{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OWKSAWTK2FGMHON4UGZINRKQIV","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":"ee7d9ba85132965606cf5e0837019582470ccdb4eb629a6e77c93c4865ec3e62","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T12:07:00Z","title_canon_sha256":"d43bd3329558fd7d0293419a59cc61dc3d92b13de6e200acab7bba8ce332aa40"},"schema_version":"1.0","source":{"id":"2607.02072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02072","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02072v1","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02072","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"OWKSAWTK2FGM","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"pith_short_16","alias_value":"OWKSAWTK2FGMHON4","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"pith_short_8","alias_value":"OWKSAWTK","created_at":"2026-07-03T01:17:38Z"}],"graph_snapshots":[{"event_id":"sha256:d707689c27f96b8780aca9fa7110de58d8b4fe3d7e6ba5df6a20dc04045d4360","target":"graph","created_at":"2026-07-03T01:17:38Z","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/2607.02072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominately rely on fine-tuning to build classifiers, which often suffer from low generalization and high inference latency. We present kNNGuard, a training-free guardrail that utilizes the activation space of an off-the-shelf LLM. Given a small bank of 50 safe and unsafe prompts, kNNGuard extracts hidden activations and performs multi-layer kNN fusing activation-space and embedding-space scores for classification. Across six domains ","authors_text":"Hamid Nasiri, Mahmoud Abdelfattah, Peter Garraghan","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T12:07:00Z","title":"kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02072","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":"sha256:6993519dd3f8d31fe4dede5954f51d55fda715c35f81d7e46da7f7654869c0d8","target":"record","created_at":"2026-07-03T01:17:38Z","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":"ee7d9ba85132965606cf5e0837019582470ccdb4eb629a6e77c93c4865ec3e62","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T12:07:00Z","title_canon_sha256":"d43bd3329558fd7d0293419a59cc61dc3d92b13de6e200acab7bba8ce332aa40"},"schema_version":"1.0","source":{"id":"2607.02072","kind":"arxiv","version":1}},"canonical_sha256":"7595205a6ad14cc3b9bca1b286c550455dd9cfac6749ba127765833eb0079771","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7595205a6ad14cc3b9bca1b286c550455dd9cfac6749ba127765833eb0079771","first_computed_at":"2026-07-03T01:17:38.960361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:38.960361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xyd5zqrluo6Bq1VhbeXwU0kh3/LAXc0b2g8HVIo/4Chh+JH2UoOrqKoJcmY8v+59HxRSgkeWdQEJ8hpu5P/8BQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:38.960793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6993519dd3f8d31fe4dede5954f51d55fda715c35f81d7e46da7f7654869c0d8","sha256:d707689c27f96b8780aca9fa7110de58d8b4fe3d7e6ba5df6a20dc04045d4360"],"state_sha256":"e449dbab51cd75a857e295b48e6bf868aa62701bc039a751f1fe1be213918b15"}