{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MZFUZAAV5IVIV7SUH4UHX7QCCD","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":"048c56b92caffca42f4998f13b3a17f3f2196cad32098bdeaba5cff46d055fab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T21:06:08Z","title_canon_sha256":"0d974ee802519e0f93832ac232cfc9c44ab0e00c531ccc0b7da4d3f9c8ab69b2"},"schema_version":"1.0","source":{"id":"2502.15845","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15845","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15845v2","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15845","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_12","alias_value":"MZFUZAAV5IVI","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_16","alias_value":"MZFUZAAV5IVIV7SU","created_at":"2026-07-01T00:17:07Z"},{"alias_kind":"pith_short_8","alias_value":"MZFUZAAV","created_at":"2026-07-01T00:17:07Z"}],"graph_snapshots":[{"event_id":"sha256:6281fc9a35164df9b1f9afa229254c884e20ccee234319f2830dac862aa1689a","target":"graph","created_at":"2026-07-01T00:17:07Z","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/2502.15845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) often hallucinate, limiting their reliability in sensitive applications. In black-box settings, several self-consistency-based techniques have been proposed for hallucination detection. We empirically show that these methods perform nearly as well as a supervised (black-box) oracle, leaving limited room for further gains within this paradigm. To address this limitation, we explore cross-model consistency checking between the target model and an additional verifier LLM. With this extra information, we observe improved oracle performance compared to purely self-consi","authors_text":"Baharan Mirzasoleiman, Kristjan Greenewald, Yihao Xue, Youssef Mroueh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T21:06:08Z","title":"Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15845","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":"sha256:6bf945ff5434047aaf02b4ad8c76ec048e65a96c0efb45e3af775280cba5ebb0","target":"record","created_at":"2026-07-01T00:17:07Z","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":"048c56b92caffca42f4998f13b3a17f3f2196cad32098bdeaba5cff46d055fab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T21:06:08Z","title_canon_sha256":"0d974ee802519e0f93832ac232cfc9c44ab0e00c531ccc0b7da4d3f9c8ab69b2"},"schema_version":"1.0","source":{"id":"2502.15845","kind":"arxiv","version":2}},"canonical_sha256":"664b4c8015ea2a8afe543f287bfe0210e1df91129bf0412ee0063468f85c2139","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"664b4c8015ea2a8afe543f287bfe0210e1df91129bf0412ee0063468f85c2139","first_computed_at":"2026-07-01T00:17:07.913000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T00:17:07.913000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RkzjPYcCypu9QKO1Zl52f9fOOd4sAEv5tgtY4OhRttiZSvpdA+nZIBawzqaECfQX2GVr6mUv5yOHOyFRnyTlAw==","signature_status":"signed_v1","signed_at":"2026-07-01T00:17:07.913534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15845","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bf945ff5434047aaf02b4ad8c76ec048e65a96c0efb45e3af775280cba5ebb0","sha256:6281fc9a35164df9b1f9afa229254c884e20ccee234319f2830dac862aa1689a"],"state_sha256":"35c135e26118e87be4541cc333dbae461876e61f87acda8c2aa6fe664dad0947"}