{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UPQ23KJTDYRNHMKHEMZOHXIJSH","short_pith_number":"pith:UPQ23KJT","canonical_record":{"source":{"id":"2406.11839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"8e457f448976e281734bc880ee3a876ec4cc87ae14194068ef78b273982bb071","abstract_canon_sha256":"f3c785f35f5eb23c6d209ca96f5d07a020d3fac1aa1d44b7a5d2b4cfc5a8a42f"},"schema_version":"1.0"},"canonical_sha256":"a3e1ada9331e22d3b1472332e3dd0991f3e5f76cda119d5475841a302d534e4c","source":{"kind":"arxiv","id":"2406.11839","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11839","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11839v2","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11839","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"UPQ23KJTDYRN","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"UPQ23KJTDYRNHMKH","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"UPQ23KJT","created_at":"2026-07-05T09:16:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UPQ23KJTDYRNHMKHEMZOHXIJSH","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"8e457f448976e281734bc880ee3a876ec4cc87ae14194068ef78b273982bb071","abstract_canon_sha256":"f3c785f35f5eb23c6d209ca96f5d07a020d3fac1aa1d44b7a5d2b4cfc5a8a42f"},"schema_version":"1.0"},"canonical_sha256":"a3e1ada9331e22d3b1472332e3dd0991f3e5f76cda119d5475841a302d534e4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:50.174806Z","signature_b64":"T7W7WEv5ZjChLuwM6/v0V4TCVzHmduu80srDhZul0C2UM7OX9BYV+2Js8gkIjs/uU6NrFwpyZaCW3zwVCIl3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3e1ada9331e22d3b1472332e3dd0991f3e5f76cda119d5475841a302d534e4c","last_reissued_at":"2026-07-05T09:16:50.174308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:50.174308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11839","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c1mnJrl9ObSiiQT2fPklSW1GQyF2WBjNCtIVyiYDDpr7UBTu5n25EjFDPzlCvV3GNdhkQBX0uogKwTNPySwHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:25:27.725081Z"},"content_sha256":"b90d1a6f5edeafedfcf1385f8fc8f92fd0f7ead95932eeb22bfce04597b7b772","schema_version":"1.0","event_id":"sha256:b90d1a6f5edeafedfcf1385f8fc8f92fd0f7ead95932eeb22bfce04597b7b772"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UPQ23KJTDYRNHMKHEMZOHXIJSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fei Wang, Hoifung Poon, James Y. Huang, Muhao Chen, Nan Xu, Sheng Zhang, Wenxuan Zhou","submitted_at":"2024-06-17T17:59:58Z","abstract_excerpt":"Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement. Through a comparative experiment, we identify the unconditional preference problem in multimodal preference optimization, where the model overlooks the image condition. To address this problem, we propose mDPO, a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference. Moreover, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11839","kind":"arxiv","version":2},"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/2406.11839/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":"2026-07-05T09:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ca43FFDjwGpVmefWJRNZd7hs3mHH9mtw51lYpATae+3pJTrLlZReuLl33tbrw+u6BkPO0JH/4wgleJFDI2q0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:25:27.725580Z"},"content_sha256":"02f29d1a21415fbd4ef647a936231f2c0fa97de336b2e9a6bd1e8e5092542e95","schema_version":"1.0","event_id":"sha256:02f29d1a21415fbd4ef647a936231f2c0fa97de336b2e9a6bd1e8e5092542e95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPQ23KJTDYRNHMKHEMZOHXIJSH/bundle.json","state_url":"https://pith.science/pith/UPQ23KJTDYRNHMKHEMZOHXIJSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPQ23KJTDYRNHMKHEMZOHXIJSH/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":"2026-08-09T21:25:27Z","links":{"resolver":"https://pith.science/pith/UPQ23KJTDYRNHMKHEMZOHXIJSH","bundle":"https://pith.science/pith/UPQ23KJTDYRNHMKHEMZOHXIJSH/bundle.json","state":"https://pith.science/pith/UPQ23KJTDYRNHMKHEMZOHXIJSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPQ23KJTDYRNHMKHEMZOHXIJSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UPQ23KJTDYRNHMKHEMZOHXIJSH","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":"f3c785f35f5eb23c6d209ca96f5d07a020d3fac1aa1d44b7a5d2b4cfc5a8a42f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:58Z","title_canon_sha256":"8e457f448976e281734bc880ee3a876ec4cc87ae14194068ef78b273982bb071"},"schema_version":"1.0","source":{"id":"2406.11839","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11839","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11839v2","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11839","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"UPQ23KJTDYRN","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"UPQ23KJTDYRNHMKH","created_at":"2026-07-05T09:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"UPQ23KJT","created_at":"2026-07-05T09:16:50Z"}],"graph_snapshots":[{"event_id":"sha256:02f29d1a21415fbd4ef647a936231f2c0fa97de336b2e9a6bd1e8e5092542e95","target":"graph","created_at":"2026-07-05T09:16:50Z","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/2406.11839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement. Through a comparative experiment, we identify the unconditional preference problem in multimodal preference optimization, where the model overlooks the image condition. To address this problem, we propose mDPO, a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference. Moreover, we ","authors_text":"Fei Wang, Hoifung Poon, James Y. Huang, Muhao Chen, Nan Xu, Sheng Zhang, Wenxuan Zhou","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:58Z","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11839","kind":"arxiv","version":2},"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:b90d1a6f5edeafedfcf1385f8fc8f92fd0f7ead95932eeb22bfce04597b7b772","target":"record","created_at":"2026-07-05T09:16:50Z","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":"f3c785f35f5eb23c6d209ca96f5d07a020d3fac1aa1d44b7a5d2b4cfc5a8a42f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:58Z","title_canon_sha256":"8e457f448976e281734bc880ee3a876ec4cc87ae14194068ef78b273982bb071"},"schema_version":"1.0","source":{"id":"2406.11839","kind":"arxiv","version":2}},"canonical_sha256":"a3e1ada9331e22d3b1472332e3dd0991f3e5f76cda119d5475841a302d534e4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3e1ada9331e22d3b1472332e3dd0991f3e5f76cda119d5475841a302d534e4c","first_computed_at":"2026-07-05T09:16:50.174308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:50.174308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T7W7WEv5ZjChLuwM6/v0V4TCVzHmduu80srDhZul0C2UM7OX9BYV+2Js8gkIjs/uU6NrFwpyZaCW3zwVCIl3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:50.174806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11839","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b90d1a6f5edeafedfcf1385f8fc8f92fd0f7ead95932eeb22bfce04597b7b772","sha256:02f29d1a21415fbd4ef647a936231f2c0fa97de336b2e9a6bd1e8e5092542e95"],"state_sha256":"ca643fb51d5a668e81e0167e5967aa0d88672fc8ebb550230460c4c3cbafc915"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JpzsliciLIygG441iJv74zmxL22A6rnwF27W0WoMUaMGnkHdlJ66VDFctPYnkSbXSL84PBHu9dkQxg4Zrm8HCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:25:27.729464Z","bundle_sha256":"5739a029419b2f717e9382de74a19bf560e1b8e00becbfb36d0fea0b5d7651b5"}}