{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FEMXJGTVMRFBA5RPJSXIJYQANB","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":"1bb6ed9a8072f20ced013cda9e08832a9c78e4ddf770cfaedc80fcb7d11bb24a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:14:41Z","title_canon_sha256":"e07fd8ca8b13593a9a43895386d5baf1a900741e082e6d4942ae8ac31a5647cb"},"schema_version":"1.0","source":{"id":"2409.11365","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11365","created_at":"2026-07-05T09:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11365v2","created_at":"2026-07-05T09:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11365","created_at":"2026-07-05T09:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"FEMXJGTVMRFB","created_at":"2026-07-05T09:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"FEMXJGTVMRFBA5RP","created_at":"2026-07-05T09:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"FEMXJGTV","created_at":"2026-07-05T09:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:d138ce5dead97716667be049a59b316ca8b91ec2f393f0365a8b5f76474c0dff","target":"graph","created_at":"2026-07-05T09:17:48Z","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/2409.11365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deployment of multimodal large language models (MLLMs) has demonstrated remarkable success in engaging in conversations involving visual inputs, thanks to the superior power of large language models (LLMs). Those MLLMs are typically built based on the LLMs, with an image encoder to process images into the token embedding space of the LLMs. However, the integration of visual modality has introduced a unique vulnerability: the MLLM becomes susceptible to malicious visual inputs and prone to generating sensitive or harmful responses, even though the LLM has been trained on textual dataset to ","authors_text":"Han Wu, Jiahui Gao, Lanqing Hong, Lingpeng Kong, Renjie Pi, Tianyang Han, Xin Jiang, Zhenguo Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:14:41Z","title":"CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11365","kind":"arxiv","version":2},"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":"sha256:2fbf85cbce1fca46578cdade73e2c4a9313cc85fa94ab5f5eaf505dc90dac62f","target":"record","created_at":"2026-07-05T09:17:48Z","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":"1bb6ed9a8072f20ced013cda9e08832a9c78e4ddf770cfaedc80fcb7d11bb24a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:14:41Z","title_canon_sha256":"e07fd8ca8b13593a9a43895386d5baf1a900741e082e6d4942ae8ac31a5647cb"},"schema_version":"1.0","source":{"id":"2409.11365","kind":"arxiv","version":2}},"canonical_sha256":"2919749a75644a10762f4cae84e2006877799d82dc8a9d25a0d57f147bfaadc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2919749a75644a10762f4cae84e2006877799d82dc8a9d25a0d57f147bfaadc0","first_computed_at":"2026-07-05T09:17:48.253919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:48.253919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PB+Yk3O4s3bbmRh4HDT5pE9uxN/JOiyh7bfpuK4XKabqTIrEW+Ihi9FH+bgotfYvvUNVNEM7lZRNQPi5BDXZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:48.254420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11365","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fbf85cbce1fca46578cdade73e2c4a9313cc85fa94ab5f5eaf505dc90dac62f","sha256:d138ce5dead97716667be049a59b316ca8b91ec2f393f0365a8b5f76474c0dff"],"state_sha256":"538b66c2da5984608154fb924bf014f60e6a3600b47b954da4c0d86e1811a82e"}