{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HB7NV4PM3Q3DGI2QIEPK32MXNK","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":"92774fafed989d57ad664c5ddc55f6f3dea3f6abe223de8c085c32410d5a0541","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-06T20:09:37Z","title_canon_sha256":"2e70e7b8b5d3a1eaadc27c6b3b54e4b75436b168500ef995c67fe57900034c60"},"schema_version":"1.0","source":{"id":"2510.05342","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05342","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05342v2","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05342","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"HB7NV4PM3Q3D","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"HB7NV4PM3Q3DGI2Q","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"HB7NV4PM","created_at":"2026-06-02T02:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:fdf17aa140f5f93e2a1fa2f0c1d24c6cb1e5a80f23a5f75ffebecfe47789f11f","target":"graph","created_at":"2026-06-02T02:04:48Z","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/2510.05342/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 simple and effective method for aligning large language models. However, its reliance on a fixed temperature parameter leads to suboptimal training on diverse preference data, causing overfitting on easy examples and under-learning from informative ones. Recent methods have emerged to counter this. While IPO addresses general overfitting, its uniform regularization can be overly conservative. The more targeted approach of $\\beta$-DPO suffers from its own limitations: its batch-level adaptation applies a single, compromised temperature to mi","authors_text":"Hyung Gyu Rho","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-06T20:09:37Z","title":"Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05342","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":"sha256:1deb31aeadccaed6fedfdb1797af2f7b77bce3232dd5fd26c0e4693f690b28ce","target":"record","created_at":"2026-06-02T02:04:48Z","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":"92774fafed989d57ad664c5ddc55f6f3dea3f6abe223de8c085c32410d5a0541","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-06T20:09:37Z","title_canon_sha256":"2e70e7b8b5d3a1eaadc27c6b3b54e4b75436b168500ef995c67fe57900034c60"},"schema_version":"1.0","source":{"id":"2510.05342","kind":"arxiv","version":2}},"canonical_sha256":"387edaf1ecdc36332350411eade9976abf3234fa7b908b2c41f8688f9b5dbe34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"387edaf1ecdc36332350411eade9976abf3234fa7b908b2c41f8688f9b5dbe34","first_computed_at":"2026-06-02T02:04:48.191971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:48.191971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"odH7B2kdv0F3oJ3t/iPP/g4oEYOCBwWTtxcrseO8GNO8dsU6ghqDL3Y7zelDF3uVnwbWKqS8oz5f1UcW3HUsCw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:48.192422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.05342","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1deb31aeadccaed6fedfdb1797af2f7b77bce3232dd5fd26c0e4693f690b28ce","sha256:fdf17aa140f5f93e2a1fa2f0c1d24c6cb1e5a80f23a5f75ffebecfe47789f11f"],"state_sha256":"5c369cc9a3e507253272b24a9e33e1d7b239da42f5acd9267097c0b102eb0e08"}