{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BQVD4VSZ52GG4AJDJFOO6GKWE7","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":"a81ad6d738144932afc51ec5c4553f5f2bd85a29e8a8664bd5109b74a7e8c947","cross_cats_sorted":["cs.CL","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T11:44:19Z","title_canon_sha256":"4ca4009190fbdb8340d416c3bab59952422046a3247ca5c9a08d6b2634d40cc6"},"schema_version":"1.0","source":{"id":"2506.04909","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04909","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04909v1","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04909","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"BQVD4VSZ52GG","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"BQVD4VSZ52GG4AJD","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"BQVD4VSZ","created_at":"2026-07-05T11:16:38Z"}],"graph_snapshots":[{"event_id":"sha256:81115b1fb0a7fe8101ec951c1bc133ef568ca4e6a5f926762e8daee0befaccc6","target":"graph","created_at":"2026-07-05T11:16:38Z","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/2506.04909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be possibly explained as some kind of hallucination, those models' explicit thought paths enable us to study strategic deception--goal-driven, intentional misinformation where reasoning contradicts outputs. Using representation engineering, we systematically induce, detect, and control such deception in CoT-enabled LLMs, extracting \"deception vectors\" via Linea","authors_text":"Kai Wang, Meng Sun, Yihao Zhang","cross_cats":["cs.CL","cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T11:44:19Z","title":"When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04909","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:f4217baa1e97f1d8234a55d8b34bba4145a52cd8f5ee63c0f19fafd246428252","target":"record","created_at":"2026-07-05T11:16:38Z","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":"a81ad6d738144932afc51ec5c4553f5f2bd85a29e8a8664bd5109b74a7e8c947","cross_cats_sorted":["cs.CL","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T11:44:19Z","title_canon_sha256":"4ca4009190fbdb8340d416c3bab59952422046a3247ca5c9a08d6b2634d40cc6"},"schema_version":"1.0","source":{"id":"2506.04909","kind":"arxiv","version":1}},"canonical_sha256":"0c2a3e5659ee8c6e0123495cef195627e75725aae267e72c2bc97d28cc8e3ed4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c2a3e5659ee8c6e0123495cef195627e75725aae267e72c2bc97d28cc8e3ed4","first_computed_at":"2026-07-05T11:16:38.860333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:38.860333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MmO251Ulq8HC+KGFPl5y0LXYlCotwX9RjQMERV6BJoHEo+qN9/JdeSE4poFpkDwvws8pbY9RO0kKxrVEnX6qDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:38.860884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04909","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4217baa1e97f1d8234a55d8b34bba4145a52cd8f5ee63c0f19fafd246428252","sha256:81115b1fb0a7fe8101ec951c1bc133ef568ca4e6a5f926762e8daee0befaccc6"],"state_sha256":"cf2c43d5edbd2938d4b226ec2e0ae48d8632a06e2d14661fefd427c4b279f6fd"}