{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5UTQ3P6RDSIBFKATPGBSEW4ZAX","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":"21754a4c1746339c351ea496ecb4892af7191d51907581c4a3184223bc5d5145","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T06:28:25Z","title_canon_sha256":"e0010db9d6ac1fd95fdb743da6ba443455b84fdb64b65e1bfc143db76e44b2ab"},"schema_version":"1.0","source":{"id":"2503.12854","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12854","created_at":"2026-07-05T11:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12854v3","created_at":"2026-07-05T11:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12854","created_at":"2026-07-05T11:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"5UTQ3P6RDSIB","created_at":"2026-07-05T11:44:02Z"},{"alias_kind":"pith_short_16","alias_value":"5UTQ3P6RDSIBFKAT","created_at":"2026-07-05T11:44:02Z"},{"alias_kind":"pith_short_8","alias_value":"5UTQ3P6R","created_at":"2026-07-05T11:44:02Z"}],"graph_snapshots":[{"event_id":"sha256:725706b6a058fb9e2d56d01b6d36117bed1bfc8cdcdbf43ada27b9568cc4a05c","target":"graph","created_at":"2026-07-05T11:44:02Z","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/2503.12854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with RL-based approaches have led to growing interest in alternative paradigms, such as Direct Preference Optimization (DPO). In this study, we investigate the effectiveness of DPO in facilitating self-improvement for LLMs through iterative preference-based learning. We demonstrate that a single round of DPO with coarse filtering significantly enhances mathematica","authors_text":"Dongbin Zhao, Dongmei Jiang, Jiahao Lin, Linjing Li, Nan Xu, Qichao Zhang, Songjun Tu, Wei He, Xiangyuan Lan, Xiangyu Tian, Yuqian Fu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T06:28:25Z","title":"Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12854","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":"sha256:381a1bbb45021438e773da07a761e80dd585c26e133bde70d8e54c68d06d96a9","target":"record","created_at":"2026-07-05T11:44:02Z","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":"21754a4c1746339c351ea496ecb4892af7191d51907581c4a3184223bc5d5145","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T06:28:25Z","title_canon_sha256":"e0010db9d6ac1fd95fdb743da6ba443455b84fdb64b65e1bfc143db76e44b2ab"},"schema_version":"1.0","source":{"id":"2503.12854","kind":"arxiv","version":3}},"canonical_sha256":"ed270dbfd11c9012a8137983225b9905fa0016fbefabe0a0333d06e583e6b988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed270dbfd11c9012a8137983225b9905fa0016fbefabe0a0333d06e583e6b988","first_computed_at":"2026-07-05T11:44:02.789860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:02.789860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QlHUpDPlXnw2aCiSNceHnre2GQcngLqpvfI4trltukebUHgfjVwLqdU3K4VlD1HV/73K4tW+KsXje6u+bPKqCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:02.790364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12854","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:381a1bbb45021438e773da07a761e80dd585c26e133bde70d8e54c68d06d96a9","sha256:725706b6a058fb9e2d56d01b6d36117bed1bfc8cdcdbf43ada27b9568cc4a05c"],"state_sha256":"d639f31b5e1d432d83894ff22023bba125bd52fea5d8ca5cd33d2fdbb67813d0"}