{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G3BXTFOROGF6P4IGJDVXHSBIWA","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":"3867afbcf55988ad96022ccf2ade5f8fa1484253390d61818ab4155d0de468d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T03:41:29Z","title_canon_sha256":"82a6ad423e07d264b55e1e5088fdcf6fbb3969173ae62195ebfe86e8ac330e30"},"schema_version":"1.0","source":{"id":"2606.17478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17478","created_at":"2026-06-19T16:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17478v1","created_at":"2026-06-19T16:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17478","created_at":"2026-06-19T16:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"G3BXTFOROGF6","created_at":"2026-06-19T16:10:14Z"},{"alias_kind":"pith_short_16","alias_value":"G3BXTFOROGF6P4IG","created_at":"2026-06-19T16:10:14Z"},{"alias_kind":"pith_short_8","alias_value":"G3BXTFOR","created_at":"2026-06-19T16:10:14Z"}],"graph_snapshots":[{"event_id":"sha256:e61c183fa697ecb9c386507e509207169c42e0e122e7b0f7743d5f367a5fbaa4","target":"graph","created_at":"2026-06-19T16:10:14Z","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/2606.17478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern. Existing deception monitors either score visible transcripts or derive scalar probe scores from representation vectors, leaving little inspectable evidence about why a response is suspicious. We introduce STATEWITNESS, an activation explainer for deception auditing. A separate decoder reads a target model's hidden states, then answers natural-language queries or emits structured reports about them. We evaluate STATEWITNESS on two target reasoning LLMs across seven deception datas","authors_text":"Dongxia Wang, Haonan Zhang, Kexin Chen, Xinyu Deng, Yanhui Li, Yi Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T03:41:29Z","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17478","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":"sha256:7bd9f0b36ca869d92569c36fe8e2e1f85786f24169f67f4810b5a6fb650137bf","target":"record","created_at":"2026-06-19T16:10:14Z","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":"3867afbcf55988ad96022ccf2ade5f8fa1484253390d61818ab4155d0de468d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T03:41:29Z","title_canon_sha256":"82a6ad423e07d264b55e1e5088fdcf6fbb3969173ae62195ebfe86e8ac330e30"},"schema_version":"1.0","source":{"id":"2606.17478","kind":"arxiv","version":1}},"canonical_sha256":"36c37995d1718be7f10648eb73c828b033916e065c99df7931ce5f8349fdf6a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36c37995d1718be7f10648eb73c828b033916e065c99df7931ce5f8349fdf6a3","first_computed_at":"2026-06-19T16:10:14.074601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:14.074601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8niSwSvgYn0TC0iHgct4IlGSWFX3ulVBjR4R2w/l8MJsspc4jAfDccI2i2Pd2ygwE5jXDEuzWxdQGKTPEqoICA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:14.074964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bd9f0b36ca869d92569c36fe8e2e1f85786f24169f67f4810b5a6fb650137bf","sha256:e61c183fa697ecb9c386507e509207169c42e0e122e7b0f7743d5f367a5fbaa4"],"state_sha256":"aafcdc4aed83b5deee954986d7b3e7b3545723253b57ac774b45263c583b7aa3"}