{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7YF2LCIPNXOL736HX2I2SGIHS5","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":"7e2dede3fe07a47c7679bb3ad8f0b25fcb86e9a39dc8ee3afc68ae07137aff63","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-27T09:47:57Z","title_canon_sha256":"55bff1aba6de3959a83cae2af3605a67105ee8b4f3a02dfebc5a8c4e8778c721"},"schema_version":"1.0","source":{"id":"2603.26846","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.26846","created_at":"2026-06-08T01:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2603.26846v2","created_at":"2026-06-08T01:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26846","created_at":"2026-06-08T01:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"7YF2LCIPNXOL","created_at":"2026-06-08T01:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"7YF2LCIPNXOL736H","created_at":"2026-06-08T01:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"7YF2LCIP","created_at":"2026-06-08T01:04:02Z"}],"graph_snapshots":[{"event_id":"sha256:2b1d0df4aaadae75c2cfcfe90445d064b1dc3548d9680c24c5e410608e4d0b50","target":"graph","created_at":"2026-06-08T01:04:02Z","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/2603.26846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategically mislead users to achieve their own objectives. Existing alignment approaches based on chain-of-thought (CoT) monitoring supervise explicit reasoning traces. However, under optimization pressure, models are incentivized to conceal deceptive reasoning, rendering semantic supervision fundamentally unreliable. Grounded in cognitive psychology, we hypothesize that a deceptive LLM maintains a stable internal belief in it","authors_text":"Guoxi Zhang, Jiawei Chen, Jingwei Yi, Juntao Dai, Lang Qin, Tianzhuo Yang, Yaodong Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-27T09:47:57Z","title":"Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.26846","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":"sha256:7c9a670a8407ab190b1e4d163342be205bb0ad7797acfbe4354032ca3dc4bcce","target":"record","created_at":"2026-06-08T01:04:02Z","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":"7e2dede3fe07a47c7679bb3ad8f0b25fcb86e9a39dc8ee3afc68ae07137aff63","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-27T09:47:57Z","title_canon_sha256":"55bff1aba6de3959a83cae2af3605a67105ee8b4f3a02dfebc5a8c4e8778c721"},"schema_version":"1.0","source":{"id":"2603.26846","kind":"arxiv","version":2}},"canonical_sha256":"fe0ba5890f6ddcbfefc7be91a919079749564a04b5cb5656038f665865a9888a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe0ba5890f6ddcbfefc7be91a919079749564a04b5cb5656038f665865a9888a","first_computed_at":"2026-06-08T01:04:02.603847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:02.603847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d0BRIl1uOEKLSSXi6TnXwqP5rEo1mrccerH5XlAppYqgRSWsaDHJ96nXJCa27yfrsHkjbXj7lBdf9FNYEBPOCQ==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:02.604848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.26846","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c9a670a8407ab190b1e4d163342be205bb0ad7797acfbe4354032ca3dc4bcce","sha256:2b1d0df4aaadae75c2cfcfe90445d064b1dc3548d9680c24c5e410608e4d0b50"],"state_sha256":"933c1e1d529ba3fad1309d13c9f2bc8f1f97855077da268ae72e80b6de74a744"}