_16","alias_value":"3UJ7O2U24XG3SM2O","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"pith_short_8","alias_value":"3UJ7O2U2","created_at":"2026-07-05T09:16:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3UJ7O2U24XG3SM2OHOXXPFPWGP","target":"record","payload":{"canonical_record":{"source":{"id":"2403.19270","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T09:56:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b528bb95cdefe528ab4cdb008a42d1c2337176e35c512942e859dd0c48dc9c24","abstract_canon_sha256":"7a1c22ec0f8d0783d7d7c5613c1091cd5b7381ec2b93bc3a9321d19a0cab1ebd"},"schema_version":"1.0"},"canonical_sha256":"dd13f76a9ae5cdb9334e3baf7795f633d088466550e6c35db8115d19b541cfef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:47.579522Z","signature_b64":"Xs0gawier1FrmhG28skZiF2YTpgyK6bIDWDnOqywSc/DQc1Y9iVDp5Quduz+YH2g51LhgPVNjdmqDkK0IqoFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd13f76a9ae5cdb9334e3baf7795f633d088466550e6c35db8115d19b541cfef","last_reissued_at":"2026-07-05T09:16:47.579020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:47.579020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.19270","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":"2026-07-05T09:16:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ME4O6WrY6MtMsUoAChNJdh1agMwSqHpxw/kI+I3cNAD4l4n1B1A98vXPJcta1FldsninTsucj0hNRWcqFI1fBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:05:40.062282Z"},"content_sha256":"0b7ca507d9dd16b9fc6e3680dcb0ce22f041f3b641804da16da5b04f1581b95e","schema_version":"1.0","event_id":"sha256:0b7ca507d9dd16b9fc6e3680dcb0ce22f041f3b641804da16da5b04f1581b95e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3UJ7O2U24XG3SM2OHOXXPFPWGP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"sDPO: Don't Use Your Data All at Once","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjun Park, Dahyun Kim, Hyeonwoo Kim, Sanghoon Kim, Wonho Song, Yungi Kim, Yunsu Kim","submitted_at":"2024-03-28T09:56:04Z","abstract_excerpt":"As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO) for alignment tuning. This approach involves dividing the available preference datasets and utilizing them in a stepwise manner, rather than employing it all at once. We demonstrate that this method facilitates the use of more precisely aligned reference models within the DPO training framework. Furthermore, sDPO trains the final model to be more performant,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19270","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/2403.19270/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":"2026-07-05T09:16:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/3idW8+OSvxntqpOzkFGmfWnd6q3ESJFETUrS1B13Sbx9UuTOvTPeYST/CEhx1/4/r1Tgf5Fuxc5pVLgMET9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:05:40.062851Z"},"content_sha256":"945946b838655b3495f1e93116890a9af402bbd474671f3ea0d58f0b799954ff","schema_version":"1.0","event_id":"sha256:945946b838655b3495f1e93116890a9af402bbd474671f3ea0d58f0b799954ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3UJ7O2U24XG3SM2OHOXXPFPWGP/bundle.json","state_url":"https://pith.science/pith/3UJ7O2U24XG3SM2OHOXXPFPWGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3UJ7O2U24XG3SM2OHOXXPFPWGP/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":"2026-08-08T01:05:40Z","links":{"resolver":"https://pith.science/pith/3UJ7O2U24XG3SM2OHOXXPFPWGP","bundle":"https://pith.science/pith/3UJ7O2U24XG3SM2OHOXXPFPWGP/bundle.json","state":"https://pith.science/pith/3UJ7O2U24XG3SM2OHOXXPFPWGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3UJ7O2U24XG3SM2OHOXXPFPWGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3UJ7O2U24XG3SM2OHOXXPFPWGP","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":"7a1c22ec0f8d0783d7d7c5613c1091cd5b7381ec2b93bc3a9321d19a0cab1ebd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T09:56:04Z","title_canon_sha256":"b528bb95cdefe528ab4cdb008a42d1c2337176e35c512942e859dd0c48dc9c24"},"schema_version":"1.0","source":{"id":"2403.19270","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19270","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19270v2","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19270","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"pith_short_12","alias_value":"3UJ7O2U24XG3","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"pith_short_16","alias_value":"3UJ7O2U24XG3SM2O","created_at":"2026-07-05T09:16:47Z"},{"alias_kind":"pith_short_8","alias_value":"3UJ7O2U2","created_at":"2026-07-05T09:16:47Z"}],"graph_snapshots":[{"event_id":"sha256:945946b838655b3495f1e93116890a9af402bbd474671f3ea0d58f0b799954ff","target":"graph","created_at":"2026-07-05T09:16:47Z","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/2403.19270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO) for alignment tuning. This approach involves dividing the available preference datasets and utilizing them in a stepwise manner, rather than employing it all at once. We demonstrate that this method facilitates the use of more precisely aligned reference models within the DPO training framework. Furthermore, sDPO trains the final model to be more performant,","authors_text":"Chanjun Park, Dahyun Kim, Hyeonwoo Kim, Sanghoon Kim, Wonho Song, Yungi Kim, Yunsu Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T09:56:04Z","title":"sDPO: Don't Use Your Data All at Once"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19270","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":"sha256:0b7ca507d9dd16b9fc6e3680dcb0ce22f041f3b641804da16da5b04f1581b95e","target":"record","created_at":"2026-07-05T09:16:47Z","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":"7a1c22ec0f8d0783d7d7c5613c1091cd5b7381ec2b93bc3a9321d19a0cab1ebd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T09:56:04Z","title_canon_sha256":"b528bb95cdefe528ab4cdb008a42d1c2337176e35c512942e859dd0c48dc9c24"},"schema_version":"1.0","source":{"id":"2403.19270","kind":"arxiv","version":2}},"canonical_sha256":"dd13f76a9ae5cdb9334e3baf7795f633d088466550e6c35db8115d19b541cfef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd13f76a9ae5cdb9334e3baf7795f633d088466550e6c35db8115d19b541cfef","first_computed_at":"2026-07-05T09:16:47.579020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:47.579020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xs0gawier1FrmhG28skZiF2YTpgyK6bIDWDnOqywSc/DQc1Y9iVDp5Quduz+YH2g51LhgPVNjdmqDkK0IqoFDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:47.579522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19270","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b7ca507d9dd16b9fc6e3680dcb0ce22f041f3b641804da16da5b04f1581b95e","sha256:945946b838655b3495f1e93116890a9af402bbd474671f3ea0d58f0b799954ff"],"state_sha256":"0c95fd72ce48bf14b459b2dd3e1fc3fa99bdf3fc65518edd5e335701abeea2b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iarsq0EjBtZ+ENh5IQfo263TWDsLvY8PusA2O32EeVkkwTawT0dwg9FHbp4VxXbBSneVxyGSkAXdUMHqydAfCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:05:40.109421Z","bundle_sha256":"c9ff6e88b47a0d759c405ab48b692a152e010358c1b629815138cac1d02e18e9"}}