{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M243X7DS6KY7S2FU2JNCQVP5Y5","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":"6444a1b1dac105cb0ce44c8251662f13e3c698582b6ad8d67b8c502cd8c33adc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T06:31:18Z","title_canon_sha256":"78d4017885c0bdee48f3eac76ef440f3eb2657c2197805c7fa1f014bc40a8bfa"},"schema_version":"1.0","source":{"id":"2508.14460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14460","created_at":"2026-07-05T11:56:32Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14460v1","created_at":"2026-07-05T11:56:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14460","created_at":"2026-07-05T11:56:32Z"},{"alias_kind":"pith_short_12","alias_value":"M243X7DS6KY7","created_at":"2026-07-05T11:56:32Z"},{"alias_kind":"pith_short_16","alias_value":"M243X7DS6KY7S2FU","created_at":"2026-07-05T11:56:32Z"},{"alias_kind":"pith_short_8","alias_value":"M243X7DS","created_at":"2026-07-05T11:56:32Z"}],"graph_snapshots":[{"event_id":"sha256:60c7f02f9180331b736da8223e454888db086b626078c41a95f8fec60eb58eda","target":"graph","created_at":"2026-07-05T11:56:32Z","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/2508.14460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present DuPO, a dual learning-based preference optimization framework that generates annotation-free feedback via a generalized duality. DuPO addresses two key limitations: Reinforcement Learning with Verifiable Rewards (RLVR)'s reliance on costly labels and applicability restricted to verifiable tasks, and traditional dual learning's restriction to strictly dual task pairs (e.g., translation and back-translation). Specifically, DuPO decomposes a primal task's input into known and unknown components, then constructs its dual task to reconstruct the unknown part using the primal output and k","authors_text":"Lu Lu, Lu Xu, Shanbo Cheng, Shuaijie She, Shujian Huang, Tao Li, Wenhao Zhu, Yu Bao, Yu Lu, Yuxuan Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T06:31:18Z","title":"DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14460","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":"sha256:8d79b1603b222c2aec153e779cb348dfcbc1642e4871e031e5d873714b54262c","target":"record","created_at":"2026-07-05T11:56:32Z","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":"6444a1b1dac105cb0ce44c8251662f13e3c698582b6ad8d67b8c502cd8c33adc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T06:31:18Z","title_canon_sha256":"78d4017885c0bdee48f3eac76ef440f3eb2657c2197805c7fa1f014bc40a8bfa"},"schema_version":"1.0","source":{"id":"2508.14460","kind":"arxiv","version":1}},"canonical_sha256":"66b9bbfc72f2b1f968b4d25a2855fdc75c1d774d21d7f483ca3214498127792f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66b9bbfc72f2b1f968b4d25a2855fdc75c1d774d21d7f483ca3214498127792f","first_computed_at":"2026-07-05T11:56:32.411309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:32.411309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UG/imMw6OtL7CU0t4h0taYEFl5AvsFZTxYS37PnIIwmOlNAB+rF900f21Ws+SP/IeBgVZ3+Eh9S8CZraWUj0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:32.411784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d79b1603b222c2aec153e779cb348dfcbc1642e4871e031e5d873714b54262c","sha256:60c7f02f9180331b736da8223e454888db086b626078c41a95f8fec60eb58eda"],"state_sha256":"bffb73ce13c983e66ef6c3e3b7436a8eddbe406d41fdfe8bda3158b94013a813"}