{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ORUSCBSI5U5L44FIMOM6E3W3IF","short_pith_number":"pith:ORUSCBSI","canonical_record":{"source":{"id":"2606.03486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T11:01:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1bb9489e216873b5a80a59de48b3a04e492fc48f2ca517922a6bbee92b5c6e21","abstract_canon_sha256":"0b8650226d5baf32b1c2d2729acfb99080864f4384cb93fb4611a6256fa2fd94"},"schema_version":"1.0"},"canonical_sha256":"7469210648ed3abe70a86399e26edb416381f0147706bac0707d2a9748e6b5c9","source":{"kind":"arxiv","id":"2606.03486","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ORUSCBSI5U5L44FIMOM6E3W3IF","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T11:01:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1bb9489e216873b5a80a59de48b3a04e492fc48f2ca517922a6bbee92b5c6e21","abstract_canon_sha256":"0b8650226d5baf32b1c2d2729acfb99080864f4384cb93fb4611a6256fa2fd94"},"schema_version":"1.0"},"canonical_sha256":"7469210648ed3abe70a86399e26edb416381f0147706bac0707d2a9748e6b5c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:59.051814Z","signature_b64":"oiEz2gLn5FeHyM4IDE/zfs1NZJ7/sT3hPx47DpV+gnRG6JZ5G6rCVigrfm+jzIyableayWAZM/Y/FdjJsAdYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7469210648ed3abe70a86399e26edb416381f0147706bac0707d2a9748e6b5c9","last_reissued_at":"2026-06-03T01:05:59.051434Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:59.051434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03486","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXHncjOn/EPukNuji/EPP+5YaJOctpva3BwRQk1E33yIb5VAI3vaxli6nAffnnDal5YL6+fLjp1hDsDjVF68BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T09:37:53.299520Z"},"content_sha256":"091a2e3a8f1894bb10f52b673fe1fd18a415d643718347be75e1e72e91655bfd","schema_version":"1.0","event_id":"sha256:091a2e3a8f1894bb10f52b673fe1fd18a415d643718347be75e1e72e91655bfd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ORUSCBSI5U5L44FIMOM6E3W3IF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Feifei Zhai, Pengyuan Liu, Zhongyang Lin, Ziran Zhao","submitted_at":"2026-06-02T11:01:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03486","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.03486/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KIDPELAGBwb9yMyjGE+SJxxY8ZLmIJROAktIqQpm3DoG1B0dlTo/TbWeQDUlbmjkl4Qs3nAhZQh3giefX7raDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T09:37:53.299900Z"},"content_sha256":"0ffac9f7d676aa768bee278f289ed8cafa5f0093c157d3c9db7da14bf694e2eb","schema_version":"1.0","event_id":"sha256:0ffac9f7d676aa768bee278f289ed8cafa5f0093c157d3c9db7da14bf694e2eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORUSCBSI5U5L44FIMOM6E3W3IF/bundle.json","state_url":"https://pith.science/pith/ORUSCBSI5U5L44FIMOM6E3W3IF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORUSCBSI5U5L44FIMOM6E3W3IF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T09:37:53Z","links":{"resolver":"https://pith.science/pith/ORUSCBSI5U5L44FIMOM6E3W3IF","bundle":"https://pith.science/pith/ORUSCBSI5U5L44FIMOM6E3W3IF/bundle.json","state":"https://pith.science/pith/ORUSCBSI5U5L44FIMOM6E3W3IF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORUSCBSI5U5L44FIMOM6E3W3IF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/rPsBcvmDj81hlZE/gU69IBgdqvtperVFD2k1C83dZFbjigi97JkamYMCcWN76nHODqM4UPRqkC4oONeBBFdDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T09:37:53.301901Z","bundle_sha256":"4efd2fdb588bcec50c6bff7028c5d4b5432e7ecb0c0a5973c19f9352bed2e4d1"}}