{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IVAJQSJDYCHGS6LRA2NTUKHX3X","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":"75f395ee759af387420d848868b6d2c4c4f0baf0fac4adc657a7835a90cdd21d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T16:07:54Z","title_canon_sha256":"77e150922aa684d1547faa2ec732d4bc69fb1d8b616f6425c4a36a1c8363cd27"},"schema_version":"1.0","source":{"id":"2309.15840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15840","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15840v1","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15840","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"IVAJQSJDYCHG","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_16","alias_value":"IVAJQSJDYCHGS6LR","created_at":"2026-07-05T06:54:58Z"},{"alias_kind":"pith_short_8","alias_value":"IVAJQSJD","created_at":"2026-07-05T06:54:58Z"}],"graph_snapshots":[{"event_id":"sha256:78a3391c2cd0341377e25765819f99b6cba91347dbff3472d76b9694610f5915","target":"graph","created_at":"2026-07-05T06:54:58Z","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/2309.15840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) can \"lie\", which we define as outputting false statements despite \"knowing\" the truth in a demonstrable sense. LLMs might \"lie\", for example, when instructed to output misinformation. Here, we develop a simple lie detector that requires neither access to the LLM's activations (black-box) nor ground-truth knowledge of the fact in question. The detector works by asking a predefined set of unrelated follow-up questions after a suspected lie, and feeding the LLM's yes/no answers into a logistic regression classifier. Despite its simplicity, this lie detector is highly ","authors_text":"Alexa Y. Pan, Alex J. Chan, Ilan Moscovitz, Jan Brauner, Lorenzo Pacchiardi, Owain Evans, S\\\"oren Mindermann, Yarin Gal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T16:07:54Z","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15840","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":"sha256:776f16e32d97574a1f20ce6282568cadb5ae52b92710d80c966e3dac602df094","target":"record","created_at":"2026-07-05T06:54:58Z","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":"75f395ee759af387420d848868b6d2c4c4f0baf0fac4adc657a7835a90cdd21d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T16:07:54Z","title_canon_sha256":"77e150922aa684d1547faa2ec732d4bc69fb1d8b616f6425c4a36a1c8363cd27"},"schema_version":"1.0","source":{"id":"2309.15840","kind":"arxiv","version":1}},"canonical_sha256":"4540984923c08e697971069b3a28f7dde1e72c99400885afaef3ae7768237825","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4540984923c08e697971069b3a28f7dde1e72c99400885afaef3ae7768237825","first_computed_at":"2026-07-05T06:54:58.436172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:58.436172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1AIIbvvY/2OLNsSKH8ZdHR0AnoSOGO/KjIiEevJmfBPlfpztbDKtpBJU5iCHFE1XY9XK+MBJ/+TBZMsgaf+FBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:58.436666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:776f16e32d97574a1f20ce6282568cadb5ae52b92710d80c966e3dac602df094","sha256:78a3391c2cd0341377e25765819f99b6cba91347dbff3472d76b9694610f5915"],"state_sha256":"608a8a01b9eb12a49f87373e357fbbc6957ac6eaa3b091a8628af367c2893ad0"}