{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3U7HLCYMI24TXPAMPJ26ODVMVS","short_pith_number":"pith:3U7HLCYM","canonical_record":{"source":{"id":"2501.16629","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:05:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b25500d928c7181a629122914ccca492f7e0160c60e7bc40bb5bc8984f47dbde","abstract_canon_sha256":"0ab00d08acb74defbf11f823887c1b105570b3628d9411314b7ffb24e69f967e"},"schema_version":"1.0"},"canonical_sha256":"dd3e758b0c46b93bbc0c7a75e70eacaca1de704e84a27c3bf942bc3b99f1d821","source":{"kind":"arxiv","id":"2501.16629","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16629","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16629v1","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16629","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"3U7HLCYMI24T","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"3U7HLCYMI24TXPAM","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"3U7HLCYM","created_at":"2026-07-05T10:06:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3U7HLCYMI24TXPAMPJ26ODVMVS","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16629","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:05:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b25500d928c7181a629122914ccca492f7e0160c60e7bc40bb5bc8984f47dbde","abstract_canon_sha256":"0ab00d08acb74defbf11f823887c1b105570b3628d9411314b7ffb24e69f967e"},"schema_version":"1.0"},"canonical_sha256":"dd3e758b0c46b93bbc0c7a75e70eacaca1de704e84a27c3bf942bc3b99f1d821","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:16.105075Z","signature_b64":"8WWckZ2RjFw8ZsMSQee6qEW0JZDwe5MTe6c4uQwhnMCexIPb3E9IxtK5IsB62a12IZRy2+4KAHDI9fx1qtSeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd3e758b0c46b93bbc0c7a75e70eacaca1de704e84a27c3bf942bc3b99f1d821","last_reissued_at":"2026-07-05T10:06:16.104624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:16.104624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16629","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":"2026-07-05T10:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Fr2gl9py9dB6t2iFrXosmKepKzajqjohoXYUoENUgactTduYjcEl8QA5D0kZFVRE2MO2kLPYJ2pUYPOnUpQBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:54:56.975832Z"},"content_sha256":"9fac21224671ed91ad9de85cac6be6228040aea071d950c2d7ec2c88b0cf8e03","schema_version":"1.0","event_id":"sha256:9fac21224671ed91ad9de85cac6be6228040aea071d950c2d7ec2c88b0cf8e03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3U7HLCYMI24TXPAMPJ26ODVMVS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bryan Hooi, Hao Fei, Jinlan Fu, See-kiong Ng, Shenzhen Huangfu, Xiaoyu Shen, Xipeng Qiu","submitted_at":"2025-01-28T02:05:38Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. Recent studies have attempted to mitigate this by applying Direct Preference Optimization (DPO) to multimodal scenarios using preference pairs from text-based responses. However, our analysis of representation distributions reveals that multimodal DPO struggles to align image and text representations and to distinguish between hallucinated and non-hallucinated descriptions. To address these challenges, in this work, we propose a Cross-modal Hierarchical Direct Preference Optimizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16629","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/2501.16629/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":"2026-07-05T10:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3YHRheJH51AolVHqzYGQ5EMlyccyQja0jXtL6Gzmiq4xmuE4+KtAJkOMa/8Mf/Wt7y0xKdx3ub9zB2MXi3wlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:54:56.976141Z"},"content_sha256":"c45f2f847c7457f258401783e7823371540750345b27c68ed0488b546b2b73a4","schema_version":"1.0","event_id":"sha256:c45f2f847c7457f258401783e7823371540750345b27c68ed0488b546b2b73a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3U7HLCYMI24TXPAMPJ26ODVMVS/bundle.json","state_url":"https://pith.science/pith/3U7HLCYMI24TXPAMPJ26ODVMVS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3U7HLCYMI24TXPAMPJ26ODVMVS/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":"2026-08-06T01:54:56Z","links":{"resolver":"https://pith.science/pith/3U7HLCYMI24TXPAMPJ26ODVMVS","bundle":"https://pith.science/pith/3U7HLCYMI24TXPAMPJ26ODVMVS/bundle.json","state":"https://pith.science/pith/3U7HLCYMI24TXPAMPJ26ODVMVS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3U7HLCYMI24TXPAMPJ26ODVMVS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3U7HLCYMI24TXPAMPJ26ODVMVS","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":"0ab00d08acb74defbf11f823887c1b105570b3628d9411314b7ffb24e69f967e","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:05:38Z","title_canon_sha256":"b25500d928c7181a629122914ccca492f7e0160c60e7bc40bb5bc8984f47dbde"},"schema_version":"1.0","source":{"id":"2501.16629","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16629","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16629v1","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16629","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"3U7HLCYMI24T","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"3U7HLCYMI24TXPAM","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"3U7HLCYM","created_at":"2026-07-05T10:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:c45f2f847c7457f258401783e7823371540750345b27c68ed0488b546b2b73a4","target":"graph","created_at":"2026-07-05T10:06:16Z","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/2501.16629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. Recent studies have attempted to mitigate this by applying Direct Preference Optimization (DPO) to multimodal scenarios using preference pairs from text-based responses. However, our analysis of representation distributions reveals that multimodal DPO struggles to align image and text representations and to distinguish between hallucinated and non-hallucinated descriptions. To address these challenges, in this work, we propose a Cross-modal Hierarchical Direct Preference Optimizat","authors_text":"Bryan Hooi, Hao Fei, Jinlan Fu, See-kiong Ng, Shenzhen Huangfu, Xiaoyu Shen, Xipeng Qiu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:05:38Z","title":"CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16629","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":"sha256:9fac21224671ed91ad9de85cac6be6228040aea071d950c2d7ec2c88b0cf8e03","target":"record","created_at":"2026-07-05T10:06:16Z","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":"0ab00d08acb74defbf11f823887c1b105570b3628d9411314b7ffb24e69f967e","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:05:38Z","title_canon_sha256":"b25500d928c7181a629122914ccca492f7e0160c60e7bc40bb5bc8984f47dbde"},"schema_version":"1.0","source":{"id":"2501.16629","kind":"arxiv","version":1}},"canonical_sha256":"dd3e758b0c46b93bbc0c7a75e70eacaca1de704e84a27c3bf942bc3b99f1d821","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd3e758b0c46b93bbc0c7a75e70eacaca1de704e84a27c3bf942bc3b99f1d821","first_computed_at":"2026-07-05T10:06:16.104624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:16.104624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8WWckZ2RjFw8ZsMSQee6qEW0JZDwe5MTe6c4uQwhnMCexIPb3E9IxtK5IsB62a12IZRy2+4KAHDI9fx1qtSeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:16.105075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16629","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fac21224671ed91ad9de85cac6be6228040aea071d950c2d7ec2c88b0cf8e03","sha256:c45f2f847c7457f258401783e7823371540750345b27c68ed0488b546b2b73a4"],"state_sha256":"23809c98372da152c1ee2457ff56abcd313dd98d1446c472755152389e454c58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FqQmQZMyf2eR7DoIaF2j6rvQN2dM/UkJYruN31+qmmtd4Kn3171K7Kz0PcnpElUvTJ8AcYdk0Z1efR4/KDhwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:54:56.979809Z","bundle_sha256":"66c1824f8ccc03016644a5df5c74b66f91342fc9c5dcec33f93fc539ea4fc501"}}