{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IVAJQSJDYCHGS6LRA2NTUKHX3X","short_pith_number":"pith:IVAJQSJD","schema_version":"1.0","canonical_sha256":"4540984923c08e697971069b3a28f7dde1e72c99400885afaef3ae7768237825","source":{"kind":"arxiv","id":"2309.15840","version":1},"attestation_state":"computed","paper":{"title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexa Y. Pan, Alex J. Chan, Ilan Moscovitz, Jan Brauner, Lorenzo Pacchiardi, Owain Evans, S\\\"oren Mindermann, Yarin Gal","submitted_at":"2023-09-26T16:07:54Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.15840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T16:07:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"77e150922aa684d1547faa2ec732d4bc69fb1d8b616f6425c4a36a1c8363cd27","abstract_canon_sha256":"75f395ee759af387420d848868b6d2c4c4f0baf0fac4adc657a7835a90cdd21d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:58.436666Z","signature_b64":"1AIIbvvY/2OLNsSKH8ZdHR0AnoSOGO/KjIiEevJmfBPlfpztbDKtpBJU5iCHFE1XY9XK+MBJ/+TBZMsgaf+FBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4540984923c08e697971069b3a28f7dde1e72c99400885afaef3ae7768237825","last_reissued_at":"2026-07-05T06:54:58.436172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:58.436172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexa Y. Pan, Alex J. Chan, Ilan Moscovitz, Jan Brauner, Lorenzo Pacchiardi, Owain Evans, S\\\"oren Mindermann, Yarin Gal","submitted_at":"2023-09-26T16:07:54Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15840","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.15840/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.15840","created_at":"2026-07-05T06:54:58.436224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15840v1","created_at":"2026-07-05T06:54:58.436224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15840","created_at":"2026-07-05T06:54:58.436224+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVAJQSJDYCHG","created_at":"2026-07-05T06:54:58.436224+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVAJQSJDYCHGS6LR","created_at":"2026-07-05T06:54:58.436224+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVAJQSJD","created_at":"2026-07-05T06:54:58.436224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26523","citing_title":"Radical AI Interpretability","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12618","citing_title":"\"Did you lie?\" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18852","citing_title":"Mechanistic Interpretability Needs Philosophy","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2503.11926","citing_title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12826","citing_title":"Scheming Ability in LLM-to-LLM Strategic Interactions","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":246,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09391","citing_title":"Do Linear Probes Generalize Better in Persona Coordinates?","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X","json":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X.json","graph_json":"https://pith.science/api/pith-number/IVAJQSJDYCHGS6LRA2NTUKHX3X/graph.json","events_json":"https://pith.science/api/pith-number/IVAJQSJDYCHGS6LRA2NTUKHX3X/events.json","paper":"https://pith.science/paper/IVAJQSJD"},"agent_actions":{"view_html":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X","download_json":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X.json","view_paper":"https://pith.science/paper/IVAJQSJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15840&json=true","fetch_graph":"https://pith.science/api/pith-number/IVAJQSJDYCHGS6LRA2NTUKHX3X/graph.json","fetch_events":"https://pith.science/api/pith-number/IVAJQSJDYCHGS6LRA2NTUKHX3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X/action/storage_attestation","attest_author":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X/action/author_attestation","sign_citation":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X/action/citation_signature","submit_replication":"https://pith.science/pith/IVAJQSJDYCHGS6LRA2NTUKHX3X/action/replication_record"}},"created_at":"2026-07-05T06:54:58.436224+00:00","updated_at":"2026-07-05T06:54:58.436224+00:00"}