{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5VFGFXMWA5TSPNCBWYK3W7MLIW","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":"77f91d3b47c11e9d41918208159936b9235d45ccf759de2796b5747145bfc990","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-29T07:53:50Z","title_canon_sha256":"6f57f5162c7bb0a62b2a92db47ba3848fc6efdab4f379c7683d340c0291a1056"},"schema_version":"1.0","source":{"id":"2409.19605","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19605","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19605v3","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19605","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"5VFGFXMWA5TS","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"5VFGFXMWA5TSPNCB","created_at":"2026-07-05T10:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"5VFGFXMW","created_at":"2026-07-05T10:08:21Z"}],"graph_snapshots":[{"event_id":"sha256:3e3f4b4319cd8219aa29ddea320e0c0e9c5d4f8f4b23f599803d78131d79a17c","target":"graph","created_at":"2026-07-05T10:08:21Z","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/2409.19605/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 stable, scalable, and efficient solution for language model alignment. Despite its empirical success, the optimization properties, particularly the impact of samplers on its convergence rates, remain under-explored. In this paper, we provide a rigorous analysis of DPO's convergence rates with different sampling strategies under the exact gradient setting, revealing a surprising separation: uniform sampling achieves $\\textbf{linear}$ convergence, while our proposed online sampler achieves $\\textbf{quadratic}$ convergence. We further adapt th","authors_text":"Ruizhe Shi, Runlong Zhou, Simon S. Du","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-29T07:53:50Z","title":"The Crucial Role of Samplers in Online Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19605","kind":"arxiv","version":3},"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":"sha256:0590d822ad7551ada32886f1ae5e4da7e4f1cf62a21f745ac01a33161c3e7063","target":"record","created_at":"2026-07-05T10:08:21Z","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":"77f91d3b47c11e9d41918208159936b9235d45ccf759de2796b5747145bfc990","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-29T07:53:50Z","title_canon_sha256":"6f57f5162c7bb0a62b2a92db47ba3848fc6efdab4f379c7683d340c0291a1056"},"schema_version":"1.0","source":{"id":"2409.19605","kind":"arxiv","version":3}},"canonical_sha256":"ed4a62dd96076727b441b615bb7d8b45bb56dc1bf741442de726d5d221614c4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed4a62dd96076727b441b615bb7d8b45bb56dc1bf741442de726d5d221614c4c","first_computed_at":"2026-07-05T10:08:21.916376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:21.916376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OIcgTJ3x48uzKhTy2n2WH9Nb87kfgkeKAAdLKdDLj3BJP2XvesH+XnR/bUdOcVPCO4iCYJc6pGHLaRsXqxZMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:21.916879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19605","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0590d822ad7551ada32886f1ae5e4da7e4f1cf62a21f745ac01a33161c3e7063","sha256:3e3f4b4319cd8219aa29ddea320e0c0e9c5d4f8f4b23f599803d78131d79a17c"],"state_sha256":"d7c7d71b646b05e9c36570ebfef94f3474887daeff59dc3d0cabd2702b292268"}