{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y2TKICKAK2YGTW5XNRGWH7IWDA","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":"2249997031ee26ed620b230c128fe30272dc9759a113b2ffbac696922fbb7850","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T16:21:18Z","title_canon_sha256":"814b14d176b816fa00061d31d6915ee586fda73c282b601b3b9c420944b0da0e"},"schema_version":"1.0","source":{"id":"2407.08639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08639","created_at":"2026-07-05T09:19:30Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08639v2","created_at":"2026-07-05T09:19:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08639","created_at":"2026-07-05T09:19:30Z"},{"alias_kind":"pith_short_12","alias_value":"Y2TKICKAK2YG","created_at":"2026-07-05T09:19:30Z"},{"alias_kind":"pith_short_16","alias_value":"Y2TKICKAK2YGTW5X","created_at":"2026-07-05T09:19:30Z"},{"alias_kind":"pith_short_8","alias_value":"Y2TKICKA","created_at":"2026-07-05T09:19:30Z"}],"graph_snapshots":[{"event_id":"sha256:4174013c8ac511be85260b78b7d4096f926c880b47bc3ae41261134222d60ed0","target":"graph","created_at":"2026-07-05T09:19:30Z","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/2407.08639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO is sensitive to the fine-tuning of its trade-off parameter $\\beta$, as well as to the quality of the preference data. We analyze the impact of $\\beta$ and data quality on DPO, uncovering that optimal $\\beta$ values vary with the informativeness of pairwise data. Addressing the limitations of static $\\beta$ values, we introduce a novel framework that dynamically calibrates $\\beta$ at the batch level, informed by data ","authors_text":"Bolin Ding, Jiancan Wu, Jinyang Gao, Junkang Wu, Xiangnan He, Xiang Wang, Yuexiang Xie, Zhengyi Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T16:21:18Z","title":"$\\beta$-DPO: Direct Preference Optimization with Dynamic $\\beta$"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08639","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:ad1c1994966465b00abb5a818dd5be13ce74f6c7b108f9e001891db325436520","target":"record","created_at":"2026-07-05T09:19:30Z","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":"2249997031ee26ed620b230c128fe30272dc9759a113b2ffbac696922fbb7850","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T16:21:18Z","title_canon_sha256":"814b14d176b816fa00061d31d6915ee586fda73c282b601b3b9c420944b0da0e"},"schema_version":"1.0","source":{"id":"2407.08639","kind":"arxiv","version":2}},"canonical_sha256":"c6a6a4094056b069dbb76c4d63fd16180bb23430e86c520fb68e59ccd177eefb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6a6a4094056b069dbb76c4d63fd16180bb23430e86c520fb68e59ccd177eefb","first_computed_at":"2026-07-05T09:19:30.018970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:30.018970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NPM6Mdcqx0s1BV639z0rJPSz/AywPmfSXesIdB19RhtxdXHFtJOHp5PRMPKeSGLz5gAP7JHHtwmdMBealajfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:30.019452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad1c1994966465b00abb5a818dd5be13ce74f6c7b108f9e001891db325436520","sha256:4174013c8ac511be85260b78b7d4096f926c880b47bc3ae41261134222d60ed0"],"state_sha256":"61c66abe4eacf147dcbef57949a63557c4018a3188b0c2f616b883338b733e4a"}