{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ORUSCBSI5U5L44FIMOM6E3W3IF","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":"0b8650226d5baf32b1c2d2729acfb99080864f4384cb93fb4611a6256fa2fd94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T11:01:50Z","title_canon_sha256":"1bb9489e216873b5a80a59de48b3a04e492fc48f2ca517922a6bbee92b5c6e21"},"schema_version":"1.0","source":{"id":"2606.03486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03486","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03486v1","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03486","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"ORUSCBSI5U5L","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"ORUSCBSI5U5L44FI","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"ORUSCBSI","created_at":"2026-06-03T01:05:59Z"}],"graph_snapshots":[{"event_id":"sha256:0ffac9f7d676aa768bee278f289ed8cafa5f0093c157d3c9db7da14bf694e2eb","target":"graph","created_at":"2026-06-03T01:05:59Z","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/2606.03486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translation, encoding, adversarial suffixes, and multi-turn buildup. Existing defenses still struggle to handle these attacks without over-blocking benign but sensitive requests, partly because they often apply the same action to every prompt and therefore fail to balance safety and helpfulness. We propose NeuroArmor, a white-box runtime defense that uses prompt-specific safe variants as a local safety reference for deciding when intervention is needed and","authors_text":"Feifei Zhai, Pengyuan Liu, Zhongyang Lin, Ziran Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T11:01:50Z","title":"NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03486","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":"sha256:091a2e3a8f1894bb10f52b673fe1fd18a415d643718347be75e1e72e91655bfd","target":"record","created_at":"2026-06-03T01:05:59Z","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":"0b8650226d5baf32b1c2d2729acfb99080864f4384cb93fb4611a6256fa2fd94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T11:01:50Z","title_canon_sha256":"1bb9489e216873b5a80a59de48b3a04e492fc48f2ca517922a6bbee92b5c6e21"},"schema_version":"1.0","source":{"id":"2606.03486","kind":"arxiv","version":1}},"canonical_sha256":"7469210648ed3abe70a86399e26edb416381f0147706bac0707d2a9748e6b5c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7469210648ed3abe70a86399e26edb416381f0147706bac0707d2a9748e6b5c9","first_computed_at":"2026-06-03T01:05:59.051434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:59.051434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oiEz2gLn5FeHyM4IDE/zfs1NZJ7/sT3hPx47DpV+gnRG6JZ5G6rCVigrfm+jzIyableayWAZM/Y/FdjJsAdYAw==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:59.051814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:091a2e3a8f1894bb10f52b673fe1fd18a415d643718347be75e1e72e91655bfd","sha256:0ffac9f7d676aa768bee278f289ed8cafa5f0093c157d3c9db7da14bf694e2eb"],"state_sha256":"521be523b8042cf660ce9cab4b56120529c8c52d4588ec851aa2fccff48d5eb9"}