{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JHN53VR26EYUFIIBVWCINEWNN7","short_pith_number":"pith:JHN53VR2","schema_version":"1.0","canonical_sha256":"49dbddd63af13142a101ad848692cd6fe5173b5f89cf38e1916f657598a44499","source":{"kind":"arxiv","id":"2507.14649","version":1},"attestation_state":"computed","paper":{"title":"Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyunsoo Cho, Minsuh Joo","submitted_at":"2025-07-19T14:48:24Z","abstract_excerpt":"Despite the outstanding performance of large language models (LLMs) across various NLP tasks, hallucinations in LLMs--where LLMs generate inaccurate responses--remains as a critical problem as it can be directly connected to a crisis of building safe and reliable LLMs. Uncertainty estimation is primarily used to measure hallucination levels in LLM responses so that correct and incorrect answers can be distinguished clearly. This study proposes an effective uncertainty estimation approach, \\textbf{Cl}ust\\textbf{e}ring-based sem\\textbf{an}tic con\\textbf{s}ist\\textbf{e}ncy (\\textbf{Cleanse}). Cle"},"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":"2507.14649","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T14:48:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7bb859f535f2ed0b950f33910fccc6edf7df32cbfaae9146185c5340c0b3a23","abstract_canon_sha256":"add2f2a831db4ec853df8cbddedc8878fe052e5f106129a25437b9ba054b0646"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:11.182421Z","signature_b64":"W7cwQtt6aWbxRQtTCzElmHdLcGPs78G9WNuYRqdpP4gHMps7i5nH5XfJvxI7VaJQGqWJZqtkWloe2EgKJFVPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49dbddd63af13142a101ad848692cd6fe5173b5f89cf38e1916f657598a44499","last_reissued_at":"2026-07-05T11:40:11.182019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:11.182019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyunsoo Cho, Minsuh Joo","submitted_at":"2025-07-19T14:48:24Z","abstract_excerpt":"Despite the outstanding performance of large language models (LLMs) across various NLP tasks, hallucinations in LLMs--where LLMs generate inaccurate responses--remains as a critical problem as it can be directly connected to a crisis of building safe and reliable LLMs. Uncertainty estimation is primarily used to measure hallucination levels in LLM responses so that correct and incorrect answers can be distinguished clearly. This study proposes an effective uncertainty estimation approach, \\textbf{Cl}ust\\textbf{e}ring-based sem\\textbf{an}tic con\\textbf{s}ist\\textbf{e}ncy (\\textbf{Cleanse}). Cle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14649","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/2507.14649/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":"2507.14649","created_at":"2026-07-05T11:40:11.182073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14649v1","created_at":"2026-07-05T11:40:11.182073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14649","created_at":"2026-07-05T11:40:11.182073+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHN53VR26EYU","created_at":"2026-07-05T11:40:11.182073+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHN53VR26EYUFIIB","created_at":"2026-07-05T11:40:11.182073+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHN53VR2","created_at":"2026-07-05T11:40:11.182073+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/JHN53VR26EYUFIIBVWCINEWNN7","json":"https://pith.science/pith/JHN53VR26EYUFIIBVWCINEWNN7.json","graph_json":"https://pith.science/api/pith-number/JHN53VR26EYUFIIBVWCINEWNN7/graph.json","events_json":"https://pith.science/api/pith-number/JHN53VR26EYUFIIBVWCINEWNN7/events.json","paper":"https://pith.science/paper/JHN53VR2"},"agent_actions":{"view_html":"https://pith.science/pith/JHN53VR26EYUFIIBVWCINEWNN7","download_json":"https://pith.science/pith/JHN53VR26EYUFIIBVWCINEWNN7.json","view_paper":"https://pith.science/paper/JHN53VR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14649&json=true","fetch_graph":"https://pith.science/api/pith-number/JHN53VR26EYUFIIBVWCINEWNN7/graph.json","fetch_events":"https://pith.science/api/pith-number/JHN53VR26EYUFIIBVWCINEWNN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHN53VR26EYUFIIBVWCINEWNN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHN53VR26EYUFIIBVWCINEWNN7/action/storage_attestation","attest_author":"https://pith.science/pith/JHN53VR26EYUFIIBVWCINEWNN7/action/author_attestation","sign_citation":"https://pith.science/pith/JHN53VR26EYUFIIBVWCINEWNN7/action/citation_signature","submit_replication":"https://pith.science/pith/JHN53VR26EYUFIIBVWCINEWNN7/action/replication_record"}},"created_at":"2026-07-05T11:40:11.182073+00:00","updated_at":"2026-07-05T11:40:11.182073+00:00"}