{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QJGWLE4L276BRLY2KUXLQKEA63","short_pith_number":"pith:QJGWLE4L","schema_version":"1.0","canonical_sha256":"824d65938bd7fc18af1a552eb82880f6ff54b26adf5ad292132672b936ed0b64","source":{"kind":"arxiv","id":"2311.08718","version":2},"attestation_state":"computed","paper":{"title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bairu Hou, Jacob Andreas, Kaizhi Qian, Shiyu Chang, Yang Zhang, Yujian Liu","submitted_at":"2023-11-15T05:58:35Z","abstract_excerpt":"Uncertainty decomposition refers to the task of decomposing the total uncertainty of a predictive model into aleatoric (data) uncertainty, resulting from inherent randomness in the data-generating process, and epistemic (model) uncertainty, resulting from missing information in the model's training data. In large language models (LLMs) specifically, identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability, but remains an important open research question. In this paper, we introduce an uncertainty decomposition framework for LLM"},"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":"2311.08718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T05:58:35Z","cross_cats_sorted":[],"title_canon_sha256":"21bb4bcaefabf641553219a54faff5d1b1fd63921fde0696b2ab120e8f1ad894","abstract_canon_sha256":"b64b2dc38a804146b1ab66e4a6aa836215e743309205b9691740f92029e6c0df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:45.169216Z","signature_b64":"1H/wCWaLHcOh6A5J9VpR+EFAyOIzPlhlGYYrSHaYjWPJxG4YonFVpBVgBwioazXEbPB54Ol/LWmLBi/bQQKXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"824d65938bd7fc18af1a552eb82880f6ff54b26adf5ad292132672b936ed0b64","last_reissued_at":"2026-07-05T08:29:45.168744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:45.168744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bairu Hou, Jacob Andreas, Kaizhi Qian, Shiyu Chang, Yang Zhang, Yujian Liu","submitted_at":"2023-11-15T05:58:35Z","abstract_excerpt":"Uncertainty decomposition refers to the task of decomposing the total uncertainty of a predictive model into aleatoric (data) uncertainty, resulting from inherent randomness in the data-generating process, and epistemic (model) uncertainty, resulting from missing information in the model's training data. In large language models (LLMs) specifically, identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability, but remains an important open research question. In this paper, we introduce an uncertainty decomposition framework for LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08718","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/2311.08718/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":"2311.08718","created_at":"2026-07-05T08:29:45.168804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08718v2","created_at":"2026-07-05T08:29:45.168804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08718","created_at":"2026-07-05T08:29:45.168804+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJGWLE4L276B","created_at":"2026-07-05T08:29:45.168804+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJGWLE4L276BRLY2","created_at":"2026-07-05T08:29:45.168804+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJGWLE4L","created_at":"2026-07-05T08:29:45.168804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32032","citing_title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28778","citing_title":"Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11737","citing_title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17200","citing_title":"Calibrating Model-Based Evaluation Metrics for Summarization","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63","json":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63.json","graph_json":"https://pith.science/api/pith-number/QJGWLE4L276BRLY2KUXLQKEA63/graph.json","events_json":"https://pith.science/api/pith-number/QJGWLE4L276BRLY2KUXLQKEA63/events.json","paper":"https://pith.science/paper/QJGWLE4L"},"agent_actions":{"view_html":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63","download_json":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63.json","view_paper":"https://pith.science/paper/QJGWLE4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08718&json=true","fetch_graph":"https://pith.science/api/pith-number/QJGWLE4L276BRLY2KUXLQKEA63/graph.json","fetch_events":"https://pith.science/api/pith-number/QJGWLE4L276BRLY2KUXLQKEA63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63/action/storage_attestation","attest_author":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63/action/author_attestation","sign_citation":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63/action/citation_signature","submit_replication":"https://pith.science/pith/QJGWLE4L276BRLY2KUXLQKEA63/action/replication_record"}},"created_at":"2026-07-05T08:29:45.168804+00:00","updated_at":"2026-07-05T08:29:45.168804+00:00"}