{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6EUQY3NM3XZLJOVXMTGWFS6EWR","short_pith_number":"pith:6EUQY3NM","schema_version":"1.0","canonical_sha256":"f1290c6dacddf2b4bab764cd62cbc4b44b5217150c27a5dcb75e294c20da3787","source":{"kind":"arxiv","id":"2405.19648","version":1},"attestation_state":"computed","paper":{"title":"Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ernesto Quevedo, Jorge Yero, Pablo Rivas, Rachel Koerner, Tomas Cerny","submitted_at":"2024-05-30T03:00:47Z","abstract_excerpt":"Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated content. Current methods often demand substantial resources and rely on extensive LLMs or employ supervised learning with multidimensional features or intricate linguistic and semantic analyses difficult to reproduce and largely depend on using the same LLM that hallucinated. This paper introduces a supervised learning approach employing two simple classifiers "},"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":"2405.19648","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T03:00:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c1d61f128ea8a0e2660168610ef1096117170314948de8008675f19d88e9b577","abstract_canon_sha256":"de549975cb013c8296940390a642d14f5b87f96345114f9dbc90cbdb59532a0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:23.443876Z","signature_b64":"mzTx4p+db2qTrYVqtUo1Dw0lThyE2agt32bSV3PR//NyjsN0FDA/ni/JhpCjPab6kwVjFxQWKuvpGKri1W1YBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1290c6dacddf2b4bab764cd62cbc4b44b5217150c27a5dcb75e294c20da3787","last_reissued_at":"2026-07-05T08:25:23.443395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:23.443395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ernesto Quevedo, Jorge Yero, Pablo Rivas, Rachel Koerner, Tomas Cerny","submitted_at":"2024-05-30T03:00:47Z","abstract_excerpt":"Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated content. Current methods often demand substantial resources and rely on extensive LLMs or employ supervised learning with multidimensional features or intricate linguistic and semantic analyses difficult to reproduce and largely depend on using the same LLM that hallucinated. This paper introduces a supervised learning approach employing two simple classifiers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19648","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/2405.19648/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":"2405.19648","created_at":"2026-07-05T08:25:23.443460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19648v1","created_at":"2026-07-05T08:25:23.443460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19648","created_at":"2026-07-05T08:25:23.443460+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EUQY3NM3XZL","created_at":"2026-07-05T08:25:23.443460+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EUQY3NM3XZLJOVX","created_at":"2026-07-05T08:25:23.443460+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EUQY3NM","created_at":"2026-07-05T08:25:23.443460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25182","citing_title":"What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24790","citing_title":"Grad Detect: Gradient-Based Hallucination Detection in LLMs","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17028","citing_title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR","json":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR.json","graph_json":"https://pith.science/api/pith-number/6EUQY3NM3XZLJOVXMTGWFS6EWR/graph.json","events_json":"https://pith.science/api/pith-number/6EUQY3NM3XZLJOVXMTGWFS6EWR/events.json","paper":"https://pith.science/paper/6EUQY3NM"},"agent_actions":{"view_html":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR","download_json":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR.json","view_paper":"https://pith.science/paper/6EUQY3NM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19648&json=true","fetch_graph":"https://pith.science/api/pith-number/6EUQY3NM3XZLJOVXMTGWFS6EWR/graph.json","fetch_events":"https://pith.science/api/pith-number/6EUQY3NM3XZLJOVXMTGWFS6EWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR/action/storage_attestation","attest_author":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR/action/author_attestation","sign_citation":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR/action/citation_signature","submit_replication":"https://pith.science/pith/6EUQY3NM3XZLJOVXMTGWFS6EWR/action/replication_record"}},"created_at":"2026-07-05T08:25:23.443460+00:00","updated_at":"2026-07-05T08:25:23.443460+00:00"}