{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D6WJZD7UPEERE333U3KWM4YOLI","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":"3cc947f60635f74ce0dddba1bcc03f5a3ff79c0f86032bbf90b6b1afbcfc0a74","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T06:09:58Z","title_canon_sha256":"61bf35919ef9b8ec3858c47e49e84f8bbb7fdfe9cafbd8edb8966aef29ff5564"},"schema_version":"1.0","source":{"id":"2502.13458","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13458","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13458v2","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13458","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"pith_short_12","alias_value":"D6WJZD7UPEER","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"pith_short_16","alias_value":"D6WJZD7UPEERE333","created_at":"2026-07-05T11:10:52Z"},{"alias_kind":"pith_short_8","alias_value":"D6WJZD7U","created_at":"2026-07-05T11:10:52Z"}],"graph_snapshots":[{"event_id":"sha256:042a5969c836ea8def38406e051aa782166ec5eb5f2bc6a192c7db276953376f","target":"graph","created_at":"2026-07-05T11:10:52Z","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/2502.13458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety violations. To address this, we propose ThinkGuard, a critique-augmented guardrail model that distills knowledge from high-capacity LLMs by generating structured critiques alongside safety labels. Fine-tuned on critique-augmented data, the captured deliberative thinking ability drastically enhances the guardrail's cautiousness and interpretability. Evaluate","authors_text":"Muhao Chen, Wenjie Jacky Mo, Wenxuan Zhou, Xiaofei Wen","cross_cats":["cs.AI","cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T06:09:58Z","title":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13458","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":"sha256:8c36688df9d0c04e46854f7d20523240d5fe9135fc800575c41bba91962d10da","target":"record","created_at":"2026-07-05T11:10:52Z","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":"3cc947f60635f74ce0dddba1bcc03f5a3ff79c0f86032bbf90b6b1afbcfc0a74","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T06:09:58Z","title_canon_sha256":"61bf35919ef9b8ec3858c47e49e84f8bbb7fdfe9cafbd8edb8966aef29ff5564"},"schema_version":"1.0","source":{"id":"2502.13458","kind":"arxiv","version":2}},"canonical_sha256":"1fac9c8ff47909126f7ba6d566730e5a0c0d1b1648601b80e0ab7a0e7887aa4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fac9c8ff47909126f7ba6d566730e5a0c0d1b1648601b80e0ab7a0e7887aa4f","first_computed_at":"2026-07-05T11:10:52.922737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:52.922737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MH8aG2hcTs4ZDMTKdKieWrkwv7D+lIUfJL9WBIu9d/lONjiywwESH4U4adpzasAfRPxKZ0TDQAxDsp0ElobfDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:52.923207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13458","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c36688df9d0c04e46854f7d20523240d5fe9135fc800575c41bba91962d10da","sha256:042a5969c836ea8def38406e051aa782166ec5eb5f2bc6a192c7db276953376f"],"state_sha256":"7d2e498fb8ab005f068bad6ff599355616b241f24f1d74bb648515afb6b04b0b"}