{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNQYCEDCE4Y567NUTIZ6WLCANL","short_pith_number":"pith:FNQYCEDC","schema_version":"1.0","canonical_sha256":"2b618110622731df7db49a33eb2c406afe7bcb071ead87b55597f489d15539db","source":{"kind":"arxiv","id":"2410.22685","version":1},"attestation_state":"computed","paper":{"title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Edwin V. Bonilla, Thang D. Bui, Yashvir S. Grewal","submitted_at":"2024-10-30T04:41:46Z","abstract_excerpt":"Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict bidirectional entailment criteria between multiple generated responses and also depend on sequence likelihoods. While effective, these approaches often overestimate uncertainty due to their sensitivity to minor wording differences, additional correct information, and non-important words in the sequence. We propose a novel approach that leverages semantic emb"},"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":"2410.22685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T04:41:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"285526beef4c4ca6bd66e0298312fe0a272360c39f4ba97c93913bc7f63a717b","abstract_canon_sha256":"e247bd87e99d3f61a20123bd62d579e1f4dbc19ab1b7acfcbc7ef6bf1805bb7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:20.183835Z","signature_b64":"6i18e8mYUJdnpQ1OUYrls+41d+7ynnt9xyXYOOyMrLgLMhOck3mo/deypBefa4422YnLFiQz5CMCFCfu6qNfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b618110622731df7db49a33eb2c406afe7bcb071ead87b55597f489d15539db","last_reissued_at":"2026-07-05T09:28:20.183414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:20.183414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Edwin V. Bonilla, Thang D. Bui, Yashvir S. Grewal","submitted_at":"2024-10-30T04:41:46Z","abstract_excerpt":"Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict bidirectional entailment criteria between multiple generated responses and also depend on sequence likelihoods. While effective, these approaches often overestimate uncertainty due to their sensitivity to minor wording differences, additional correct information, and non-important words in the sequence. We propose a novel approach that leverages semantic emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22685","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/2410.22685/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":"2410.22685","created_at":"2026-07-05T09:28:20.183474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22685v1","created_at":"2026-07-05T09:28:20.183474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22685","created_at":"2026-07-05T09:28:20.183474+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNQYCEDCE4Y5","created_at":"2026-07-05T09:28:20.183474+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNQYCEDCE4Y567NU","created_at":"2026-07-05T09:28:20.183474+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNQYCEDC","created_at":"2026-07-05T09:28:20.183474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19868","citing_title":"A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19559","citing_title":"Uncertainty Decomposition for Clarification Seeking in LLM Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32032","citing_title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28920","citing_title":"Conf-Gen: Conformal Uncertainty Quantification for Generative Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28778","citing_title":"Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12015","citing_title":"Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2506.10060","citing_title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08346","citing_title":"Sanity Checks for Long-Form Hallucination Detection","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL","json":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL.json","graph_json":"https://pith.science/api/pith-number/FNQYCEDCE4Y567NUTIZ6WLCANL/graph.json","events_json":"https://pith.science/api/pith-number/FNQYCEDCE4Y567NUTIZ6WLCANL/events.json","paper":"https://pith.science/paper/FNQYCEDC"},"agent_actions":{"view_html":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL","download_json":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL.json","view_paper":"https://pith.science/paper/FNQYCEDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22685&json=true","fetch_graph":"https://pith.science/api/pith-number/FNQYCEDCE4Y567NUTIZ6WLCANL/graph.json","fetch_events":"https://pith.science/api/pith-number/FNQYCEDCE4Y567NUTIZ6WLCANL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL/action/storage_attestation","attest_author":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL/action/author_attestation","sign_citation":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL/action/citation_signature","submit_replication":"https://pith.science/pith/FNQYCEDCE4Y567NUTIZ6WLCANL/action/replication_record"}},"created_at":"2026-07-05T09:28:20.183474+00:00","updated_at":"2026-07-05T09:28:20.183474+00:00"}