{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SH2GEG5J3TUDUM7ZVGZD2UZMJE","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":"aa0a42d50394a47b6b43ab8b8fb05b5aa68831882dc7f644cb0c4a748f181016","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T01:11:28Z","title_canon_sha256":"e0f2c2e42d3e02b7c3fe90309e10b1bdc49009885d68acbedae5019efdc72865"},"schema_version":"1.0","source":{"id":"2411.02708","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02708","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02708v3","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02708","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"SH2GEG5J3TUD","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"SH2GEG5J3TUDUM7Z","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"SH2GEG5J","created_at":"2026-07-05T12:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:df1e39889f6560f7bc7b2a7a05e1df533c45e20c747e522980e39868966ff415","target":"graph","created_at":"2026-07-05T12:03:44Z","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/2411.02708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding. However, existing studies have concentrated mainly on visual-textual misalignment, leaving largely unexplored the MLLMs' ability to preserve an originally correct answer when confronted with misleading information. We reveal a response uncertainty phenomenon: across nine standard datasets, twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue. To system","authors_text":"Aiwei Liu, Jia Liu, Jingyu Wang, Jungang Li, Mengxi Gao, Peijie Jiang, Xin Zou, Xuming Hu, Yanggan Gu, Yibo Yan, Yunkai Dang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T01:11:28Z","title":"Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02708","kind":"arxiv","version":3},"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:dc3c49188dadf41de0916e97eb996fb28618f86b2da06e77b25a960e6b0c101e","target":"record","created_at":"2026-07-05T12:03:44Z","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":"aa0a42d50394a47b6b43ab8b8fb05b5aa68831882dc7f644cb0c4a748f181016","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T01:11:28Z","title_canon_sha256":"e0f2c2e42d3e02b7c3fe90309e10b1bdc49009885d68acbedae5019efdc72865"},"schema_version":"1.0","source":{"id":"2411.02708","kind":"arxiv","version":3}},"canonical_sha256":"91f4621ba9dce83a33f9a9b23d532c492e4e7a34a85bafcba98e83be0e0c2641","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91f4621ba9dce83a33f9a9b23d532c492e4e7a34a85bafcba98e83be0e0c2641","first_computed_at":"2026-07-05T12:03:44.020879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:44.020879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IZs2RiLYnnYDVfnW58wi3/+SBMTIVNvcUHuplU2+DeHRNgAtvseEm8lWpA4LN/j8bDcEi4y5RMaEqsUL3deiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:44.021414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02708","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc3c49188dadf41de0916e97eb996fb28618f86b2da06e77b25a960e6b0c101e","sha256:df1e39889f6560f7bc7b2a7a05e1df533c45e20c747e522980e39868966ff415"],"state_sha256":"20c2bf145fc0783081836c3716209883b3e5eda30b60cf4818d3818375b40a08"}