{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MU3MVGWX6PJAB4RG6ZCFGGYJNI","short_pith_number":"pith:MU3MVGWX","schema_version":"1.0","canonical_sha256":"6536ca9ad7f3d200f226f644531b096a3c751df169b7d26ffbb86fb2484a0bfb","source":{"kind":"arxiv","id":"2412.05563","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Allen Z. Ren, Anirudha Majumdar, Justin Lidard, Ola Shorinwa, Zhiting Mei","submitted_at":"2024-12-07T06:56:01Z","abstract_excerpt":"The remarkable performance of large language models (LLMs) in content generation, coding, and common-sense reasoning has spurred widespread integration into many facets of society. However, integration of LLMs raises valid questions on their reliability and trustworthiness, given their propensity to generate hallucinations: plausible, factually-incorrect responses, which are expressed with striking confidence. Previous work has shown that hallucinations and other non-factual responses generated by LLMs can be detected by examining the uncertainty of the LLM in its response to the pertinent pro"},"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":"2412.05563","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-07T06:56:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ceb3f8a53f4136c03b23f2809a0c034832663d1e1bf6ec9bf92ea2092e1b22f","abstract_canon_sha256":"cd454208431bb1c07fbeb735cdc4e5b582c66f441b5b9b7ba7a11652fc638e93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:21.478900Z","signature_b64":"vufSo5tEW7+eupuAWBLp6uq9puY3dAJXBU9w5yo6oWByqq8aVBHDolf5M/38Fw0ce+WBqambPilNwQJb5AhGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6536ca9ad7f3d200f226f644531b096a3c751df169b7d26ffbb86fb2484a0bfb","last_reissued_at":"2026-07-05T11:30:21.478415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:21.478415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Allen Z. Ren, Anirudha Majumdar, Justin Lidard, Ola Shorinwa, Zhiting Mei","submitted_at":"2024-12-07T06:56:01Z","abstract_excerpt":"The remarkable performance of large language models (LLMs) in content generation, coding, and common-sense reasoning has spurred widespread integration into many facets of society. However, integration of LLMs raises valid questions on their reliability and trustworthiness, given their propensity to generate hallucinations: plausible, factually-incorrect responses, which are expressed with striking confidence. Previous work has shown that hallucinations and other non-factual responses generated by LLMs can be detected by examining the uncertainty of the LLM in its response to the pertinent pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05563","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/2412.05563/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":"2412.05563","created_at":"2026-07-05T11:30:21.478473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05563v2","created_at":"2026-07-05T11:30:21.478473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05563","created_at":"2026-07-05T11:30:21.478473+00:00"},{"alias_kind":"pith_short_12","alias_value":"MU3MVGWX6PJA","created_at":"2026-07-05T11:30:21.478473+00:00"},{"alias_kind":"pith_short_16","alias_value":"MU3MVGWX6PJAB4RG","created_at":"2026-07-05T11:30:21.478473+00:00"},{"alias_kind":"pith_short_8","alias_value":"MU3MVGWX","created_at":"2026-07-05T11:30:21.478473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02289","citing_title":"DECK: A Consistency x Confidence Taxonomy of LLM Hallucinations","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24053","citing_title":"Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28500","citing_title":"Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16120","citing_title":"LLM-Powered AI Agent Systems and Their Applications in Industry","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08010","citing_title":"Measuring and mitigating overreliance to build human-compatible AI","ref_index":108,"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":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00269","citing_title":"How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17112","citing_title":"Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04638","citing_title":"Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI","json":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI.json","graph_json":"https://pith.science/api/pith-number/MU3MVGWX6PJAB4RG6ZCFGGYJNI/graph.json","events_json":"https://pith.science/api/pith-number/MU3MVGWX6PJAB4RG6ZCFGGYJNI/events.json","paper":"https://pith.science/paper/MU3MVGWX"},"agent_actions":{"view_html":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI","download_json":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI.json","view_paper":"https://pith.science/paper/MU3MVGWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05563&json=true","fetch_graph":"https://pith.science/api/pith-number/MU3MVGWX6PJAB4RG6ZCFGGYJNI/graph.json","fetch_events":"https://pith.science/api/pith-number/MU3MVGWX6PJAB4RG6ZCFGGYJNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI/action/storage_attestation","attest_author":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI/action/author_attestation","sign_citation":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI/action/citation_signature","submit_replication":"https://pith.science/pith/MU3MVGWX6PJAB4RG6ZCFGGYJNI/action/replication_record"}},"created_at":"2026-07-05T11:30:21.478473+00:00","updated_at":"2026-07-05T11:30:21.478473+00:00"}