{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PRQFANIQOOLJDCJTRPTXGNYRVN","short_pith_number":"pith:PRQFANIQ","schema_version":"1.0","canonical_sha256":"7c6050351073969189338be7733711ab57a3081752d7e9c73c741fc8a2d52f0f","source":{"kind":"arxiv","id":"2605.27016","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Relevance of Uncertainty Estimators for LLM Hallucination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Annabelle Blangero, Anna Korba, Karteek Alahari, Nicolas Chesneau, Yedidia Agnimo","submitted_at":"2026-05-26T13:34:54Z","abstract_excerpt":"Large language models (LLMs) are prone to hallucinations, i.e., statements unsupported by the input or training data, hindering reliable deployment. In parallel, numerous uncertainty estimation (UE) methods have been proposed to quantify model confidence and are often implicitly treated as proxies for model failure. However, the relationship between uncertainty and hallucinations remains insufficiently characterized. We present a systematic empirical study of the association between uncertainty estimators and hallucinations in LLMs. Rather than assuming this association, we evaluate directly w"},"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":"2605.27016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T13:34:54Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"322ff5a6bf875141e63d1735625586f7dca3d2bd67566b518aded6dabb9b22bf","abstract_canon_sha256":"68fe3bbc8872bc735d97785faadb31144e60eeb695b15f88d84ab19c1a33a2a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:24.302192Z","signature_b64":"2/p/2N5vZH8s1aa7bor9dZiDt9CMP/y///TRdE3ll0uWcqYO4Ud6Nln8imZj0LtU0+ivIoicSMeNGDMQWzt2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c6050351073969189338be7733711ab57a3081752d7e9c73c741fc8a2d52f0f","last_reissued_at":"2026-05-27T01:06:24.301147Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:24.301147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Relevance of Uncertainty Estimators for LLM Hallucination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Annabelle Blangero, Anna Korba, Karteek Alahari, Nicolas Chesneau, Yedidia Agnimo","submitted_at":"2026-05-26T13:34:54Z","abstract_excerpt":"Large language models (LLMs) are prone to hallucinations, i.e., statements unsupported by the input or training data, hindering reliable deployment. In parallel, numerous uncertainty estimation (UE) methods have been proposed to quantify model confidence and are often implicitly treated as proxies for model failure. However, the relationship between uncertainty and hallucinations remains insufficiently characterized. We present a systematic empirical study of the association between uncertainty estimators and hallucinations in LLMs. Rather than assuming this association, we evaluate directly w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27016","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/2605.27016/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":"2605.27016","created_at":"2026-05-27T01:06:24.301278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27016v1","created_at":"2026-05-27T01:06:24.301278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27016","created_at":"2026-05-27T01:06:24.301278+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRQFANIQOOLJ","created_at":"2026-05-27T01:06:24.301278+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRQFANIQOOLJDCJT","created_at":"2026-05-27T01:06:24.301278+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRQFANIQ","created_at":"2026-05-27T01:06:24.301278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN","json":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN.json","graph_json":"https://pith.science/api/pith-number/PRQFANIQOOLJDCJTRPTXGNYRVN/graph.json","events_json":"https://pith.science/api/pith-number/PRQFANIQOOLJDCJTRPTXGNYRVN/events.json","paper":"https://pith.science/paper/PRQFANIQ"},"agent_actions":{"view_html":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN","download_json":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN.json","view_paper":"https://pith.science/paper/PRQFANIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27016&json=true","fetch_graph":"https://pith.science/api/pith-number/PRQFANIQOOLJDCJTRPTXGNYRVN/graph.json","fetch_events":"https://pith.science/api/pith-number/PRQFANIQOOLJDCJTRPTXGNYRVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN/action/storage_attestation","attest_author":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN/action/author_attestation","sign_citation":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN/action/citation_signature","submit_replication":"https://pith.science/pith/PRQFANIQOOLJDCJTRPTXGNYRVN/action/replication_record"}},"created_at":"2026-05-27T01:06:24.301278+00:00","updated_at":"2026-05-27T01:06:24.301278+00:00"}