{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KSCNH22Q43F47DXVGWKWS753UA","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":"77d011d519f793b48a0b7968ba8e0a10c8976564274b7561737b7eb6abdcd999","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T06:32:43Z","title_canon_sha256":"c9b071f5c1d5fbed9bd4f180effefed50ad8b437a149282228821e0af384ac42"},"schema_version":"1.0","source":{"id":"2311.01740","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01740","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01740v2","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01740","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_12","alias_value":"KSCNH22Q43F4","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_16","alias_value":"KSCNH22Q43F47DXV","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_8","alias_value":"KSCNH22Q","created_at":"2026-07-05T07:46:25Z"}],"graph_snapshots":[{"event_id":"sha256:4ffb865eddfe33ccce030cc8846939b576e461b9a63c5deeabc4627949aac770","target":"graph","created_at":"2026-07-05T07:46:25Z","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/2311.01740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucination detection is a critical step toward understanding the trustworthiness of modern language models (LMs). To achieve this goal, we re-examine existing detection approaches based on the self-consistency of LMs and uncover two types of hallucinations resulting from 1) question-level and 2) model-level, which cannot be effectively identified through self-consistency check alone. Building upon this discovery, we propose a novel sampling-based method, i.e., semantic-aware cross-check consistency (SAC3) that expands on the principle of self-consistency checking. Our SAC3 approach incorpor","authors_text":"Bradley A. Malin, Jiaxin Zhang, Kamalika Das, Sricharan Kumar, Zhuohang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T06:32:43Z","title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01740","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":"sha256:6c7b5084d3f000bb70d5c8e0940ddaff5afb203bf91c1bb5fefecf9207fb62f3","target":"record","created_at":"2026-07-05T07:46:25Z","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":"77d011d519f793b48a0b7968ba8e0a10c8976564274b7561737b7eb6abdcd999","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T06:32:43Z","title_canon_sha256":"c9b071f5c1d5fbed9bd4f180effefed50ad8b437a149282228821e0af384ac42"},"schema_version":"1.0","source":{"id":"2311.01740","kind":"arxiv","version":2}},"canonical_sha256":"5484d3eb50e6cbcf8ef53595697fbba033ecbd40195421a73c7daacbca9e2757","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5484d3eb50e6cbcf8ef53595697fbba033ecbd40195421a73c7daacbca9e2757","first_computed_at":"2026-07-05T07:46:25.846265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:25.846265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jYtQZpL7BQtHVkGveST1nmXXyohcUo2xxBrvxOHOpvCoZpguX287hbKO/AS0W+7r3nzGs0NCGSgoZkoHk/3PDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:25.847070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01740","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c7b5084d3f000bb70d5c8e0940ddaff5afb203bf91c1bb5fefecf9207fb62f3","sha256:4ffb865eddfe33ccce030cc8846939b576e461b9a63c5deeabc4627949aac770"],"state_sha256":"61670e99e5623332d8cd26c3996e381745ff544e2db43632501a7468cffaf3e7"}