{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SBA4GVL2CDMLGITAB6FDPDXRA6","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":"ebcac5812a4906c4f7fd1319fe6eba63c61b0f83311a3d06ee6963d1b3563bd7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T15:52:30Z","title_canon_sha256":"f6b71a9ba0fc6e39991e9ec0740198f35aca26793cb3f2197428f36ce38575bb"},"schema_version":"1.0","source":{"id":"2607.22716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22716","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22716v1","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22716","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"SBA4GVL2CDML","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"SBA4GVL2CDMLGITA","created_at":"2026-07-28T00:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"SBA4GVL2","created_at":"2026-07-28T00:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:be5a5aa1ec11eab2dc724ef5e01087b90b227e276bab20e85475456b3b0be1ef","target":"graph","created_at":"2026-07-28T00:21:50Z","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/2607.22716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbreak attacks and hallucinations. Given that vision and language modalities cannot be perfectly aligned, the misaligned visual tokens might act as out-of-distribution (OOD) inputs, leading to unpredictable outputs and introducing potential vulnerabilities. Building on this insight, we aim to enhance model robustness against jailbreaks and hallucinations by reducing OOD visual tokens at robust-pruning layers, while also r","authors_text":"Jiequan Cui, Richang Hong, Shishen Gu, Wenbo Hu, Zenglin Shi, Zhenzhen Hu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T15:52:30Z","title":"Visual Token Compression Enhances Robustness of MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22716","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:dba7ffa876d88b45b5f18b148f645fb5917df9d76270774f1d01343ca2c87d61","target":"record","created_at":"2026-07-28T00:21:50Z","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":"ebcac5812a4906c4f7fd1319fe6eba63c61b0f83311a3d06ee6963d1b3563bd7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T15:52:30Z","title_canon_sha256":"f6b71a9ba0fc6e39991e9ec0740198f35aca26793cb3f2197428f36ce38575bb"},"schema_version":"1.0","source":{"id":"2607.22716","kind":"arxiv","version":1}},"canonical_sha256":"9041c3557a10d8b322600f8a378ef107a7e1fce94a8c5034ebebc278bd259a0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9041c3557a10d8b322600f8a378ef107a7e1fce94a8c5034ebebc278bd259a0a","first_computed_at":"2026-07-28T00:21:50.775555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:50.775555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0EOWWbpqvXCJX7pv1lNdiMMdaB4Bbk50xWmkqPlWP1A83+dlRGgQvFhkL9WetXhn+5/aIYGVTtxFi7Kkm8NeAQ==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:50.776382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dba7ffa876d88b45b5f18b148f645fb5917df9d76270774f1d01343ca2c87d61","sha256:be5a5aa1ec11eab2dc724ef5e01087b90b227e276bab20e85475456b3b0be1ef"],"state_sha256":"d0852893710220db4a59ff854f14d01d40dfe8a7d882b4deae57300d8fa1a34e"}