{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2RYEBC6IL5OPZ4OOVG7BTOEH2W","short_pith_number":"pith:2RYEBC6I","schema_version":"1.0","canonical_sha256":"d470408bc85f5cfcf1cea9be19b887d59e98ef03f9897bda99030020439fa342","source":{"kind":"arxiv","id":"2503.15850","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chacha Chen, Hua Wei, Longchao Da, Tiejin Chen, Xiaoou Liu, Zhen Lin","submitted_at":"2025-03-20T05:04:29Z","abstract_excerpt":"Large Language Models (LLMs) excel in text generation, reasoning, and decision-making, enabling their adoption in high-stakes domains such as healthcare, law, and transportation. However, their reliability is a major concern, as they often produce plausible but incorrect responses. Uncertainty quantification (UQ) enhances trustworthiness by estimating confidence in outputs, enabling risk mitigation and selective prediction. However, traditional UQ methods struggle with LLMs due to computational constraints and decoding inconsistencies. Moreover, LLMs introduce unique uncertainty sources, such "},"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":"2503.15850","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-20T05:04:29Z","cross_cats_sorted":[],"title_canon_sha256":"cb0f1a0a6de22904c2637e4d9dfa0e9d928ce94569b6844e99085446446e8345","abstract_canon_sha256":"b00b45ab0afd2b63c94110334affca96f7fe1f79dd094bf254520d7577d64c56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:20.118100Z","signature_b64":"ZHs91GIwbToo6lOUREjqHcWcX3+vLPzqH2+cEvo81K5Tn7R/EkHa90d7ONsxHI73ta/imDZk9dwnuwbzijrhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d470408bc85f5cfcf1cea9be19b887d59e98ef03f9897bda99030020439fa342","last_reissued_at":"2026-07-05T11:15:20.117540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:20.117540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chacha Chen, Hua Wei, Longchao Da, Tiejin Chen, Xiaoou Liu, Zhen Lin","submitted_at":"2025-03-20T05:04:29Z","abstract_excerpt":"Large Language Models (LLMs) excel in text generation, reasoning, and decision-making, enabling their adoption in high-stakes domains such as healthcare, law, and transportation. However, their reliability is a major concern, as they often produce plausible but incorrect responses. Uncertainty quantification (UQ) enhances trustworthiness by estimating confidence in outputs, enabling risk mitigation and selective prediction. However, traditional UQ methods struggle with LLMs due to computational constraints and decoding inconsistencies. Moreover, LLMs introduce unique uncertainty sources, such "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15850","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/2503.15850/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":"2503.15850","created_at":"2026-07-05T11:15:20.117638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15850v2","created_at":"2026-07-05T11:15:20.117638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15850","created_at":"2026-07-05T11:15:20.117638+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RYEBC6IL5OP","created_at":"2026-07-05T11:15:20.117638+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RYEBC6IL5OPZ4OO","created_at":"2026-07-05T11:15:20.117638+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RYEBC6I","created_at":"2026-07-05T11:15:20.117638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06327","citing_title":"Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22949","citing_title":"MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22949","citing_title":"MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04152","citing_title":"SocialLM: Social Signal Processing of Patient-Provider Communication using LLMs and Contextual Aggregation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11737","citing_title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13595","citing_title":"Inducing Artificial Uncertainty in Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11235","citing_title":"Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02241","citing_title":"Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02010","citing_title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W","json":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W.json","graph_json":"https://pith.science/api/pith-number/2RYEBC6IL5OPZ4OOVG7BTOEH2W/graph.json","events_json":"https://pith.science/api/pith-number/2RYEBC6IL5OPZ4OOVG7BTOEH2W/events.json","paper":"https://pith.science/paper/2RYEBC6I"},"agent_actions":{"view_html":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W","download_json":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W.json","view_paper":"https://pith.science/paper/2RYEBC6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15850&json=true","fetch_graph":"https://pith.science/api/pith-number/2RYEBC6IL5OPZ4OOVG7BTOEH2W/graph.json","fetch_events":"https://pith.science/api/pith-number/2RYEBC6IL5OPZ4OOVG7BTOEH2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W/action/storage_attestation","attest_author":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W/action/author_attestation","sign_citation":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W/action/citation_signature","submit_replication":"https://pith.science/pith/2RYEBC6IL5OPZ4OOVG7BTOEH2W/action/replication_record"}},"created_at":"2026-07-05T11:15:20.117638+00:00","updated_at":"2026-07-05T11:15:20.117638+00:00"}