{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6XXJD7AQEAYECFU25YYJ7E4UGO","short_pith_number":"pith:6XXJD7AQ","canonical_record":{"source":{"id":"2410.22304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:50:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ffee1c1aada5baf108e01cbe57a5cf7a10e4a5142721c926285da2ed6428216","abstract_canon_sha256":"9c38e5a519a526f773c99f78711966f1ae8ecac446c05b4062900e2326844852"},"schema_version":"1.0"},"canonical_sha256":"f5ee91fc10203041169aee309f939433986441060954ed48ce4d01feb7df809d","source":{"kind":"arxiv","id":"2410.22304","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22304","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22304v1","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22304","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"6XXJD7AQEAYE","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"6XXJD7AQEAYECFU2","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"6XXJD7AQ","created_at":"2026-07-05T09:28:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6XXJD7AQEAYECFU25YYJ7E4UGO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.22304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:50:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ffee1c1aada5baf108e01cbe57a5cf7a10e4a5142721c926285da2ed6428216","abstract_canon_sha256":"9c38e5a519a526f773c99f78711966f1ae8ecac446c05b4062900e2326844852"},"schema_version":"1.0"},"canonical_sha256":"f5ee91fc10203041169aee309f939433986441060954ed48ce4d01feb7df809d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:07.184484Z","signature_b64":"kGhzrDfazo9bFBGPKX3SLh25NUkCJUDPSjl5N4nPTHOa0GxllXTafqLNwW3ABgQAeh3o3ct5LLhPITiK4DsEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5ee91fc10203041169aee309f939433986441060954ed48ce4d01feb7df809d","last_reissued_at":"2026-07-05T09:28:07.184010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:07.184010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.22304","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqlL2SsnzXnIozlw4EI4gzlCh+JWfpyT5PGBSR/OmXSbPYMmdUwUr75fSILXcM9m9kmTOIlQ5EC6Shdq9mFMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:28:54.785700Z"},"content_sha256":"352465d6756208c5842e308423d5404e4b0aa30038ddae1539028022f67e9914","schema_version":"1.0","event_id":"sha256:352465d6756208c5842e308423d5404e4b0aa30038ddae1539028022f67e9914"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6XXJD7AQEAYECFU25YYJ7E4UGO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Paul Mineiro, Yihe Deng","submitted_at":"2024-10-29T17:50:31Z","abstract_excerpt":"Mathematical reasoning is a crucial capability for Large Language Models (LLMs), yet generating detailed and accurate reasoning traces remains a significant challenge. This paper introduces a novel approach to produce high-quality reasoning traces for LLM fine-tuning using online learning \\textbf{Flows}. Our method employs an incremental output production Flow, where component LLMs collaboratively construct solutions through iterative communication. We train the Flow using online Direct Preference Optimization (DPO) learning with rollouts, generating DPO pairs for each training example and upd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22304","kind":"arxiv","version":1},"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/2410.22304/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":"2026-07-05T09:28:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DkL+6oz2kcdFMag6Rsg9bcjh3RWiRoiXgbeMRiIer+JRoZtXXEXxC4e0ldPQ3EIXNyrhGdnPs3EzfGZu4frMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:28:54.786600Z"},"content_sha256":"2fccee10f9e74887a360f37678a5626347dc5ea378c1fc64435c10124642c108","schema_version":"1.0","event_id":"sha256:2fccee10f9e74887a360f37678a5626347dc5ea378c1fc64435c10124642c108"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/bundle.json","state_url":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/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":"2026-08-09T07:28:54Z","links":{"resolver":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO","bundle":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/bundle.json","state":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6XXJD7AQEAYECFU25YYJ7E4UGO","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":"9c38e5a519a526f773c99f78711966f1ae8ecac446c05b4062900e2326844852","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:50:31Z","title_canon_sha256":"7ffee1c1aada5baf108e01cbe57a5cf7a10e4a5142721c926285da2ed6428216"},"schema_version":"1.0","source":{"id":"2410.22304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22304","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22304v1","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22304","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"6XXJD7AQEAYE","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"6XXJD7AQEAYECFU2","created_at":"2026-07-05T09:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"6XXJD7AQ","created_at":"2026-07-05T09:28:07Z"}],"graph_snapshots":[{"event_id":"sha256:2fccee10f9e74887a360f37678a5626347dc5ea378c1fc64435c10124642c108","target":"graph","created_at":"2026-07-05T09:28:07Z","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/2410.22304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical reasoning is a crucial capability for Large Language Models (LLMs), yet generating detailed and accurate reasoning traces remains a significant challenge. This paper introduces a novel approach to produce high-quality reasoning traces for LLM fine-tuning using online learning \\textbf{Flows}. Our method employs an incremental output production Flow, where component LLMs collaboratively construct solutions through iterative communication. We train the Flow using online Direct Preference Optimization (DPO) learning with rollouts, generating DPO pairs for each training example and upd","authors_text":"Paul Mineiro, Yihe Deng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:50:31Z","title":"Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22304","kind":"arxiv","version":1},"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":"sha256:352465d6756208c5842e308423d5404e4b0aa30038ddae1539028022f67e9914","target":"record","created_at":"2026-07-05T09:28:07Z","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":"9c38e5a519a526f773c99f78711966f1ae8ecac446c05b4062900e2326844852","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:50:31Z","title_canon_sha256":"7ffee1c1aada5baf108e01cbe57a5cf7a10e4a5142721c926285da2ed6428216"},"schema_version":"1.0","source":{"id":"2410.22304","kind":"arxiv","version":1}},"canonical_sha256":"f5ee91fc10203041169aee309f939433986441060954ed48ce4d01feb7df809d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5ee91fc10203041169aee309f939433986441060954ed48ce4d01feb7df809d","first_computed_at":"2026-07-05T09:28:07.184010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:07.184010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kGhzrDfazo9bFBGPKX3SLh25NUkCJUDPSjl5N4nPTHOa0GxllXTafqLNwW3ABgQAeh3o3ct5LLhPITiK4DsEDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:07.184484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:352465d6756208c5842e308423d5404e4b0aa30038ddae1539028022f67e9914","sha256:2fccee10f9e74887a360f37678a5626347dc5ea378c1fc64435c10124642c108"],"state_sha256":"d83ffa812166e1472566dc928409223799e0fe69a5c00334a66e0ec902c73342"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+yTYdttQM2w0vWk7c60xjIh9H6PzPEkwbSlFgC6r85HOzHItPJQnn/O5w9XKtEpmpRBL9MxEcAIQiHSgXm/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:28:54.792080Z","bundle_sha256":"c81656fc77b03e530548d43a462d05f9dbab39e9ff392a544baadb63448ae926"}}