{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KSCNH22Q43F47DXVGWKWS753UA","short_pith_number":"pith:KSCNH22Q","schema_version":"1.0","canonical_sha256":"5484d3eb50e6cbcf8ef53595697fbba033ecbd40195421a73c7daacbca9e2757","source":{"kind":"arxiv","id":"2311.01740","version":2},"attestation_state":"computed","paper":{"title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bradley A. Malin, Jiaxin Zhang, Kamalika Das, Sricharan Kumar, Zhuohang Li","submitted_at":"2023-11-03T06:32:43Z","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"},"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":"2311.01740","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T06:32:43Z","cross_cats_sorted":[],"title_canon_sha256":"c9b071f5c1d5fbed9bd4f180effefed50ad8b437a149282228821e0af384ac42","abstract_canon_sha256":"77d011d519f793b48a0b7968ba8e0a10c8976564274b7561737b7eb6abdcd999"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:25.847070Z","signature_b64":"jYtQZpL7BQtHVkGveST1nmXXyohcUo2xxBrvxOHOpvCoZpguX287hbKO/AS0W+7r3nzGs0NCGSgoZkoHk/3PDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5484d3eb50e6cbcf8ef53595697fbba033ecbd40195421a73c7daacbca9e2757","last_reissued_at":"2026-07-05T07:46:25.846265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:25.846265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bradley A. Malin, Jiaxin Zhang, Kamalika Das, Sricharan Kumar, Zhuohang Li","submitted_at":"2023-11-03T06:32:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01740","kind":"arxiv","version":2},"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/2311.01740/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":"2311.01740","created_at":"2026-07-05T07:46:25.846347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01740v2","created_at":"2026-07-05T07:46:25.846347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01740","created_at":"2026-07-05T07:46:25.846347+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSCNH22Q43F4","created_at":"2026-07-05T07:46:25.846347+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSCNH22Q43F47DXV","created_at":"2026-07-05T07:46:25.846347+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSCNH22Q","created_at":"2026-07-05T07:46:25.846347+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03535","citing_title":"Can LLM Rerankers Predict Their Own Ranking Performance?","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07353","citing_title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA","json":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA.json","graph_json":"https://pith.science/api/pith-number/KSCNH22Q43F47DXVGWKWS753UA/graph.json","events_json":"https://pith.science/api/pith-number/KSCNH22Q43F47DXVGWKWS753UA/events.json","paper":"https://pith.science/paper/KSCNH22Q"},"agent_actions":{"view_html":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA","download_json":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA.json","view_paper":"https://pith.science/paper/KSCNH22Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01740&json=true","fetch_graph":"https://pith.science/api/pith-number/KSCNH22Q43F47DXVGWKWS753UA/graph.json","fetch_events":"https://pith.science/api/pith-number/KSCNH22Q43F47DXVGWKWS753UA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA/action/storage_attestation","attest_author":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA/action/author_attestation","sign_citation":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA/action/citation_signature","submit_replication":"https://pith.science/pith/KSCNH22Q43F47DXVGWKWS753UA/action/replication_record"}},"created_at":"2026-07-05T07:46:25.846347+00:00","updated_at":"2026-07-05T07:46:25.846347+00:00"}