{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M243X7DS6KY7S2FU2JNCQVP5Y5","short_pith_number":"pith:M243X7DS","canonical_record":{"source":{"id":"2508.14460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T06:31:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"78d4017885c0bdee48f3eac76ef440f3eb2657c2197805c7fa1f014bc40a8bfa","abstract_canon_sha256":"6444a1b1dac105cb0ce44c8251662f13e3c698582b6ad8d67b8c502cd8c33adc"},"schema_version":"1.0"},"canonical_sha256":"66b9bbfc72f2b1f968b4d25a2855fdc75c1d774d21d7f483ca3214498127792f","source":{"kind":"arxiv","id":"2508.14460","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M243X7DS6KY7S2FU2JNCQVP5Y5","target":"record","payload":{"canonical_record":{"source":{"id":"2508.14460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T06:31:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"78d4017885c0bdee48f3eac76ef440f3eb2657c2197805c7fa1f014bc40a8bfa","abstract_canon_sha256":"6444a1b1dac105cb0ce44c8251662f13e3c698582b6ad8d67b8c502cd8c33adc"},"schema_version":"1.0"},"canonical_sha256":"66b9bbfc72f2b1f968b4d25a2855fdc75c1d774d21d7f483ca3214498127792f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:32.411784Z","signature_b64":"UG/imMw6OtL7CU0t4h0taYEFl5AvsFZTxYS37PnIIwmOlNAB+rF900f21Ws+SP/IeBgVZ3+Eh9S8CZraWUj0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66b9bbfc72f2b1f968b4d25a2855fdc75c1d774d21d7f483ca3214498127792f","last_reissued_at":"2026-07-05T11:56:32.411309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:32.411309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.14460","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":"2026-07-05T11:56:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYW8jTnd2Tq4fDbQqeh4KTGYmQXIPz0GRbhKvRLqa9RL3eLrDgRuEmQHHHSkk/gKX5X4hJVCTQuOXAqLf1JQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:47:44.498990Z"},"content_sha256":"8d79b1603b222c2aec153e779cb348dfcbc1642e4871e031e5d873714b54262c","schema_version":"1.0","event_id":"sha256:8d79b1603b222c2aec153e779cb348dfcbc1642e4871e031e5d873714b54262c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M243X7DS6KY7S2FU2JNCQVP5Y5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Lu Lu, Lu Xu, Shanbo Cheng, Shuaijie She, Shujian Huang, Tao Li, Wenhao Zhu, Yu Bao, Yu Lu, Yuxuan Wang","submitted_at":"2025-08-20T06:31:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14460","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/2508.14460/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":"2026-07-05T11:56:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VJDWbAcYwpe4SlDkpliHYUALsU0/QSInBYCn8AYZP+nDY1qpapr5X5XleHM46TlfUbV1WxLUWMEVdmPMYF1hDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:47:44.500060Z"},"content_sha256":"60c7f02f9180331b736da8223e454888db086b626078c41a95f8fec60eb58eda","schema_version":"1.0","event_id":"sha256:60c7f02f9180331b736da8223e454888db086b626078c41a95f8fec60eb58eda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M243X7DS6KY7S2FU2JNCQVP5Y5/bundle.json","state_url":"https://pith.science/pith/M243X7DS6KY7S2FU2JNCQVP5Y5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M243X7DS6KY7S2FU2JNCQVP5Y5/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":"2026-08-05T11:47:44Z","links":{"resolver":"https://pith.science/pith/M243X7DS6KY7S2FU2JNCQVP5Y5","bundle":"https://pith.science/pith/M243X7DS6KY7S2FU2JNCQVP5Y5/bundle.json","state":"https://pith.science/pith/M243X7DS6KY7S2FU2JNCQVP5Y5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M243X7DS6KY7S2FU2JNCQVP5Y5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74R0pgMpTdQ6max1GRRGd0IlWe/q0drPPjhjZlqZA8YFUaEgmj/64g9sa4daRIqd6zhCmVxIwSrJ/K+/ktTuCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:47:44.518778Z","bundle_sha256":"55bf6ab7de18a3fe7be6f1cbad609b2c06ffb8ada9590d4327f18e92949a7768"}}