{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4D6FBQZ7RANEOPAXE6SWBBBEVZ","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":"2eb54d16aaf1f6f3990551792995a9154ed45cb9fa5ef003207adedadbfc03b8","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-23T04:23:07Z","title_canon_sha256":"b7a48cd740c1457713026ba84cc98f69204992851606afc60c823bd0d27904a4"},"schema_version":"1.0","source":{"id":"2503.17932","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17932","created_at":"2026-07-05T10:37:58Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17932v1","created_at":"2026-07-05T10:37:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17932","created_at":"2026-07-05T10:37:58Z"},{"alias_kind":"pith_short_12","alias_value":"4D6FBQZ7RANE","created_at":"2026-07-05T10:37:58Z"},{"alias_kind":"pith_short_16","alias_value":"4D6FBQZ7RANEOPAX","created_at":"2026-07-05T10:37:58Z"},{"alias_kind":"pith_short_8","alias_value":"4D6FBQZ7","created_at":"2026-07-05T10:37:58Z"}],"graph_snapshots":[{"event_id":"sha256:eb017f3fc5a05234841f25f21c7431de01c28b4248d1133d7226912c84990351","target":"graph","created_at":"2026-07-05T10:37:58Z","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/2503.17932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from adaptive attacks or require computationally expensive auxiliary models, we present STShield, a lightweight framework for real-time jailbroken judgement. STShield introduces a novel single-token sentinel mechanism that appends a binary safety indicator to the model's response sequence, leveraging the LLM's own alignment capabilities for detection. Our framework combines supervised fine-tuning on normal prompts with adver","authors_text":"Daoyuan Wu, Pingchuan Ma, Shuai Wang, Wenxuan Wang, Xunguang Wang, Zhenlan Ji, Zongjie Li","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-23T04:23:07Z","title":"STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17932","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":"sha256:4b36302863d702a85079383bb9c3d6a71f533ddfed9b271506178cd242456d43","target":"record","created_at":"2026-07-05T10:37:58Z","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":"2eb54d16aaf1f6f3990551792995a9154ed45cb9fa5ef003207adedadbfc03b8","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-23T04:23:07Z","title_canon_sha256":"b7a48cd740c1457713026ba84cc98f69204992851606afc60c823bd0d27904a4"},"schema_version":"1.0","source":{"id":"2503.17932","kind":"arxiv","version":1}},"canonical_sha256":"e0fc50c33f881a473c1727a5608424ae4a748b10a7ec5ece411fc078effd9a9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0fc50c33f881a473c1727a5608424ae4a748b10a7ec5ece411fc078effd9a9f","first_computed_at":"2026-07-05T10:37:58.952235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:58.952235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gNIxzYxGIhxi5q0s0pdqWqcT2zv6R7+KM1FRg18rLuEQaLEy+gLvA3rvJi2CPQlu+igg8HSkE6s40VaGSHTIDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:58.952775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17932","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b36302863d702a85079383bb9c3d6a71f533ddfed9b271506178cd242456d43","sha256:eb017f3fc5a05234841f25f21c7431de01c28b4248d1133d7226912c84990351"],"state_sha256":"f50ece48cf8926c174a2437587077e0c0591088db5c543b1058aeb08101619c4"}