{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:62OUNQ7WD7LNPWBTJVCFZCWAWZ","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":"4cd521b92c650ef5dfdbfc056225446b359c8baed94246d569608450460fec31","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T14:48:27Z","title_canon_sha256":"72fa18f4d54b477d4afc8559f3e85a3569720786e2ce74753f725f0baffdf043"},"schema_version":"1.0","source":{"id":"2507.00817","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00817","created_at":"2026-07-05T11:30:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00817v1","created_at":"2026-07-05T11:30:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00817","created_at":"2026-07-05T11:30:14Z"},{"alias_kind":"pith_short_12","alias_value":"62OUNQ7WD7LN","created_at":"2026-07-05T11:30:14Z"},{"alias_kind":"pith_short_16","alias_value":"62OUNQ7WD7LNPWBT","created_at":"2026-07-05T11:30:14Z"},{"alias_kind":"pith_short_8","alias_value":"62OUNQ7W","created_at":"2026-07-05T11:30:14Z"}],"graph_snapshots":[{"event_id":"sha256:d1711a84be86f1b6e57af6eeff6754d176c3c36ab337b71f9e5eed192f026a63","target":"graph","created_at":"2026-07-05T11:30:14Z","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/2507.00817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Multimodal Large Language Models (V-MLLMs) have shown impressive capabilities in temporal reasoning and cross-modal understanding, yet their vulnerability to adversarial attacks remains underexplored due to unique challenges: complex cross-modal reasoning mechanisms, temporal dependencies, and computational constraints. We present CAVALRY-V (Cross-modal Language-Vision Adversarial Yielding for Videos), a novel framework that directly targets the critical interface between visual perception and language generation in V-MLLMs. Our approach introduces two key innovations: (1) a dual-objecti","authors_text":"Jiaming Zhang, Qing Guo, Rui Hu, Wei Yang Bryan Lim","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T14:48:27Z","title":"CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00817","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":"sha256:5bdba01326cd00793067562ebc717f2ce88a715447a78c98b02b77f06134a7c2","target":"record","created_at":"2026-07-05T11:30:14Z","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":"4cd521b92c650ef5dfdbfc056225446b359c8baed94246d569608450460fec31","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T14:48:27Z","title_canon_sha256":"72fa18f4d54b477d4afc8559f3e85a3569720786e2ce74753f725f0baffdf043"},"schema_version":"1.0","source":{"id":"2507.00817","kind":"arxiv","version":1}},"canonical_sha256":"f69d46c3f61fd6d7d8334d445c8ac0b676fc2c4054e53443191c36a6adc2212c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f69d46c3f61fd6d7d8334d445c8ac0b676fc2c4054e53443191c36a6adc2212c","first_computed_at":"2026-07-05T11:30:14.964376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:14.964376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KwnqDqWDFIx/bZ69Wvz7KP0vxjYcS2NU0jNZ4TsUSHGrr+ipLLVnkq6SIHb94uwnlXOA4smkpToVXBpP8Y51Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:14.964822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00817","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bdba01326cd00793067562ebc717f2ce88a715447a78c98b02b77f06134a7c2","sha256:d1711a84be86f1b6e57af6eeff6754d176c3c36ab337b71f9e5eed192f026a63"],"state_sha256":"e23a4ba402646051c8875beaeca0d190730e178b393cbd8205116e939d523718"}