{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RQIUB36DYIZIILFJCWBAN3WEBV","short_pith_number":"pith:RQIUB36D","schema_version":"1.0","canonical_sha256":"8c1140efc3c232842ca9158206eec40d5e433d21bfe0e1bc894062bf988598b0","source":{"kind":"arxiv","id":"2308.16175","version":2},"attestation_state":"computed","paper":{"title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiuhai Chen, Jonas Mueller","submitted_at":"2023-08-30T17:53:25Z","abstract_excerpt":"We introduce BSDetector, a method for detecting bad and speculative answers from a pretrained Large Language Model by estimating a numeric confidence score for any output it generated. Our uncertainty quantification technique works for any LLM accessible only via a black-box API, whose training data remains unknown. By expending a bit of extra computation, users of any LLM API can now get the same response as they would ordinarily, as well as a confidence estimate that cautions when not to trust this response. Experiments on both closed and open-form Question-Answer benchmarks reveal that BSDe"},"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":"2308.16175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T17:53:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28af5c6f2a0eeeaba2c22da1de548b994a8841a42afbb7ab3dcb2e7a3f6c98d7","abstract_canon_sha256":"a5f9220947613d8acb144c84cde732e4409e1e35c7d40beb520858c7109f002e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:09.877062Z","signature_b64":"2KLvdAMGW5x6TuUx80JDHOI349u94que3q1cIJqNmYumR9I7/YwnD3n87hWCHm34jdkLRoPMPA2Gubl4ncV9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c1140efc3c232842ca9158206eec40d5e433d21bfe0e1bc894062bf988598b0","last_reissued_at":"2026-07-05T06:57:09.876597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:09.876597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiuhai Chen, Jonas Mueller","submitted_at":"2023-08-30T17:53:25Z","abstract_excerpt":"We introduce BSDetector, a method for detecting bad and speculative answers from a pretrained Large Language Model by estimating a numeric confidence score for any output it generated. Our uncertainty quantification technique works for any LLM accessible only via a black-box API, whose training data remains unknown. By expending a bit of extra computation, users of any LLM API can now get the same response as they would ordinarily, as well as a confidence estimate that cautions when not to trust this response. Experiments on both closed and open-form Question-Answer benchmarks reveal that BSDe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16175","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/2308.16175/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":"2308.16175","created_at":"2026-07-05T06:57:09.876657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16175v2","created_at":"2026-07-05T06:57:09.876657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16175","created_at":"2026-07-05T06:57:09.876657+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQIUB36DYIZI","created_at":"2026-07-05T06:57:09.876657+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQIUB36DYIZIILFJ","created_at":"2026-07-05T06:57:09.876657+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQIUB36D","created_at":"2026-07-05T06:57:09.876657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24420","citing_title":"Beyond Logprobs: A Multi-Signal Confidence Engine for LLM-Based Document Field Extraction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30814","citing_title":"When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs","ref_index":60,"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":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20173","citing_title":"Qiskit Code Migration with LLMs","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2406.15927","citing_title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08346","citing_title":"Sanity Checks for Long-Form Hallucination Detection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09075","citing_title":"Optimality of Sub-network Laplace Approximations: New Results and Methods","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09106","citing_title":"Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05952","citing_title":"Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17200","citing_title":"Calibrating Model-Based Evaluation Metrics for Summarization","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV","json":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV.json","graph_json":"https://pith.science/api/pith-number/RQIUB36DYIZIILFJCWBAN3WEBV/graph.json","events_json":"https://pith.science/api/pith-number/RQIUB36DYIZIILFJCWBAN3WEBV/events.json","paper":"https://pith.science/paper/RQIUB36D"},"agent_actions":{"view_html":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV","download_json":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV.json","view_paper":"https://pith.science/paper/RQIUB36D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16175&json=true","fetch_graph":"https://pith.science/api/pith-number/RQIUB36DYIZIILFJCWBAN3WEBV/graph.json","fetch_events":"https://pith.science/api/pith-number/RQIUB36DYIZIILFJCWBAN3WEBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV/action/storage_attestation","attest_author":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV/action/author_attestation","sign_citation":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV/action/citation_signature","submit_replication":"https://pith.science/pith/RQIUB36DYIZIILFJCWBAN3WEBV/action/replication_record"}},"created_at":"2026-07-05T06:57:09.876657+00:00","updated_at":"2026-07-05T06:57:09.876657+00:00"}