{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F4CTTAVUN5UU4HXEQZAP7WRAYH","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":"30045cca7967dc71187ed516370db9ef9855b6d80305827ffbd3996261f500a0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T07:21:43Z","title_canon_sha256":"2a582818d691bc2099c005e7976b94712408678bb493ad0369e1e6577330e6c5"},"schema_version":"1.0","source":{"id":"2410.06625","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06625","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06625v2","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06625","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"F4CTTAVUN5UU","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"F4CTTAVUN5UU4HXE","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"F4CTTAVU","created_at":"2026-07-05T10:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:385a34baa64643fbd35336443b9cdcbda5ccca3a38a3f1eaa435cfc92b2bfbb0","target":"graph","created_at":"2026-07-05T10:11:25Z","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/2410.06625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) have become essential backbones for multimodal intelligence, yet significant safety challenges limit their real-world application. While textual inputs are often effectively safeguarded, adversarial visual inputs can easily bypass VLM defense mechanisms. Existing defense methods are either resource-intensive, requiring substantial data and compute, or fail to simultaneously ensure safety and usefulness in responses. To address these limitations, we propose a novel two-phase inference-time alignment framework, Evaluating Then Aligning (ETA): 1) Evaluating input vis","authors_text":"Bolian Li, Ruqi Zhang, Yi Ding","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T07:21:43Z","title":"ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06625","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":"sha256:4001d5688604df10305693fb82615cde4f46c65b92cfae042b8a4922b4295475","target":"record","created_at":"2026-07-05T10:11:25Z","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":"30045cca7967dc71187ed516370db9ef9855b6d80305827ffbd3996261f500a0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T07:21:43Z","title_canon_sha256":"2a582818d691bc2099c005e7976b94712408678bb493ad0369e1e6577330e6c5"},"schema_version":"1.0","source":{"id":"2410.06625","kind":"arxiv","version":2}},"canonical_sha256":"2f053982b46f694e1ee48640ffda20c1eab39e804f2129ddb3ba0b481ae4f93e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f053982b46f694e1ee48640ffda20c1eab39e804f2129ddb3ba0b481ae4f93e","first_computed_at":"2026-07-05T10:11:25.498196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:25.498196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bn3biuwQwD66pgnJ4IG7ittdztCVZdHpuVDgd1hQSMTOYDBZjM8VeM/NRM3frQUadVqf3m72dA4XAgkZMXJ2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:25.499091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06625","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4001d5688604df10305693fb82615cde4f46c65b92cfae042b8a4922b4295475","sha256:385a34baa64643fbd35336443b9cdcbda5ccca3a38a3f1eaa435cfc92b2bfbb0"],"state_sha256":"d2dd80e7e2192107567c12dd3609d6e9051a4f9ec9347fcabb900471dd2f3ef7"}