{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YZFSBQNMYQTTK6ECUKAFEMRA7F","short_pith_number":"pith:YZFSBQNM","canonical_record":{"source":{"id":"2509.10515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T10:20:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8d96b89013e0637b79f67a7a56c73fa23ccae18bf86758684bf97f5b70bca02a","abstract_canon_sha256":"c7918060d9103f11793a27dc6f396e95bba552fe7610076ae9219d2918adec98"},"schema_version":"1.0"},"canonical_sha256":"c64b20c1acc427357882a280523220f95f556f0d97f7dacfd26983f066497e91","source":{"kind":"arxiv","id":"2509.10515","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10515","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10515v1","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10515","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"YZFSBQNMYQTT","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"YZFSBQNMYQTTK6EC","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"YZFSBQNM","created_at":"2026-05-26T01:03:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YZFSBQNMYQTTK6ECUKAFEMRA7F","target":"record","payload":{"canonical_record":{"source":{"id":"2509.10515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T10:20:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8d96b89013e0637b79f67a7a56c73fa23ccae18bf86758684bf97f5b70bca02a","abstract_canon_sha256":"c7918060d9103f11793a27dc6f396e95bba552fe7610076ae9219d2918adec98"},"schema_version":"1.0"},"canonical_sha256":"c64b20c1acc427357882a280523220f95f556f0d97f7dacfd26983f066497e91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:15.462534Z","signature_b64":"zhUqv5o29XdKHPe4PQbX6yv8nZfYHZ/HL6hwaU7pvovWqsVNroIcI30J4g5MrA/tqutlUZzLxebGQjeQSEtoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c64b20c1acc427357882a280523220f95f556f0d97f7dacfd26983f066497e91","last_reissued_at":"2026-05-26T01:03:15.461910Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:15.461910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.10515","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":"2026-05-26T01:03:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oiFNjXQ0hkgu42dILGfxC4FKdwE41dtPaG8RgTdKsd6PEh3tZEI0D/ao2ugwAq5XWR2POpD4WiU6xVNCIkKJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:12:44.000325Z"},"content_sha256":"00549d448f1ecb12b37fe15fc991180d9319545e2b3ae77cf422227141341072","schema_version":"1.0","event_id":"sha256:00549d448f1ecb12b37fe15fc991180d9319545e2b3ae77cf422227141341072"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YZFSBQNMYQTTK6ECUKAFEMRA7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Preference Optimization with Uncertainty-aware Utility Anchor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiaqi Li, Qi Liu, Xiaobo Wang, Zilong Zheng, Zixia Jia","submitted_at":"2025-09-03T10:20:08Z","abstract_excerpt":"Offline preference optimization methods are efficient for large language models (LLMs) alignment. Direct Preference optimization (DPO)-like learning, one of the most popular approaches, stands out for its efficiency in reward modeling. However, these methods typically follow the convention to use Bradley-Terry (BT) reward modeling that faces several critical assumptions, including the requirement for pairwise training data, model distribution shifting, human rationality assumption, etc. To address these limitations, we propose a general framework for offline preference optimization methods, Ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10515","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/2509.10515/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":"2026-05-26T01:03:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sZpBA07mgi5S9GS4hM5/wss7hqrIqYqvVHKqCfy0s/HZOqcyux6c4YDbRVXkvFdyBEsMh1qHKtn9Zv/KiphYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:12:44.000776Z"},"content_sha256":"13112ff0ff0d6defc6d18fcad6b07a2031c667b24e8f9f01c608c4b22a966e69","schema_version":"1.0","event_id":"sha256:13112ff0ff0d6defc6d18fcad6b07a2031c667b24e8f9f01c608c4b22a966e69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZFSBQNMYQTTK6ECUKAFEMRA7F/bundle.json","state_url":"https://pith.science/pith/YZFSBQNMYQTTK6ECUKAFEMRA7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZFSBQNMYQTTK6ECUKAFEMRA7F/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":"2026-05-26T13:12:44Z","links":{"resolver":"https://pith.science/pith/YZFSBQNMYQTTK6ECUKAFEMRA7F","bundle":"https://pith.science/pith/YZFSBQNMYQTTK6ECUKAFEMRA7F/bundle.json","state":"https://pith.science/pith/YZFSBQNMYQTTK6ECUKAFEMRA7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZFSBQNMYQTTK6ECUKAFEMRA7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YZFSBQNMYQTTK6ECUKAFEMRA7F","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":"c7918060d9103f11793a27dc6f396e95bba552fe7610076ae9219d2918adec98","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T10:20:08Z","title_canon_sha256":"8d96b89013e0637b79f67a7a56c73fa23ccae18bf86758684bf97f5b70bca02a"},"schema_version":"1.0","source":{"id":"2509.10515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10515","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10515v1","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10515","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"YZFSBQNMYQTT","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"YZFSBQNMYQTTK6EC","created_at":"2026-05-26T01:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"YZFSBQNM","created_at":"2026-05-26T01:03:15Z"}],"graph_snapshots":[{"event_id":"sha256:13112ff0ff0d6defc6d18fcad6b07a2031c667b24e8f9f01c608c4b22a966e69","target":"graph","created_at":"2026-05-26T01:03:15Z","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/2509.10515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline preference optimization methods are efficient for large language models (LLMs) alignment. Direct Preference optimization (DPO)-like learning, one of the most popular approaches, stands out for its efficiency in reward modeling. However, these methods typically follow the convention to use Bradley-Terry (BT) reward modeling that faces several critical assumptions, including the requirement for pairwise training data, model distribution shifting, human rationality assumption, etc. To address these limitations, we propose a general framework for offline preference optimization methods, Ad","authors_text":"Jiaqi Li, Qi Liu, Xiaobo Wang, Zilong Zheng, Zixia Jia","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T10:20:08Z","title":"Adaptive Preference Optimization with Uncertainty-aware Utility Anchor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10515","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":"sha256:00549d448f1ecb12b37fe15fc991180d9319545e2b3ae77cf422227141341072","target":"record","created_at":"2026-05-26T01:03:15Z","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":"c7918060d9103f11793a27dc6f396e95bba552fe7610076ae9219d2918adec98","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T10:20:08Z","title_canon_sha256":"8d96b89013e0637b79f67a7a56c73fa23ccae18bf86758684bf97f5b70bca02a"},"schema_version":"1.0","source":{"id":"2509.10515","kind":"arxiv","version":1}},"canonical_sha256":"c64b20c1acc427357882a280523220f95f556f0d97f7dacfd26983f066497e91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c64b20c1acc427357882a280523220f95f556f0d97f7dacfd26983f066497e91","first_computed_at":"2026-05-26T01:03:15.461910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:15.461910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zhUqv5o29XdKHPe4PQbX6yv8nZfYHZ/HL6hwaU7pvovWqsVNroIcI30J4g5MrA/tqutlUZzLxebGQjeQSEtoAA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:15.462534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.10515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00549d448f1ecb12b37fe15fc991180d9319545e2b3ae77cf422227141341072","sha256:13112ff0ff0d6defc6d18fcad6b07a2031c667b24e8f9f01c608c4b22a966e69"],"state_sha256":"a0ab965c33f38e7d6703d873e109a340cabc079a3bee0611be61b642501d92ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"So7ZeduS+DKeirL3cQLkN4JU8/s43jcFPlos0GJBesmAANXuRdYKxBnroDedNUc58MHbvLbA0KZlXfPMh3qTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:12:44.003078Z","bundle_sha256":"0255246da0f71964bb08710f1d56434971dfff5de6d83b10d2aecdf9a573e7dd"}}