{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5UTQ3P6RDSIBFKATPGBSEW4ZAX","short_pith_number":"pith:5UTQ3P6R","canonical_record":{"source":{"id":"2503.12854","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T06:28:25Z","cross_cats_sorted":[],"title_canon_sha256":"e0010db9d6ac1fd95fdb743da6ba443455b84fdb64b65e1bfc143db76e44b2ab","abstract_canon_sha256":"21754a4c1746339c351ea496ecb4892af7191d51907581c4a3184223bc5d5145"},"schema_version":"1.0"},"canonical_sha256":"ed270dbfd11c9012a8137983225b9905fa0016fbefabe0a0333d06e583e6b988","source":{"kind":"arxiv","id":"2503.12854","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5UTQ3P6RDSIBFKATPGBSEW4ZAX","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12854","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T06:28:25Z","cross_cats_sorted":[],"title_canon_sha256":"e0010db9d6ac1fd95fdb743da6ba443455b84fdb64b65e1bfc143db76e44b2ab","abstract_canon_sha256":"21754a4c1746339c351ea496ecb4892af7191d51907581c4a3184223bc5d5145"},"schema_version":"1.0"},"canonical_sha256":"ed270dbfd11c9012a8137983225b9905fa0016fbefabe0a0333d06e583e6b988","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:02.790364Z","signature_b64":"QlHUpDPlXnw2aCiSNceHnre2GQcngLqpvfI4trltukebUHgfjVwLqdU3K4VlD1HV/73K4tW+KsXje6u+bPKqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed270dbfd11c9012a8137983225b9905fa0016fbefabe0a0333d06e583e6b988","last_reissued_at":"2026-07-05T11:44:02.789860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:02.789860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12854","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHTE9uUWvIAiosRhlg4dMU+jMk0LkffnG59EsYh570msqm1sX37WWsmpaynYiHzHhGEoxbFguThfaRccR+UjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:01:02.787021Z"},"content_sha256":"381a1bbb45021438e773da07a761e80dd585c26e133bde70d8e54c68d06d96a9","schema_version":"1.0","event_id":"sha256:381a1bbb45021438e773da07a761e80dd585c26e133bde70d8e54c68d06d96a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5UTQ3P6RDSIBFKATPGBSEW4ZAX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongbin Zhao, Dongmei Jiang, Jiahao Lin, Linjing Li, Nan Xu, Qichao Zhang, Songjun Tu, Wei He, Xiangyuan Lan, Xiangyu Tian, Yuqian Fu","submitted_at":"2025-03-17T06:28:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12854","kind":"arxiv","version":3},"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/2503.12854/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":"2026-07-05T11:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WSEaNnN6RdVCiUDyi7skJGe7JN57UvJLb1fQ0M1T0+bje7YkRuZx0hHuW/jykQCYerzjG1APuktrTIQtykPJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:01:02.787569Z"},"content_sha256":"725706b6a058fb9e2d56d01b6d36117bed1bfc8cdcdbf43ada27b9568cc4a05c","schema_version":"1.0","event_id":"sha256:725706b6a058fb9e2d56d01b6d36117bed1bfc8cdcdbf43ada27b9568cc4a05c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UTQ3P6RDSIBFKATPGBSEW4ZAX/bundle.json","state_url":"https://pith.science/pith/5UTQ3P6RDSIBFKATPGBSEW4ZAX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UTQ3P6RDSIBFKATPGBSEW4ZAX/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":"2026-08-03T21:01:02Z","links":{"resolver":"https://pith.science/pith/5UTQ3P6RDSIBFKATPGBSEW4ZAX","bundle":"https://pith.science/pith/5UTQ3P6RDSIBFKATPGBSEW4ZAX/bundle.json","state":"https://pith.science/pith/5UTQ3P6RDSIBFKATPGBSEW4ZAX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UTQ3P6RDSIBFKATPGBSEW4ZAX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e80qYPnPhjj9l/hVKHPoQzQ3WbA7/8UsycWzt2GJtYOVfCSrdl4AbPxsXqaj7c5tuxdMe+YGYvro3XaowxXwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:01:02.791263Z","bundle_sha256":"d908c9beda1a01a2763b3ba33aa5047947125fa11543dbccfc525c994dd2f9af"}}