{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4IDCBSQ5ENM3Y3UM22Y2KHHAUM","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":"a476761aa47e6aff75e42056755342277d97d57fa9e26c51181d85033491a6bc","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T11:18:38Z","title_canon_sha256":"252df353ee33847f3a8d04178b869742861ca212f3af3a4623eea099e48093f8"},"schema_version":"1.0","source":{"id":"2507.07151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07151","created_at":"2026-07-05T11:34:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07151v1","created_at":"2026-07-05T11:34:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07151","created_at":"2026-07-05T11:34:31Z"},{"alias_kind":"pith_short_12","alias_value":"4IDCBSQ5ENM3","created_at":"2026-07-05T11:34:31Z"},{"alias_kind":"pith_short_16","alias_value":"4IDCBSQ5ENM3Y3UM","created_at":"2026-07-05T11:34:31Z"},{"alias_kind":"pith_short_8","alias_value":"4IDCBSQ5","created_at":"2026-07-05T11:34:31Z"}],"graph_snapshots":[{"event_id":"sha256:f77db0282defd2e37846ecb83c4e1b1afce44a7441a13471698f613267eb89a1","target":"graph","created_at":"2026-07-05T11:34:31Z","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/2507.07151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the impressive capabilities of multimodal large language models (MLLMs) in vision-language tasks, they are prone to hallucinations in real-world scenarios. This paper investigates the hallucination phenomenon in MLLMs from the perspective of modality conflict. Unlike existing works focusing on the conflicts between model responses and inputs, we study the inherent conflicts in inputs from different modalities that place MLLMs in a dilemma and directly lead to hallucinations. We formally define the modality conflict and construct a dataset named Multimodal Modality Conflict (MMMC) to si","authors_text":"Houqiang Li, Jie Zhao, Wengang Zhou, Zongmeng Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T11:18:38Z","title":"Robust Multimodal Large Language Models Against Modality Conflict"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07151","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:a26a5449df64d796494d096ff0b595fb3c60b9e63f9d8df9a355a4b97e37ff6a","target":"record","created_at":"2026-07-05T11:34:31Z","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":"a476761aa47e6aff75e42056755342277d97d57fa9e26c51181d85033491a6bc","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T11:18:38Z","title_canon_sha256":"252df353ee33847f3a8d04178b869742861ca212f3af3a4623eea099e48093f8"},"schema_version":"1.0","source":{"id":"2507.07151","kind":"arxiv","version":1}},"canonical_sha256":"e20620ca1d2359bc6e8cd6b1a51ce0a3170e2f5e90bdf688cd718781534c536f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e20620ca1d2359bc6e8cd6b1a51ce0a3170e2f5e90bdf688cd718781534c536f","first_computed_at":"2026-07-05T11:34:31.933744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:31.933744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0z9AXi3QM30SWWVkIh9zY5gQ+qRiEpVR3TuK1EXqRH10bmcgLwLFBqLnMpx3fbndZxTXeFxKPqz8Pb8LV8HPDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:31.934205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26a5449df64d796494d096ff0b595fb3c60b9e63f9d8df9a355a4b97e37ff6a","sha256:f77db0282defd2e37846ecb83c4e1b1afce44a7441a13471698f613267eb89a1"],"state_sha256":"8d04d26b8b8a30aef893a116c50b99d970eb21b2da43853f029b580535a63da2"}