{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M2EPCISKLKKUY2J7GGPBDUQYSJ","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":"c58ae6f6af0271b7d48f8252e7ecfe451a7728b2cd4609b76b5d856919658f95","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-04T06:14:08Z","title_canon_sha256":"4257cdf2d95792943ddbc406a1136ab21ff333d07340b395326d33197edd74b7"},"schema_version":"1.0","source":{"id":"2606.05743","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05743","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05743v1","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05743","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"M2EPCISKLKKU","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"M2EPCISKLKKUY2J7","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"M2EPCISK","created_at":"2026-06-05T01:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:b7797c3ae6533e1cca8b088de6a4265a1e583efdb5041d457b4eeb673e3d11a8","target":"graph","created_at":"2026-06-05T01:15:01Z","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/2606.05743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifiers cannot adapt to these evolving attacks, while adaptive memory-based guardrails tend to over-refuse benign queries that resemble stored attacks. We propose Membrane, a self-evolving guardrail built on Contrastive Safety Memory (CSM): each cell pairs the conditions for blocking a harmful query with those for permitting a superficially similar benign request. Without retraining, Membrane evolves CSM by distilling each harmful interaction and its","authors_text":"Dongjin Kim, Jaegul Choo, Jungmin Son, Minseok Choi, Seungbin Yang, Subin Kim, Youngjun Kwak, Yunseung Lee","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-04T06:14:08Z","title":"Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05743","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":"sha256:027988b41997ce24934239383187edaf940f6f26c06756df5c1ce7817c6c6d1a","target":"record","created_at":"2026-06-05T01:15:01Z","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":"c58ae6f6af0271b7d48f8252e7ecfe451a7728b2cd4609b76b5d856919658f95","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-04T06:14:08Z","title_canon_sha256":"4257cdf2d95792943ddbc406a1136ab21ff333d07340b395326d33197edd74b7"},"schema_version":"1.0","source":{"id":"2606.05743","kind":"arxiv","version":1}},"canonical_sha256":"6688f1224a5a954c693f319e11d2189251d71d87e706c9ebf947d91598ae5990","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6688f1224a5a954c693f319e11d2189251d71d87e706c9ebf947d91598ae5990","first_computed_at":"2026-06-05T01:15:01.399299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:01.399299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x72OHgd9gO2tCyW4nSW/ghrSQz875tY/GCZyZTWmpyw4USGXVW6ilpTyn0W7gy4TMfSb6LIMNRCL3PUHzPt6Ag==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:01.399758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05743","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:027988b41997ce24934239383187edaf940f6f26c06756df5c1ce7817c6c6d1a","sha256:b7797c3ae6533e1cca8b088de6a4265a1e583efdb5041d457b4eeb673e3d11a8"],"state_sha256":"bd8d9b5803d4f2bfb23b05f3cb01cb7d3b6e357210cae47e132ed489ff64b47b"}