{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:64CO7NPAK7ZJGO2FQVCTYFWYMU","short_pith_number":"pith:64CO7NPA","schema_version":"1.0","canonical_sha256":"f704efb5e057f2933b4585453c16d8653c1bd04ef06ff98d8820ff5e3a556193","source":{"kind":"arxiv","id":"2402.00251","version":1},"attestation_state":"computed","paper":{"title":"Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jian Zhang, Walter Talbott, Yao-Hung Hubert Tsai","submitted_at":"2024-02-01T00:23:31Z","abstract_excerpt":"Step-by-step decision planning with large language models (LLMs) is gaining attention in AI agent development. This paper focuses on decision planning with uncertainty estimation to address the hallucination problem in language models. Existing approaches are either white-box or computationally demanding, limiting use of black-box proprietary LLMs within budgets. The paper's first contribution is a non-parametric uncertainty quantification method for LLMs, efficiently estimating point-wise dependencies between input-decision on the fly with a single inference, without access to token logits. T"},"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":"2402.00251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T00:23:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"676e9bcd928c3c9c083b7a326dbaeabfa53facd0e91dead500ef23b1da78fbce","abstract_canon_sha256":"de023eb3d854869566b09c76bfd4f1a61ad7f29a40260080d0b51bb16853b538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:09.066108Z","signature_b64":"Nwpav3LI8Gcly53Du8PpjFjwDy9dmfwB90IP5N8IMzuP2aLV59Vw514PCTQgx5GdfOG+WK/HW9cYqCLNN8EkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f704efb5e057f2933b4585453c16d8653c1bd04ef06ff98d8820ff5e3a556193","last_reissued_at":"2026-07-05T07:40:09.065715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:09.065715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jian Zhang, Walter Talbott, Yao-Hung Hubert Tsai","submitted_at":"2024-02-01T00:23:31Z","abstract_excerpt":"Step-by-step decision planning with large language models (LLMs) is gaining attention in AI agent development. This paper focuses on decision planning with uncertainty estimation to address the hallucination problem in language models. Existing approaches are either white-box or computationally demanding, limiting use of black-box proprietary LLMs within budgets. The paper's first contribution is a non-parametric uncertainty quantification method for LLMs, efficiently estimating point-wise dependencies between input-decision on the fly with a single inference, without access to token logits. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00251","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/2402.00251/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":"2402.00251","created_at":"2026-07-05T07:40:09.065775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00251v1","created_at":"2026-07-05T07:40:09.065775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00251","created_at":"2026-07-05T07:40:09.065775+00:00"},{"alias_kind":"pith_short_12","alias_value":"64CO7NPAK7ZJ","created_at":"2026-07-05T07:40:09.065775+00:00"},{"alias_kind":"pith_short_16","alias_value":"64CO7NPAK7ZJGO2F","created_at":"2026-07-05T07:40:09.065775+00:00"},{"alias_kind":"pith_short_8","alias_value":"64CO7NPA","created_at":"2026-07-05T07:40:09.065775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17234","citing_title":"Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2503.18562","citing_title":"Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU","json":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU.json","graph_json":"https://pith.science/api/pith-number/64CO7NPAK7ZJGO2FQVCTYFWYMU/graph.json","events_json":"https://pith.science/api/pith-number/64CO7NPAK7ZJGO2FQVCTYFWYMU/events.json","paper":"https://pith.science/paper/64CO7NPA"},"agent_actions":{"view_html":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU","download_json":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU.json","view_paper":"https://pith.science/paper/64CO7NPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00251&json=true","fetch_graph":"https://pith.science/api/pith-number/64CO7NPAK7ZJGO2FQVCTYFWYMU/graph.json","fetch_events":"https://pith.science/api/pith-number/64CO7NPAK7ZJGO2FQVCTYFWYMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU/action/storage_attestation","attest_author":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU/action/author_attestation","sign_citation":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU/action/citation_signature","submit_replication":"https://pith.science/pith/64CO7NPAK7ZJGO2FQVCTYFWYMU/action/replication_record"}},"created_at":"2026-07-05T07:40:09.065775+00:00","updated_at":"2026-07-05T07:40:09.065775+00:00"}